News

Social & Information Systems

Otto Hahn Medal awarded to two MPI-SWS students

Ralf Jung and Bilal Zafar have each been awarded a 2021 Otto Hahn Medal for outstanding scientific achievement. The Max Planck Society awards the Otto Hahn Medal annually to young scientists in recognition of outstanding scientific achievement. Ralf was awarded the medal for his work on the first formal foundations for the cutting-edge systems programming language Rust, while Bilal was awarded the medal for his work on developing responsible and trustworthy AI systems that can help reduce discrimination and polarisation in society. …
Ralf Jung and Bilal Zafar have each been awarded a 2021 Otto Hahn Medal for outstanding scientific achievement. The Max Planck Society awards the Otto Hahn Medal annually to young scientists in recognition of outstanding scientific achievement. Ralf was awarded the medal for his work on the first formal foundations for the cutting-edge systems programming language Rust, while Bilal was awarded the medal for his work on developing responsible and trustworthy AI systems that can help reduce discrimination and polarisation in society. Ralf obtained his PhD in August 2020, and was advised by Derek Dreyer. Ralf is now a postdoc at MPI-SWS and research affiliate at MIT. Bilal obtained his PhD in February 2019, and was advised by Krishna Gummadi and Manuel Gomez Rodriguez. Bilal is now an Applied Scientist at Amazon Web Services.
Read more

Research Spotlight: Steering Policies in Multi-Agent Collaboration

Ever since the birth of Artificial Intelligence (AI) at the Dartmouth workshop in 1956, researchers have debated about the exact role that AI will play, and should play, in society. While some have envisioned a romanticized version of AI, incorporated into the narratives of 20th century movies, successful AI developments are often closer to J. C. R. Licklider’s vision of AI, which puts an emphasis on a collaborative relationship between humans and AI, and focuses on hybrid human-AI decision making. …
Ever since the birth of Artificial Intelligence (AI) at the Dartmouth workshop in 1956, researchers have debated about the exact role that AI will play, and should play, in society. While some have envisioned a romanticized version of AI, incorporated into the narratives of 20th century movies, successful AI developments are often closer to J. C. R. Licklider’s vision of AI, which puts an emphasis on a collaborative relationship between humans and AI, and focuses on hybrid human-AI decision making.

In the Multi-Agent Systems group at MPI-SWS, we study multi-agent sequential decision making using formal frameworks that can capture nuances often presented in human-AI collaborative settings. Specifically, we study different aspects of agent-to-agent interaction in settings where agents share a common goal, but can have different perceptions of reality. The overall goal is to design a more effective AI decision maker that accounts for the behavior of its collaborators, and compensates for their imperfections. To achieve this goal, the AI decision maker can use steering policies to nudge its collaborators to adopt better policies, i.e., policies that lead to an improved joint outcome. In what follows, we summarize some of our recent results related to this agenda.

Accounting for misaligned world-views. An effective way to model behavioral differences between humans and modern AI tools (based on machine learning) is through a model that captures the misalignment in how the agents perceive their environment. Using this approach, we have proposed a new computational model, called Multi-View Decision Process, suitable for modeling two-agent cooperative scenarios in which agents agree on their goals, but disagree on how their actions affect the state of the world [1]. This framework enables us to formally analyze the utility of accounting for the misalignment in agents’ world-views when only one of the agents has a correct model of the world. Our results show that modeling such a misalignment is not only beneficial, but critical. The main takeaway is that to facilitate a more successful collaboration among agents, it is not sufficient to make one agent (more) accurate in its world-view: naively improving the accuracy of one agent can degrade the joint performance unless one explicitly accounts for the imperfections of the other agent. To this end, we have developed an algorithm for finding an approximately optimal steering policy for the agent with the correct world-view.

Adapting to a non-stationary collaborator. In addition to accounting for a misalignment in world-views, decision makers must also account for the effects of their behavior on other agents. Namely, decision makers respond to each other's behavior, leading to behavior which is non-stationary and changes over time. In the context of human-AI collaboration, this might happen if the human agent changes their behavior over time, for example, as it learns to interact with the AI agent. Such non-stationary behavior of the human agent could have a negative impact on the collaboration, and can lead to a substantially worse performance unless the AI agent adapts to the changing behavior of the human agent. We can model this situation with a two-agent setting similar to the one presented above, but which allows agents to change their behavior as they interact over time [2]. The agent with the correct world-view now has to adapt to the non-stationary behavior of its collaborator. We have proposed a learning procedure that has provable guarantees on the joint performance under the assumption that the behavior of the other agent is not abruptly changing over time. We have shown that this assumption is not trivial to relax in that obtaining the same guarantees without this assumption would require solving a computationally intractable problem.

