Skip to content
Book Open access

Candidate Retrieval for Provider Fairness under Severe Recommendation Imbalance

Sep 2026 · Proceedings of the 20th ACM Conference on Recommender Systems · pp. 653-657 · 0 citations · 24 references

TL;DR

FairSAE, an activation-steering method that, prior to candidate retrieval, shifts user representations toward minority items through a contrastive direction in a latent space induced by a sparse autoencoder (SAE), substantially improves the fairness-accuracy trade-off compared to standalone reranking.

Abstract

Provider fairness in recommender systems is commonly addressed through reranking, which assumes that the candidate set already contains sufficient items from under-exposed provider groups. We study a setting in which this assumption breaks down: catalog representation does not translate into recommendation exposure, and minority items are largely missing from the candidates passed to the reranker. In this regime, methods such as FA*IR, calibration-based reranking, or minority boosting may fail, as suitable items are simply absent on their inputs. We address this bottleneck with FairSAE, an activation-steering method that, prior to candidate retrieval, shifts user representations toward minority items through a contrastive direction in a latent space induced by a sparse autoencoder (SAE). This intervention surfaces minority items from the full catalog and can be combined with existing fairness-aware rerankers. Across the MovieLens-25M and Steam datasets, FairSAE-steered retrieval substantially improves the fairness-accuracy trade-off compared to standalone reranking. These results show that provider fairness under severe recommendation imbalance depends not only on reranking, but also on which items are retrieved in the first place. See https://osf.io/nydez for codes and data.

Read PDF

Similar papers

Preprint Nov 2026

FAIDER: Fairness-Aware Item-Level Decoding for Large Language Model Recommenders

Large language model (LLM) recommenders can produce semantically different recommendations when a user's protected attribute changes, even if the interaction history remains fixed. Controlling this disparity is challenging when model weights and full-vocabulary logits are inaccessible. We propose FAIDER (Fairness-Aware...

Ziwei Wu, Jing-Rui He · 0 citations
Book Open access Nov 2026

FairMB: A Multi-behavior Group Fairness Model for Recommendation with Representation Augmentation

Ensuring fairness in modern recommender systems is an ongoing imperative, yet current methodologies fail to effectively capture the complex interplay between long-tail distributions and biases. Specifically, sparse interactions cause tail user nodes to undergo semantic homogenization, progressively entangling their pre...

Jin-Le He, Deng-Ping He, Jian-Xun Mi et al. · 0 citations
Book Open access Nov 2026

Evaluating Provider-Fairness Mitigation in Price-Aware Recommendation

Price-aware recommender systems incorporate economic signals into ranking, offering practical benefits but their implications for provider-side fairness remain largely unexplored. In this work, we present the first systematic evaluation of fairness mitigation in price-aware recommendation. We quantify provider-side exp...

Fernando Medina-Quispe, David Contreras Aguilar, Elizabeth Gómez et al. · 0 citations

Decision-Oriented Recommendation Reranking: An Empirical Study of Jev

Large language models (LLMs) have shown promise for recommendation reranking, but their use introduces an important tradeoff between recommendation quality and serving efficiency. We investigate whether a decision-oriented model provides a useful alternative when the reranking task is fundamentally a structured choice...

Hanjia Lyu, Ying-Long Xia · 3 citations
Open access Sep 2026

Mitigating Popularity Bias in Recommendation with Global Listwise Learning and Progressive Bi-Weighting

A debiasing framework, termed Mult-IPS, is introduced, which integrates multinomial likelihood with IPS to capture global and unbiased user preferences over the entire item set, and a Bi-Weighting strategy that jointly leverages propensity scores and a collection model, incorporating a smoothing mechanism to enhance th...

Tian-Yu Zhu, Jian-Dong Ding, Yan-Song Shi et al. · 0 citations
Preprint Nov 2026

Preprocessing Choices in Fine-Tuning Data Matter: Utility and Demographic Sensitivity in LLM-Based Recommendation

Large language models (LLMs) have introduced a generative approach to recommendation, producing item lists from textual representations of user histories and item information. However, this generative setting raises challenges concerning output validity, prompt consistency, and sensitivity to demographic descriptors. I...

Furkan Yasir Goksu, Yaren Yılmaz, Ş. Öğüdücü · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.