Fairness in the First Stage of Two-Stage Recommender Systems
- URL: http://arxiv.org/abs/2205.15436v2
- Date: Thu, 2 Jun 2022 12:50:37 GMT
- Title: Fairness in the First Stage of Two-Stage Recommender Systems
- Authors: Lequn Wang and Thorsten Joachims
- Abstract summary: We investigate how to ensure fairness to the items in large-scale recommender systems.
Existing first-stage recommenders might select an irrecoverably unfair set of candidates.
We propose two threshold-policy selection rules that find near-optimal sets of candidates.
- Score: 28.537935838669423
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Many large-scale recommender systems consist of two stages, where the first
stage focuses on efficiently generating a small subset of promising candidates
from a huge pool of items for the second-stage model to curate final
recommendations from. In this paper, we investigate how to ensure group
fairness to the items in this two-stage paradigm. In particular, we find that
existing first-stage recommenders might select an irrecoverably unfair set of
candidates such that there is no hope for the second-stage recommender to
deliver fair recommendations. To this end, we propose two threshold-policy
selection rules that, given any relevance model of queries and items and a
point-wise lower confidence bound on the expected number of relevant items for
each policy, find near-optimal sets of candidates that contain enough relevant
items in expectation from each group of items. To instantiate the rules, we
demonstrate how to derive such confidence bounds from potentially partial and
biased user feedback data, which are abundant in many large-scale recommender
systems. In addition, we provide both finite-sample and asymptotic analysis of
how close the two threshold selection rules are to the optimal thresholds.
Beyond this theoretical analysis, we show empirically that these two rules can
consistently select enough relevant items from each group while minimizing the
size of the candidate sets for a wide range of settings.
Related papers
- Centralized Selection with Preferences in the Presence of Biases [25.725937202777267]
The paper focuses on the setting in which candidates are divided into multiple groups and the observed utilities of candidates in some groups are biased--systematically lower than their true utilities.
An algorithm is presented along with proof that it produces selections that achieve near-optimal group fairness with respect to preferences while also nearly maximizing the true utility under distributional assumptions.
arXiv Detail & Related papers (2024-09-07T19:47:13Z) - Representing and Reasoning with Multi-Stakeholder Qualitative Preference
Queries [9.768677073327423]
We offer the first formal treatment of reasoning with multi-stakeholder qualitative preferences.
We introduce a query for expressing queries against such preferences over sets of outcomes that satisfy specified criteria.
We present experimental results that demonstrate the feasibility of our approach.
arXiv Detail & Related papers (2023-07-30T19:52:59Z) - Recommendation Systems with Distribution-Free Reliability Guarantees [83.80644194980042]
We show how to return a set of items rigorously guaranteed to contain mostly good items.
Our procedure endows any ranking model with rigorous finite-sample control of the false discovery rate.
We evaluate our methods on the Yahoo! Learning to Rank and MSMarco datasets.
arXiv Detail & Related papers (2022-07-04T17:49:25Z) - On component interactions in two-stage recommender systems [82.38014314502861]
Two-stage recommenders are used by many online platforms, including YouTube, LinkedIn, and Pinterest.
We show that interactions between the ranker and the nominators substantially affect the overall performance.
In particular, using a Mixture-of-Experts approach, we train the nominators to specialize on different subsets of the item pool.
arXiv Detail & Related papers (2021-06-28T20:53:23Z) - Set2setRank: Collaborative Set to Set Ranking for Implicit Feedback
based Recommendation [59.183016033308014]
In this paper, we explore the unique characteristics of the implicit feedback and propose Set2setRank framework for recommendation.
Our proposed framework is model-agnostic and can be easily applied to most recommendation prediction approaches.
arXiv Detail & Related papers (2021-05-16T08:06:22Z) - A New Approach to Overgenerating and Scoring Abstractive Summaries [9.060597430218378]
We propose a two-staged strategy to generate a diverse set of candidate summaries from the source text in stage one, then score and select admissible ones in stage two.
Our generator gives a precise control over the length of the summary, which is especially well-suited when space is limited.
Our selectors are designed to predict the optimal summary length and put special emphasis on faithfulness to the original text.
arXiv Detail & Related papers (2021-04-05T00:29:45Z) - Learning over no-Preferred and Preferred Sequence of items for Robust
Recommendation [66.8722561224499]
We propose a theoretically founded sequential strategy for training large-scale Recommender Systems (RS) over implicit feedback.
We present two variants of this strategy where model parameters are updated using either the momentum method or a gradient-based approach.
arXiv Detail & Related papers (2020-12-12T22:10:15Z) - Exploration in two-stage recommender systems [79.50534282841618]
Two-stage recommender systems are widely adopted in industry due to their scalability and maintainability.
A key challenge of this setup is that optimal performance of each stage in isolation does not imply optimal global performance.
We propose a method of synchronising the exploration strategies between the ranker and the nominators.
arXiv Detail & Related papers (2020-09-01T16:52:51Z) - 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)
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.