Steering via environment design. The previous two cases consider indirect steering policies for which the agent with the correct model implicitly influences the behavior of its collaborator by acting in the world. A more explicit influence would be obtained if the actions of this agent are directly changing the world-view of its collaborator. In the context of human-AI collaboration, the AI agent could shape the environment to nudge the human agent to adopt a more efficient decision policy. This can be done through reward shaping, i.e., by making some actions more costly for humans in terms of effort, or through dynamics shaping, i.e., by changing the perceived influence that the human’s actions have on the world. In the machine learning terminology, such a steering strategy is nothing else but a form of an adversarial attack of the AI agent (attacker) on the human agent. In our recent work [3], we have characterized how to optimally perform these types of attacks and how costly they are from an attacker’s point of view.

 

References: 

[1] Dimitrakakis, C., Parkes, D.C., Radanovic, G. and Tylkin, P., 2017. Multi-view Decision Processes: The Helper-AI Problem. In Advances in Neural Information Processing Systems.

[2] Radanovic, G., Devidze, R., Parkes, D. and Singla, A., 2019. Learning to Collaborate in Markov Decision Processes. In International Conference on Machine Learning.

[3] Rakhsha, A., Radanovic, G., Devidze, R., Zhu, X. and Singla, A., 2020. Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning. In International Conference on Machine Learning.
Read more

Manuel Gomez-Rodriguez awarded ERC Starting Grant

September 2020
Manuel Gomez-Rodriguez, head of the MPI-SWS Human-Centric Machine Learning group, has been awarded an ERC Starting Grant. Over the next five years, his project "Human-Centric Machine Learning" will receive 1.49 million euros, which will allow the group to develop the foundations of human-centric machine learning.

In the most recent round for Starting Grants, over 3300 research proposals were submitted to the ERC. The sole selection criterion is scientific excellence. This year, less than 14% of all ERC Starting Grant applicants across all scientific disciplines received the award, …
Manuel Gomez-Rodriguez, head of the MPI-SWS Human-Centric Machine Learning group, has been awarded an ERC Starting Grant. Over the next five years, his project "Human-Centric Machine Learning" will receive 1.49 million euros, which will allow the group to develop the foundations of human-centric machine learning.

In the most recent round for Starting Grants, over 3300 research proposals were submitted to the ERC. The sole selection criterion is scientific excellence. This year, less than 14% of all ERC Starting Grant applicants across all scientific disciplines received the award, with only 20 awardees in Computer Science across all of Europe!

Summary of the HumanML project proposal


With the advent of mass-scale digitization of information and virtually limitless computational power, an increasing number of social, information and cyber-physical systems evaluate, support or even replace human decisions using machine learning models and algorithms. Machine learning models and algorithms have been traditionally designed to take decisions autonomously, without human intervention, on the basis of passively collected data. However, in most social, information and cyber-physical systems, algorithmic and human decisions feed on and influence each other. As these decisions become more consequential to individuals and society, machine learning models and algorithms have been blamed for playing a major role in an increasing number of missteps, from discriminating against minorities, causing car accidents and increasing polarization to misleading people in social media.

In this project, we will develop human-centric machine learning models and algorithms for evaluating, supporting and enhancing decision-making processes where algorithmic and human decisions feed on and influence each other. These models and algorithms will account for the feedback loop between algorithmic and human decisions, which currently perpetuates or even amplifies biases and inequalities, and they will learn to operate under different automation levels. Moreover, they will anticipate how individuals will react to their algorithmic decisions, often strategically, to receive beneficial decisions and they will provide actionable insights about their algorithmic decisions. Finally, we will perform observational and interventional experiments as well as realistic simulations to evaluate their effectiveness in a wide range of applications, from content moderation, recidivism prediction, and credit scoring to medical diagnosis and autonomous driving.
Read more

Two MPI-SWS papers accepted at ICML 2020

July 2020
The following two MPI-SWS papers have been accepted to ICML 2020, one of the flagship conferences in machine learning:

  • Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning by Amin Rakhsha, Goran Radanovic, Rati Devidze, Xiaojin Zhu, Adish Singla.

  • Adaptive Reward-Poisoning Attacks against Reinforcement Learning by Xuezhou Zhang, Yuzhe Ma, Adish Singla, Xiaojin Zhu.

Isabel Valera becomes full professor at Saarland University

April 2020
Isabel Valera, a postdoc alumni of the Human-Centric Machine Learning group, has become full professor in the Department of Computer Science at Saarland University. Congratulations Isabel!

Isabel's research focuses on developing machine learning methods that are flexible, robust, interpretable and fair. Her research can be applied in a broad range of fields, from medicine and psychiatry to social and communication systems. You can find out more about her work at https://ivaleram.github.io/.

Three MPI-SWS papers accepted at AAAI 2020

February 2020
The following three MPI-SWS papers have been accepted to AAAI 2020, one of the flagship conferences in artificial intelligence:

  • Incremental Fairness in Two-Sided Market Platforms: On Smoothly Updating Recommendations by Gourab K. PatroAbhijnan ChakrabortyNiloy GangulyKrishna P. Gummadi.

