Simpson's Paradox in Recommender Fairness: Reconciling differences between per-user and aggregated evaluations

• URL: http://arxiv.org/abs/2210.07755v1
• Date: Fri, 14 Oct 2022 12:43:32 GMT
• Title: Simpson's Paradox in Recommender Fairness: Reconciling differences between per-user and aggregated evaluations
• Authors: Flavien Prost, Ben Packer, Jilin Chen, Li Wei, Pierre Kremp, Nicholas Blumm, Susan Wang, Tulsee Doshi, Tonia Osadebe, Lukasz Heldt, Ed H. Chi, Alex Beutel
• Abstract summary: We argue that two notions of fairness in ranking and recommender systems can lead to opposite conclusions. We reconcile these notions and show that the tension is due to differences in distributions of users where items are relevant. Based on this new understanding, practitioners might be interested in either notions, but might face challenges with the per-user metric.
• Score: 16.053419956606557
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: There has been a flurry of research in recent years on notions of fairness in ranking and recommender systems, particularly on how to evaluate if a recommender allocates exposure equally across groups of relevant items (also known as provider fairness). While this research has laid an important foundation, it gave rise to different approaches depending on whether relevant items are compared per-user/per-query or aggregated across users. Despite both being established and intuitive, we discover that these two notions can lead to opposite conclusions, a form of Simpson's Paradox. We reconcile these notions and show that the tension is due to differences in distributions of users where items are relevant, and break down the important factors of the user's recommendations. Based on this new understanding, practitioners might be interested in either notions, but might face challenges with the per-user metric due to partial observability of the relevance and user satisfaction, typical in real-world recommenders. We describe a technique based on distribution matching to estimate it in such a scenario. We demonstrate on simulated and real-world recommender data the effectiveness and usefulness of such an approach.

Related papers

• Debiasing Recommendation by Learning Identifiable Latent Confounders [49.16119112336605]
  Confounding bias arises due to the presence of unmeasured variables that can affect both a user's exposure and feedback. Existing methods either (1) make untenable assumptions about these unmeasured variables or (2) directly infer latent confounders from users' exposure. We propose a novel method, i.e., identifiable deconfounder (iDCF), which leverages a set of proxy variables to resolve the aforementioned non-identification issue.
  arXiv  Detail & Related papers  (2023-02-10T05:10:26Z)
• Experiments on Generalizability of User-Oriented Fairness in Recommender Systems [2.0932879442844476]
  A fairness-aware recommender system aims to treat different user groups similarly. We propose a user-centered fairness re-ranking framework applied on top of a base ranking model. We evaluate the final recommendations provided by the re-ranking framework from both user- (e.g., NDCG) and item-side (e.g., novelty, item-fairness) metrics.
  arXiv  Detail & Related papers  (2022-05-17T12:36:30Z)
• Joint Multisided Exposure Fairness for Recommendation [76.75990595228666]
  This paper formalizes a family of exposure fairness metrics that model the problem jointly from the perspective of both the consumers and producers. Specifically, we consider group attributes for both types of stakeholders to identify and mitigate fairness concerns that go beyond individual users and items towards more systemic biases in recommendation.
  arXiv  Detail & Related papers  (2022-04-29T19:13:23Z)
• Causal Disentanglement with Network Information for Debiased Recommendations [34.698181166037564]
  Recent research proposes to debias by modeling a recommender system from a causal perspective. The critical challenge in this setting is accounting for the hidden confounders. We propose to leverage network information (i.e., user-social and user-item networks) to better approximate hidden confounders.
  arXiv  Detail & Related papers  (2022-04-14T20:55:11Z)
• Learning Personalized Item-to-Item Recommendation Metric via Implicit Feedback [24.37151414523712]
  This paper studies the item-to-item recommendation problem in recommender systems from a new perspective of metric learning via implicit feedback. We develop and investigate a personalizable deep metric model that captures both the internal contents of items and how they were interacted with by users.
  arXiv  Detail & Related papers  (2022-03-18T18:08:57Z)
• Deep Causal Reasoning for Recommendations [47.83224399498504]
  A new trend in recommender system research is to negate the influence of confounders from a causal perspective. We model the recommendation as a multi-cause multi-outcome (MCMO) inference problem. We show that MCMO modeling may lead to high variance due to scarce observations associated with the high-dimensional causal space.
  arXiv  Detail & Related papers  (2022-01-06T15:00:01Z)
• Correcting the User Feedback-Loop Bias for Recommendation Systems [34.44834423714441]
  We propose a systematic and dynamic way to correct user feedback-loop bias in recommendation systems. Our method includes a deep-learning component to learn each user's dynamic rating history embedding. We empirically validated the existence of such user feedback-loop bias in real world recommendation systems.
  arXiv  Detail & Related papers  (2021-09-13T15:02:55Z)
• Deconfounding Scores: Feature Representations for Causal Effect Estimation with Weak Overlap [140.98628848491146]
  We introduce deconfounding scores, which induce better overlap without biasing the target of estimation. We show that deconfounding scores satisfy a zero-covariance condition that is identifiable in observed data. In particular, we show that this technique could be an attractive alternative to standard regularizations.
  arXiv  Detail & Related papers  (2021-04-12T18:50:11Z)
• SetRank: A Setwise Bayesian Approach for Collaborative Ranking from Implicit Feedback [50.13745601531148]
  We propose a novel setwise Bayesian approach for collaborative ranking, namely SetRank, to accommodate the characteristics of implicit feedback in recommender system. Specifically, SetRank aims at maximizing the posterior probability of novel setwise preference comparisons. We also present the theoretical analysis of SetRank to show that the bound of excess risk can be proportional to $sqrtM/N$.
  arXiv  Detail & Related papers  (2020-02-23T06:40:48Z)
• A Bayesian Approach to Conversational Recommendation Systems [60.12942570608859]
  We present a conversational recommendation system based on a Bayesian approach. A case study based on the application of this approach to emphstagend.com, an online platform for booking entertainers, is discussed.
  arXiv  Detail & Related papers  (2020-02-12T15:59:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.