The Role of Attributes in Product Quality Comparisons

Felipe Moraes, Jie Yang, Rongting Zhang, and Vanessa Murdock. (CHIIR'20)

Joint Policy-Value Learning for Recommendation

Olivier Jeunen, David Rohde, Flavian Vasile, and Martin Bompaire. (KDD'20)

Policy-Aware Unbiased Learning to Rank for Top-k Rankings

Harrie Oosterhuis, and Maarten de Rijke. (SIGIR'20)

What does BERT know about books, movies and music? Probing BERT for Conversational Recommendation

Gustavo Penha, and Claudia Hauff. (RecSys'20)

Graph-Embedding Empowered Entity Retrieval

Emma J. Gerritse, Faegheh Hasibi, and Arjen P. de Vries. (ECIR'20)

Conversations with Documents: An Exploration of Document-Centered Assistance

Maartje ter Hoeve, Robert Sim, Elnaz Nouri, Adam Fourney, Maarten de Rijke, and Ryen W. White. (CHIIR'20)

Beyond Optimizing for Clicks: Incorporating Editorial Values in News Recommendation

Feng Lu, Anca Dumitrache, and David Graus. (UMAP'20)

FairMatch: A Graph-based Approach for Improving Aggregate Diversity in Recommender Systems

Masoud Mansoury, Himan Abdollahpouri, Mykola Pechenizkiy, Bamshad Mobasher, and Robin Burke. (UMAP'20)

Assessing Viewpoint Diversity in Search Results Using Ranking Fairness Metrics

Tim Draws, Nava Tintarev, Ujwal Gadiraju, Alessandro Bozzon, and Benjamin Timmermans. (BIAS'20, ECML-PKDD Workshop)

What's in a User? Towards Personalising Transparency for Music Recommender Interfaces

Martijn Millecamp, Nyi Nyi Htun, Cristina Conati, and Katrien Verbert. (UMAP'20)

Fair Ranking with Biased Data

Thorsten Joachims, Cornell University

Abstract

Search engines and recommender systems have become the dominant matchmaker for a wide range of human endeavors -- from online retail to finding romantic partners. Consequently, they carry immense power in shaping markets and allocating opportunity to the participants. In this talk, I will discuss how the machine learning algorithms underlying these system can produce unfair or undesirable ranking policies for both exogenous and endogenous reasons. Exogenous reasons often manifest themselves as biases in the training data, which then get reflected in the learned ranking policy and lead to rich-get-richer dynamics. But even when trained with unbiased data, reasons endogenous to the algorithms can lead to unfair or undesirable allocation of opportunity. To overcome these challenges, I will present new machine learning algorithms that directly address some forms of endogenous and exogenous unfairness.

Speaker Bio

Thorsten Joachims is a Professor in the Department of Computer Science and in the Department of Information Science at Cornell University. His research interests center on a synthesis of theory and system building in machine learning, with applications in information access, language technology, and recommendation. His past research focused on counterfactual and causal inference, support vector machines, text classification, structured output prediction, convex optimization, learning to rank, learning with preferences, and learning from implicit feedback. He is an ACM Fellow, AAAI Fellow, and Humboldt Fellow.