Ashudeep Singh

ashudeep@cs.cornell.edu

349, Bill and Melinda Gates Hall

107 Hoy Rd

Ithaca, NY-14853

I am a Ph.D. Candidate in Computer Science at Cornell University in Ithaca, NY. I am advised by Thorsten Joachims. I am fortunate to have Solon Barocas, Karthik Sridharan, and David Mimno on my dissertation committee.

My research spans the broad areas of Machine Learning, Recommender Systems, and Information Retrieval. My research focuses on:

Building machine learning models and algorithms to learn from interactive user feedback in user-facing platforms such as search and recommendation.
Fairness and Responsibility aspects of Recommender Systems considering fair distribution of opportunity for both users as well as the items.

Through my research, I envision search and recommendation systems to form the foundation of economically sustainable multistakeholder online platforms that ensure utility, fairness, and safety for the users as well as the creators and producers.

During my Ph.D., I have completed internships at Google Brain, Facebook Research, and Microsoft Research (NYC and Montreal) where I had the opportunity to collaborate closely with Alex Beutel, Fernando Diaz, Khalid El-Arini, John Langford. Previously, I was an undergraduate student at the Indian Institute of Technology (IIT) Kanpur and also spent a summer at Carnegie Mellon University doing research on Natural Language Processing. You can find more information on the resume and cv.

news

Nov 1, 2020	I am on the job market for research positions in the industry. Find my resume here, cv here, research statement here or reach out via email for more relevant material.
Sep 20, 2020	Our new work on Building Healthy Recommendation Sequences for Everyone: A Safe Reinforcement Learning Approach has been accepted at FAccTRec workshop on Responsible Recommendation at ACM RecSys 2020 to be held from September 22-26, 2020. This is joint work with my collaborators at Google Research.
Aug 19, 2020	Communications of the ACM (CACM) and Cornell Chronicle covered a story about our ACM SIGIR 2020 paper Controlling Fairness and Bias in Dynamic Learning-to-Rank.
Jul 22, 2020	Our paper Controlling Fairness and Bias in Dynamic Learning-to-Rank has been awarded the Best Paper Award at the ACM SIGIR 2020 conference that was held virtually.

selected publications

Find more information on the publications page and google scholar.

* contributed equally.

KDD

Fairness of Exposure in Rankings

Ashudeep Singh, and Thorsten Joachims

In In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, London, UK, 2018.

Abstract arXiv

Rankings are ubiquitous in the online world today. As we have transitioned from finding books in libraries to ranking products, jobs, job applicants, opinions and potential romantic partners, there is a substantial precedent that ranking systems have a responsibility not only to their users but also to the items being ranked. To address these often conflicting responsibilities, we propose a conceptual and computational framework that allows the formulation of fairness constraints on rankings in terms of exposure allocation. As part of this framework, we develop efficient algorithms for finding rankings that maximize the utility for the user while provably satisfying a specifiable notion of fairness. Since fairness goals can be application specific, we show how a broad range of fairness constraints can be implemented using our framework, including forms of demographic parity, disparate treatment, and disparate impact constraints. We illustrate the effect of these constraints by providing empirical results on two ranking problems.
NeurIPS

Policy learning for fairness in ranking

Ashudeep Singh, and Thorsten Joachims

In Neural Information Processing Systems (NeurIPS), 2019.

Abstract arXiv Code Website

Conventional Learning-to-Rank (LTR) methods optimize the utility of the rankings to the users, but they are oblivious to their impact on the ranked items. However, there has been a growing understanding that the latter is important to consider for a wide range of ranking applications (e.g. online marketplaces, job placement, admissions). To address this need, we propose a general LTR framework that can optimize a wide range of utility metrics (e.g. NDCG) while satisfying fairness of exposure constraints with respect to the items. This framework expands the class of learnable ranking functions to stochastic ranking policies, which provides a language for rigorously expressing fairness specifications. Furthermore, we provide a new LTR algorithm called Fair-PG-Rank for directly searching the space of fair ranking policies via a policy-gradient approach. Beyond the theoretical evidence in deriving the framework and the algorithm, we provide empirical results on simulated and real-world datasets verifying the effectiveness of the approach in individual and group-fairness settings.
SIGIR

Controlling Fairness and Bias in Dynamic Learning-to-Rank

Marco Morik*, Ashudeep Singh*, Jessica Hong, and Thorsten Joachims

In Proceedings of ACM SIGIR Conference on Research and Development in Information Retrieval, 2020. Best Paper Award

Abstract arXiv Code Slides Website

Rankings are the primary interface through which many online platforms match users to items (e.g. news, products, music, video). In these two-sided markets, not only the users draw utility from the rankings, but the rankings also determine the utility (e.g. exposure, revenue) for the item providers (e.g. publishers, sellers, artists, studios). It has already been noted that myopically optimizing utility to the users – as done by virtually all learning-to-rank algorithms – can be unfair to the item providers. We, therefore, present a learning-to-rank approach for explicitly enforcing merit-based fairness guarantees to groups of items (e.g. articles by the same publisher, tracks by the same artist). In particular, we propose a learning algorithm that ensures notions of amortized group fairness, while simultaneously learning the ranking function from implicit feedback data. The algorithm takes the form of a controller that integrates unbiased estimators for both fairness and utility, dynamically adapting both as more data becomes available. In addition to its rigorous theoretical foundation and convergence guarantees, we find empirically that the algorithm is highly practical and robust.
RecSys Workshop

Building Healthy Recommendation Sequences for Everyone: A Safe Reinforcement Learning Approach

Ashudeep Singh, Yoni Halpern, Nithum Thain, Konstantina Christakopoulou, Ed H. Chi, Jilin Chen, and Alex Beutel

In FAccTRec Workshop at ACM RecSyS, 2020.

Abstract PDF Code Slides

A key consideration in the design of recommender systems is the long term well-being of users. In this work, we formalize this challenge as a multi-objective, safe reinforcement learning problem, balancing positive user feedback and the “healthiness” of user trajectories. We note that in some cases, naively balancing these objectives can lead to unhealthy experiences, even if unlikely, still occurring in a small subset of users leading us to examine a distributional notion of recommendation safety. Thus, we propose a reinforcement learning approach that optimizes for positive feedback from users while simultaneously optimizing for the health of worst-case users to remain high. To empirically validate our method, we develop a novel research simulation environment motivated by a movie recommendation setting that considers exposure to violence as a proxy for unhealthy recommendations. We demonstrate how our method reduces unhealthy recommendations to the most vulnerable users, without sacrificing much user satisfaction.