  • Regression Under Human Assistance by Abir De, Paramita Koley, Niloy Ganguly, Manuel Gomez-Rodriguez.

  • The Effectiveness of Peer Prediction in Long-Term Forecasting by Debmalya Mandal, Goran RadanovicDavid C. Parkes.

Machine Teaching seminar at Saarland University

September 2019
MPI-SWS faculty member Adish Singla is teaching a seminar on Machine Teaching at Saarland University in the Winter 2019/2020 semester.

Three MPI-SWS papers accepted at NeurIPS 2019

September 2019
The following three MPI-SWS papers have been accepted to NeurIPS 2019, the flagship conference in machine learning:

  • Teaching Multiple Concepts to a Forgetful Learner

  • Learner-aware Teaching: Inverse Reinforcement Learning with Preferences and Constraints

  • Preference-Based Batch and Sequential Teaching: Towards a Unified View of Models


 

MPI-SWS researchers receive Microsoft Research PhD Scholarship

September 2019
Researchers from the Machine Teaching Group at MPI-SWS have won a Microsoft Research PhD Scholarship for the project "Reinforcement Learning for Enabling Next-Generation Human-Machine Partnerships". The scholarship provides funding for one PhD student. More details about the scholarship programme can be found here.

Goran Radanovic joins MPI-SWS

September 2019
Goran Radanovic joined MPI-SWS as a research group leader on Sep 16, 2019. He is generally interested in studying AI systems, and more specifically in the design and analysis of systems with intelligent and self-interested agents. Particular topics of interest include value-aligned artificial intelligence, human-AI collaboration, and decision making systems with societally-aware utility functions. 

Prior to joining MPI-SWS, he was a postdoctoral researcher at Harvard University, where he worked with Prof. David C. Parkes. …
Goran Radanovic joined MPI-SWS as a research group leader on Sep 16, 2019. He is generally interested in studying AI systems, and more specifically in the design and analysis of systems with intelligent and self-interested agents. Particular topics of interest include value-aligned artificial intelligence, human-AI collaboration, and decision making systems with societally-aware utility functions. 

Prior to joining MPI-SWS, he was a postdoctoral researcher at Harvard University, where he worked with Prof. David C. Parkes. He received his Ph.D. in Computer Science from the Swiss Federal Institute of Technolgy in Lausanne (EPFL), under the supervision of Prof. Boi Faltings. He obtained his Master’s and Bachelor’s degrees in Computer Science fromthe Faculty of Electrical Engineering and Computing at the University of Zagreb.
Read more

Krishna Gummadi appointed MPI-SWS Director

May 2019
Krishna Gummadi has accepted the position of scientific member of the Max Planck Society and director at the MPI for Software Systems, effective 1 June 2019. Krishna has been a faculty member at the institute since July 2005. 

Krishna's appointment solidifies our institute's foothold in the emerging area of social computing and secures Krishna's leadership and contributions to the institute for the future.

Junior Research Group leader positions at MPI-SWS

April 2019
The Max Planck Institute for Software Systems (MPI-SWS) is inviting applications for Junior Research Group leader positions in systems and machine learning (SysML), human-oriented machine learning (fairness, accountability, transparency, and ethical aspects of AI), adversarial ML, reinforcement learning,  human-computer interaction with ML/social aspects, natural language processing, and learning & cognitive sciences.

Our Junior Research Group program offers young scientists the opportunity to develop their own research program. The position is funded for 5 years with the possibility of a 2-year extension. …
The Max Planck Institute for Software Systems (MPI-SWS) is inviting applications for Junior Research Group leader positions in systems and machine learning (SysML), human-oriented machine learning (fairness, accountability, transparency, and ethical aspects of AI), adversarial ML, reinforcement learning,  human-computer interaction with ML/social aspects, natural language processing, and learning & cognitive sciences.

Our Junior Research Group program offers young scientists the opportunity to develop their own research program. The position is funded for 5 years with the possibility of a 2-year extension. Applicants must have completed a doctoral degree in computer science or related areas and must have demonstrated outstanding research vision and potential to successfully lead a research group. Successful candidates are expected to build a highly visible research agenda, to mentor junior scientists, and to participate in collaborative projects.

The Max Planck Institute for Software Systems is located in Saarbruecken and Kaiserslautern in Germany. We maintain an open, international, and diverse work environment and seek applications from outstanding researchers regardless of national origin. Our working language is English. We collaborate with several major research institutions worldwide and have high international visibility. There is generous travel, administrative, and technical support available for all group members.

Please apply at https://apply.mpi-sws.org/ under ``Research Group Leader''. You need to upload your CV, a research plan, an optional teaching statement, and 3-5 references. Reviewing of applications will commence on 15 May 2019 and will continue until the positions are filled. The expecting starting date for the position is Fall 2019. Informal inquiries can be addressed to applications-sis@mpi-sws.org.

The Max Planck Society is committed to employing more individuals with disabilities and expressly welcomes them to apply. The Max Planck Society seeks to increase the percentage of women in the areas where they are underrepresented and expressly welcomes them to apply.
Read more

MPI-SWS article published in the Proceedings of Academy of Sciences (PNAS)

January 2019
The article "Enhancing Human Learning via spaced repetition optimization", coauthored by MPI-SWS and MPI-IS researchers, has been published in the Proceedings of the National Academy of Sciences (PNAS), a highly prestigious journal.

The (open-access) article can be found here: https://www.pnas.org/content/early/2019/01/18/1815156116.

Krishna Gummadi and Alan Mislove awarded a Facebook "Secure the Internet" grant

October 2018
MPI-SWS faculty member Krishna Gummadi and MPI-SWS alumnus Alan Mislove have been awarded a "Secure the Internet" grant by Facebook. Their proposal, “Towards privacy-protecting aggregate statistics in PII-based targeted advertising,” has been awarded $60,000 to develop techniques for revealing advertising statistics that provide hard guarantees of user privacy, based on a (principles-first) approach. Their goal is to develop a differential privacy-like approach that can be applied to existing advertising systems.

The Facebook "Secure the Internet" grant program is designed to improve the security, …
MPI-SWS faculty member Krishna Gummadi and MPI-SWS alumnus Alan Mislove have been awarded a "Secure the Internet" grant by Facebook. Their proposal, “Towards privacy-protecting aggregate statistics in PII-based targeted advertising,” has been awarded $60,000 to develop techniques for revealing advertising statistics that provide hard guarantees of user privacy, based on a (principles-first) approach. Their goal is to develop a differential privacy-like approach that can be applied to existing advertising systems.

The Facebook "Secure the Internet" grant program is designed to improve the security, privacy, and safety of internet users. Gummadi and Mislove's proposal was one of only 10 winning proposals, which were together awarded more than $800,000 by Facebook.
Read more

Five MPI-SWS papers accepted at NIPS 2018

October 2018
The following five MPI-SWS papers have been accepted to NIPS 2018, the flagship conference in machine learning:

  • Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Making

  • Teaching Inverse Reinforcement Learners via Features and Demonstrations

  • Understanding the Role of Adaptivity in Machine Teaching: The Case of Version Space Learners

  • Deep Reinforcement Learning of Marked Temporal Point Processes

  • Enhancing the Accuracy and Fairness of Human Decision Making


 

Research Spotlight: Learning to interact with learning agents

Many real-world systems involve repeatedly making decisions under uncertainty—for instance, choosing one of the several products to recommend to a user in an online recommendation service, or dynamically allocating resources among available stock options in a financial market. Machine learning (ML) algorithms driving these systems typically operate under the assumption that they are interacting with static components, e.g., users' preferences are fixed, trading tools providing stock recommendations are static, and data distributions are stationary. This assumption is often violated in modern systems, …
Many real-world systems involve repeatedly making decisions under uncertainty—for instance, choosing one of the several products to recommend to a user in an online recommendation service, or dynamically allocating resources among available stock options in a financial market. Machine learning (ML) algorithms driving these systems typically operate under the assumption that they are interacting with static components, e.g., users' preferences are fixed, trading tools providing stock recommendations are static, and data distributions are stationary. This assumption is often violated in modern systems, as these algorithms are increasingly interacting with and seeking information from learning agents including people, robots, and adaptive adversaries. Consequently, many well-studied ML frameworks and algorithmic techniques fail to provide desirable theoretical guarantees—for instance, algorithms might converge to a sub-optimal solution or fail arbitrarily bad in these settings.

Researchers at the Machine Teaching Group, MPI-SWS are designing novel ML algorithms that have to interact with agents that are adaptive or learning over time, especially in situations when the algorithm's decisions directly affect the state dynamics of these agents. In recent work [1], they have studied the above-mentioned problem in the context of two fundamental machine learning frameworks: (i) online learning using experts' advice and (ii) active learning using labeling oracles. In particular, they consider a setting where experts/oracles themselves are learning agents. For instance, active learning algorithms typically query labels from an oracle, e.g., a (possibly noisy) domain expert; however, in emerging crowd-powered systems, these experts are getting replaced by inexpert participants who could themselves be learning over time (e.g., volunteers in citizen science projects). They have shown that when these experts/oracles themselves are learning agents, well-studied algorithms (like the EXP3 algorithm) fail to converge to the optimal solution and can have arbitrarily bad performance for this new problem setting. Furthermore, they provide an impossibility result showing that without sharing any information across experts, it is impossible to achieve convergence guarantees. This calls for developing novel algorithms with practical ways of coordination between the central algorithm and learning agents to achieve desired guarantees.

Currently, researchers at the Machine Teaching Group are studying these challenges in the context of designing next-generation human-AI collaborative systems. As a concrete application setting, consider a car driving scenario where the goal is to develop an assistive AI agent to drive the car in an auto-pilot mode, but giving control back to the human driver in safety-critical situations. They study this setting by casting it as a multi-agent reinforcement learning problem. When the human agent has a stationary policy (i.e., the actions take by the human driver in different states/scenarios are fixed), it is trivial to learn an optimal policy for the AI agent that maximizes the overall performance of this collaborative system. However, in real-life settings where a human driver would adapt their behavior in response to the presence of an auto-pilot mode, they show that the problem of learning an optimal policy for the AI agent becomes computationally intractable. This work is one of the recent additions to an expanding set of results and algorithmic techniques developed by MPI-SWS researchers in the nascent area of Machine Teaching [2, 3].

References


[1] Adish Singla, Hamed Hassani, and Andreas Krause. Learning to Interact with Learning Agents. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI'18), 2018.

[2] Xiaojin Zhu, Adish Singla, Sandra Zilles, and Anna N. Rafferty. An Overview of Machine Teaching. arXiv 1801.05927, 2018.

[3] Maya Cakmak, Anna N. Rafferty, Adish Singla, Xiaojin Zhu, and Sandra Zilles. Workshop on Teaching Machines, Robots, and Humans. NIPS 2017.
Read more

Krishna Gummadi awarded ERC Advanced Grant

September 2018
Krishna Gummadi, head of the MPI-SWS Networked Systems group, has been awarded an ERC Advanced Grant. Over the next five years, his project "Foundations of Fair Social Computing" will receive 2.49 million euros, which will allow the group to develop the foundations for fair social computing in the future.

In the most recent round for Advanced Grants, a total of 2,167 research proposals were submitted to the ERC out of which merely 12% were selected for funding. …
Krishna Gummadi, head of the MPI-SWS Networked Systems group, has been awarded an ERC Advanced Grant. Over the next five years, his project "Foundations of Fair Social Computing" will receive 2.49 million euros, which will allow the group to develop the foundations for fair social computing in the future.

In the most recent round for Advanced Grants, a total of 2,167 research proposals were submitted to the ERC out of which merely 12% were selected for funding. The sole selection criterion is scientific excellence.

Summary of the Fair Social Computing project proposal


Social computing represents a societal-scale symbiosis of humans and computational systems, where humans interact via and with computers, actively providing inputs to influence---and in turn being influenced by---the outputs of the computations. Social computations impact all aspects of our social lives, from what news we get to see and who we meet to what goods and services are offered at what price and how our creditworthiness and welfare benefits are assessed. Given the pervasiveness and impact of social computations, it is imperative that social computations be fair, i.e., perceived as just by the participants subject to the computation. The case for fair computations in democratic societies is self-evident: when computations are deemed unjust, their outcomes will be rejected and they will eventually lose their participants.

Recently, however, several concerns have been raised about the unfairness of social computations pervading our lives, including

  1. the existence of implicit biases in online search and recommendations,

  2. the potential for discrimination in machine learning based predictive analytics, and

  3. a lack of transparency in algorithmic decision making, with systems providing little to no information about which sensitive user data they use or how they use them.


Given these concerns, we need reliable ways to assess and ensure the fairness of social computations. However, it is currently not clear how to determine whether a social computation is fair, how we can compare the fairness of two alternative computations, how to adjust a computational method to make it more fair, or how to construct a fair method by design. This project will tackle these challenges in turn. We propose a set of comprehensive fairness principles, and will show how to apply them to social computations. In particular, we will operationalize fairness, so that it can be measured from empirical observations. We will show how to characterize which fairness criteria are satisfied by a deployed computational system. Finally, we will show how to synthesize non-discriminatory computations, i.e., how to learn an algorithm from training data that satisfies a given fairness principle.
Read more

Four MPI-SWS papers accepted at AAAI 2018

February 2018
Four papers from MPI-SWS have been accepted to AAAI 2018:
  • Beyond Distributive Fairness in Algorithmic Decision Making: Feature Selection for Procedurally Fair Learning
  • Learning to Interact with Learning Agents
  • Information Gathering with Peers: Submodular Optimization with Peer-Prediction Constraints
  • Learning User Preferences to Incentivize Exploration in the Sharing Economy

Three MPI-SWS papers accepted at WWW 2018

February 2018
Three papers from MPI-SWS have been accepted to the 2018 Web Conference:

  • Human Perceptions of Fairness in Algorithmic Decision Making: A Case Study of Criminal Risk Prediction

  • On the Causal Effect of Badges

  • Fake News Detection in Social Networks via Crowd Signals

Research Spotlight: Teaching machine learning algorithms to be fair

Machine learning algorithms are increasingly being used to automate decision making in several domains such as hiring, lending and crime-risk prediction. These algorithms have shown significant promise in leveraging large or “big” training datasets to achieve high prediction accuracy, sometimes surpassing even human accuracy.

Unfortunately, some recent investigations have shown that machine learning algorithms can also lead to unfair outcomes. For example, a recent ProPublica study found that COMPAS,

Machine learning algorithms are increasingly being used to automate decision making in several domains such as hiring, lending and crime-risk prediction. These algorithms have shown significant promise in leveraging large or “big” training datasets to achieve high prediction accuracy, sometimes surpassing even human accuracy.

Unfortunately, some recent investigations have shown that machine learning algorithms can also lead to unfair outcomes. For example, a recent ProPublica study found that COMPAS, a tool used in US courtrooms for assisting judges with crime risk prediction, was unfair towards black defendants. In fact, several studies from governments, regulatory authorities, researchers as well as civil rights groups have raised concerns about machine learning potentially acting as a tool for perpetuating existing unfair practices in society, and worse, introducing new kinds of unfairness in prediction tasks. As a consequence, a flurry of recent research has focused on defining and implementing appropriate computational notions of fairness for machine learning algorithms.



Parity-based fairness


Existing computational notions of fairness in the machine learning literature are largely inspired by the concept of discrimination in social sciences and law. These notions require the decision outcomes to ensure parity (i.e. equality) in treatment and in impact.

Notions based on parity in treatment require that the decision algorithm should not take into account the sensitive feature information (e.g., gender, race) of a user. Notions based on parity in impact require that the decision algorithm should give beneficial decision outcomes (e.g., granting a loan) to similar percentages of people from all sensitive feature groups (e.g., men, women).

However, in many cases, these existing notions are too stringent and can lead to unexpected side effects. For example, ensuring parity has been shown to lead to significant reductions in prediction accuracy. Parity may also lead to scenarios where none of the groups involved in decision making (e.g., neither men nor women) get beneficial outcomes. In other words, these scenarios might be preferred neither by the decision maker using the algorithm (due to diminished accuracy), nor by the groups involved (due to very little benefits).

User preferences and fairness


In recent work, to appear at NIPS 2017, researchers at MPI-SWS have introduced two new computational notions of algorithmic fairness: preferred treatment and preferred impact. These notions are inspired by ideas related to envy-freeness and bargaining problem in economics and game theory. Preferred treatment and preferred impact leverage these ideas to build more accurate solutions that are preferable for both the decision maker and the user groups.

The new notion of preferred treatment allows basing the decisions on sensitive feature information (thereby relaxing the parity treatment criterion) as long as the decision outcomes do not lead to envy. That is, each group of users prefers their own group membership over other groups and does not feel that presenting itself to the algorithm as another group would have led to better outcomes for the group.

The new notion of preferred impact allows differences in beneficial outcome rates for different groups (thereby relaxing the parity impact criterion) as long as all the groups get more beneficial outcomes than what they would have received under the parity impact criterion.

In their work, MPI-SWS researchers have developed a technique to ensure machine learning algorithms satisfy preferred treatment and / or preferred impact. They also tested their technique by designing crime-predicting machine-learning algorithms that satisfy the above-mentioned notions. In their experiments, they show that preference-based fairness notions can provide significant gains in overall decision-making accuracy as compared to parity-based fairness, while simultaneously increasing the beneficial outcomes for the groups involved.

This work is one of the most recent additions to an expanding set of techniques developed by MPI-SWS researchers to enable fairness, accountability and interpretability of machine learning algorithms.

References


Bilal Zafar, Isabel Valera, Manuel Gomez Rodriguez, Krishna Gummadi and Adrian Weller. From Parity to Preference: Learning with Cost-effective Notions of Fairness. Neural Information Processing Systems (NIPS), Long Beach (CA, USA), December 2017
Read more

MPI-SWS paper accepted into WSDM '18

November 2017
The paper "Leveraging the Crowd to Detect and Reduce the Spread of Fake News and Misinformation " by MPI-SWS researchers, in collaboration with researchers at KAIST and MPI-IS, has been accepted to WSDM 2018, one of the flagship conferences in data mining.

WSDM will take place in Los Angeles (CA, USA) in February 2018.

MPI-SWS paper accepted into NIPS '17

September 2017
The paper "From Parity to Preference: Learning with Cost-effective Notions of Fairness" by MPI-SWS researchers, in collaboration with researchers at the University of Cambridge and MPI-IS, has been accepted to NIPS 2017, the flagship conference in machine learning.

NIPS will take place in Long Beach (CA, USA) in December 2017.

Krishna Gummadi and Peter Druschel win ACM SIGCOMM test-of-time award

July 2017
MPI-SWS researchers—faculty members Krishna Gummadi and Peter Druschel and former SWS doctoral students Alan Mislove and Massimiliano Marcon—have received the ACM SIGCOMM Test of Time Award for their IMC 2007 paper on "Measurement and Analysis of Online Social Networks." The work was done in collaboration with Bobby Bhattacharjee of the University of Maryland.

The award citation reads as follows: "This is one of the first papers that examine multiple online social networks at scale. …
MPI-SWS researchers—faculty members Krishna Gummadi and Peter Druschel and former SWS doctoral students Alan Mislove and Massimiliano Marcon—have received the ACM SIGCOMM Test of Time Award for their IMC 2007 paper on "Measurement and Analysis of Online Social Networks." The work was done in collaboration with Bobby Bhattacharjee of the University of Maryland.

The award citation reads as follows: "This is one of the first papers that examine multiple online social networks at scale. By introducing novel measurement techniques, the paper has had an enduring influence on the analysis, modeling and design of modern social media and social networking services."
The ACM SIGCOMM Test of Time Award is a retrospective award. It recognizes papers published 10 to 12 years in the past in Computer Communication Review or any SIGCOMM sponsored or co-sponsored conference that is deemed to be an outstanding paper whose contents are still a vibrant and useful contribution today.

Read more

Adish Singla to join MPI-SWS as tenure-track faculty



Adish Singla is joining us from ETH Zurich, where he has completed his Ph.D. in computer science. His research focuses on designing new machine learning frameworks and developing algorithmic techniques, particularly for situations where people are an integral part of computational systems. Adish joins the institute as a tenure-track faculty member, effective Oct 1, 2017.

Before starting his Ph.D., he worked as a Senior Development Lead in Bing Search for over three years. …


Adish Singla is joining us from ETH Zurich, where he has completed his Ph.D. in computer science. His research focuses on designing new machine learning frameworks and developing algorithmic techniques, particularly for situations where people are an integral part of computational systems. Adish joins the institute as a tenure-track faculty member, effective Oct 1, 2017.

Before starting his Ph.D., he worked as a Senior Development Lead in Bing Search for over three years. Adish received his Bachelor's degree from IIT Delhi and his Master's degree from EPFL. He is a recipient of the Facebook Fellowship in the area of Machine Learning, the Microsoft Research Tech Transfer Award, and the Microsoft Gold Star Award.

Read more

Best Paper Award Honorable Mention at WWW '17

April 2017
The MPI-SWS paper "Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate" has received a Best Paper Award Honorable Mention at WWW 2017.

The 26th International World Wide Web Conference (WWW) took place in Perth (Australia) in April 2017.

Five MPI-SWS papers accepted at WWW '17

December 2016
Five papers from MPI-SWS have been accepted to WWW 2017:

  • Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment

  • Modeling the Dynamics of Online Learning Activity

  • Distilling Information Reliability and Source Trustworthiness from Digital Traces

  • Optimizing the Recency-Relevancy Trade-off in Online News Recommendations

  • Predicting the Success of Online Petitions Leveraging Multi-dimensional Time-Series


The 26th International World Wide Web Conference (WWW) will take place in Perth, Australia in April 2017.

Two MPI-SWS papers accepted at WSDM'17

October 2016
Two papers from MPI-SWS were accepted to ACM WSDM 2017:

  • RedQueen: An Online Algorithm for Smart Broadcasting in Social Networks

  • Uncovering the Dynamics of Crowdlearning and the Value of Knowledge

Isabel Valera and Rijurekha Sen awarded Humboldt fellowships

MPI-SWS postdoctoral fellows Isabel Valera and Rijurekha Sen have each received a two-year Humboldt postdoctoral fellowship. The fellowship enables highly-qualified scientists from abroad to spend extended periods of research in Germany. Dr. Valera recently joined the newly created Learning in Networks research group and Dr. Sen collaborates with both the MPI-SWS Distributed Systems and Social Computing research groups.

Rijurekha Sen receives ACM-India Doctoral Dissertation Award

MPI-SWS postdoctoral fellow Rijurekha won the 2014 Best Doctoral Dissertation Award by ACM-India for her thesis titled "Different Sensing Modalities for Traffic Monitoring in Developing Regions" Dr. Sen recently joined the MPI-SWS Distributed Systems and Social Computing research groups.

Saptarshi Ghosh awarded Humboldt fellowship

October 2014
MPI-SWS postdoctoral fellow Saptarshi Ghosh has been awarded a one-year Humboldt postdoctoral fellowship. The fellowship enables highly-qualified scientists from abroad to spend extended periods of research in Germany. Dr. Ghosh will be spending his fellowship year with the MPI-SWS Social Computing research group.

MPI-SWS research in the New York Times

September 2014
MPI-SWS faculty Cristian Danescu-Niculescu-Mizil's work on linguistic change was mentioned in The New York Times. This is joint work with Robert West, Dan Jurafsky, Jure Leskovec, Christopher Potts.

MPI-SWS researchers receive SOUPS distinguished paper award

July 2014
Krishna Gummadi, Mainack Mondal and Bimal Viswanath, along with Yabing Liu and MPI-SWS alumni Alan Mislove, have received a distinguished paper award at SOUPS 2014, for their paper "Understanding and Specifying Social Access Control Lists."

MPI-SWS research in the news

MPI-SWS faculty member Cristian Danescu-Niculescu-Mizil has had his work on how to ask for a favor featured on various media outlets including the Huffington Post, Gizmodo, Lifehacker, Slate's Future Tense blog, ABC News and Süddeutsche Zeitung. Links to all the articles can be found here. This is joint work with Tim Althoff and Dan Jurafsky.

Cristian Danescu-Niculescu-Mizil quoted by ABC News

August 2013
MPI-SWS faculty member Cristian Danescu-Niculescu-Mizil was quoted in a recent ABC News article about social bias effects in social media.

MPI-SWS student receives Google Scholarship

MPI-SWS PhD student Juhi Kulshrestha was awarded a Google Anita Borg Scholarship. She joins Ezgi Cicek, who received an Anita Borg Scholarship in 2012. Juhi previously received a 2011 Google Fellowship for her work in social networking.

Cristian Danescu-Niculescu-Mizil wins WWW best paper award

MPI-SWS faculty member Cristian Danescu-Niculescu-Mizil, along with his co-authors, has won the 2013 WWW Best Paper Award for his paper "No Country for Old Members: User Lifecycle and Linguistic Change in Online Communities."

Two new faculty to join MPI-SWS

We are pleased to announce that two new faculty will join MPI-SWS.

allen

Allen Clement obtained his Ph.D. at the University of Texas at Austin in 2011. Allen's research aims at designing and building systems that continue to work despite the myriad of things that go 'wrong' in deployed systems, including broken components, malicious adversaries, and benign race conditions. His research builds on techniques from distributed systems, security, fault tolerance, and game theory. …
We are pleased to announce that two new faculty will join MPI-SWS.

allen

Allen Clement obtained his Ph.D. at the University of Texas at Austin in 2011. Allen's research aims at designing and building systems that continue to work despite the myriad of things that go 'wrong' in deployed systems, including broken components, malicious adversaries, and benign race conditions. His research builds on techniques from distributed systems, security, fault tolerance, and game theory.

cristian

Cristian Danescu-Niculescu-Mizil is joining us from Cornell University, where he obtained his PhD in computer science. Cristian's research aims at developing computational frameworks that can lead to a better understanding of human social behavior, by unlocking the unprecedented potential of the large amounts of natural language data generated online. His work tackles problems related to conversational behavior, opinion mining, computational semantics and computational advertising.
Read more

MPI-SWS researchers win ICWSM best paper award

Krishna Gummadi and Farshad Kooti, along with Winter Mason and previous MPI-SWS postdoctoral fellow Meeyoung Cha, have received a best paper award at ICWSM 2012, for their paper "The Emergence of Conventions in Online Social Networks."

MPI-SWS research in the news

A recent WWW 2012 paper by Krishna Gummadi, Bimal Viswanath, and their coauthors was covered by GigaOM, a popular technology news blog, in an article titled Who's to blame for Twitter spam? Obama, Gaga, and you.


Steven le Blond's work on security flaws in Skype and other peer-to-peer applications has been receiving global media attention: WSJ, Le Monde (French), die Zeit (German), Daily Mail, New Scientist, Slashdot, Wired, and the New Scientist "One Percent" blog.

MPI-SWS study exposing Facebook privacy leak attracts global media attention

A study by MPI-SWS researchers Saikat Guha (now at Microsoft Research), Bin Cheng, and Paul Francis has been highlighted on CNN, NPR, The Washington Post, Fox News, and other major media outlets.

The study, which will be presented at the ACM Internet Measurement Conference (IMC) in November, looks at the targeting behavior of Google and Facebook. While the goal of the study was to understand targeting in general,

A study by MPI-SWS researchers Saikat Guha (now at Microsoft Research), Bin Cheng, and Paul Francis has been highlighted on CNN, NPR, The Washington Post, Fox News, and other major media outlets.

The study, which will be presented at the ACM Internet Measurement Conference (IMC) in November, looks at the targeting behavior of Google and Facebook. While the goal of the study was to understand targeting in general, the researchers discovered that gay Facebook users can unknowingly reveal to advertisers that they are gay simply by clicking on an ad targeted to gay men. The ads appear innocuous in that they make no mention of targeting gay users (for instance, an ad for a nursing degree). A user's sexual orientation can be leaked even if the user made his sexual orientation private using Facebook's privacy settings.


This study was done as part of a broader research project to design techniques for making advertising more private.
Read more

MPI-SWS researchers receive ICWSM best paper award

Congratulations to Meeyoung Cha, Juan Antonio Navarro Perez, and Hamed Haddadi. Their paper "Flash Floods and Ripples: The Spread of Media Content through the Blogosphere" was selected as the ICWSM'09 best paper using the Spinn3r dataset. The winning paper was selected out of all papers in the main conference and the data challenge workshop that used the 2009 Spinn3r blog dataset.

Visiting Professor Patrick Loiseau receives Humboldt award

Patrick Loiseau, an Assistant Professor in the Data Science department at EURECOM, has been selected for a prestigious Humboldt Research Award from the Alexander von Humboldt Foundation. This award provides support for him to spend up to a year at the institute, where he will work with Krishna Gummadi and other MPI-SWS researchers on security and privacy issues in social computing systems.