When Recommendation Denoising Meets Popularity Bias: Understanding and Mitigating Their Interaction

• URL: http://arxiv.org/abs/2606.14046v1
• Date: Fri, 12 Jun 2026 02:46:24 GMT
• Title: When Recommendation Denoising Meets Popularity Bias: Understanding and Mitigating Their Interaction
• Abstract summary: Popularity-Aware Denoising (PAD) is a lightweight plug-in framework that modulates denoising strength by item popularity.<n>PAD applies stronger denoising to highly exposed items while being more conservative on tail items, preserving more clean-but-hard long-tail signals.
• Score: 20.30181867674057
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Implicit feedback is the dominant data source for recommender systems, but behavioral logs are often contaminated by false-positive interactions caused by mis-clicks, biased exposure, and interface effects. Denoising recommendation methods improve robustness by down-weighting or filtering interactions suspected to be noisy, often relying on the small-loss heuristic. We revisit this heuristic through the lens of popularity bias. Tail-item positives can be harder to fit because they are sparsely observed, and thus may receive larger losses even when they reflect genuine user preference. Under such popularity-dependent loss patterns, monotone loss-based reweighting can suppress clean-but-hard tail signals and increase the head-tail imbalance in effective supervision. We formalize this interaction through the effective head-tail signal ratio induced by denoising weights and derive a conditional reallocation result: when the loss distribution of tail positives is right-shifted relative to that of head positives, small-loss reweighting increases the effective head-tail signal ratio compared with ERM. Motivated by this analysis, we propose Popularity-Aware Denoising (PAD), a lightweight plug-in framework that modulates denoising strength by item popularity. PAD applies stronger denoising to highly exposed items while being more conservative on tail items, preserving more clean-but-hard long-tail signals. Experiments on three datasets and three backbones show that PAD generally improves over representative denoising baselines and provides favorable accuracy-diversity tradeoffs, especially on MF-style recommenders.

Related papers

• PEARL: Unbiased Percentile Estimation via Contrastive Learning for Industrial-Scale Livestream Recommendation [12.925115008779166]
  Recommender systems trained on user interaction data are susceptible to behavioral intensity imbalance.<n>This imbalance skews feedback signals such that observed interactions no longer faithfully reflect true preferences.<n>We propose a non-parametric contrastive percentile approximation framework, PEARL, that models relative preference signals instead of absolute engagement magnitudes.
  arXiv  Detail & Related papers  (2026-05-20T21:25:41Z)
• CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbacks [65.44788139573144]
  We introduce observational reward modeling -- learning reward models with observational user feedback -- as a scalable and cost-effective alternative.<n>CaulRM aims to learn unbiased reward models from observational feedback.<n>Experiments validate that CausalRM effectively learns accurate reward signals from noisy and biased observational feedback.
  arXiv  Detail & Related papers  (2026-03-19T10:37:34Z)
• Semantics-Aware Denoising: A PLM-Guided Sample Reweighting Strategy for Robust Recommendation [4.631922211808715]
  Implicit feedback, such as user clicks, serves as the primary data source for modern recommender systems.<n>We propose SAID (Semantics-Aware Implicit Denoising), a framework that leverages semantic consistency between user interests and item content to identify and downweight potentially noisy interactions.<n>Experiments on two real-world datasets demonstrate that SAID consistently improves recommendation performance, achieving up to 2.2% relative improvement in AUC over strong baselines.
  arXiv  Detail & Related papers  (2026-02-17T04:58:21Z)
• How RLHF Amplifies Sycophancy [23.213056717401418]
  Large language models often exhibit increased sycophantic behavior after preference-based post-training.<n>We identify an explicit amplification mechanism that causally links optimization against a learned reward to bias in the human preference data used for alignment.<n>We propose a training-time intervention designed to neutralize the amplification mechanism itself.
  arXiv  Detail & Related papers  (2026-02-01T03:46:14Z)
• The Unfairness of Multifactorial Bias in Recommendation [68.35079031029616]
  Popularity bias and positivity bias are prominent sources of bias in recommender systems.<n>In this work, we examine how multifactorial bias influences item-side fairness.<n>We adapt a percentile-based rating transformation as a pre-processing strategy to mitigate multifactorial bias.
  arXiv  Detail & Related papers  (2026-01-19T08:37:43Z)
• User Hesitation and Negative Transfer in Multi-Behavior Recommendation [55.78729938627577]
  We propose a recommendation framework focused on weak signal learning, termed HNT.<n>By learning the characteristics of auxiliary behaviors that lead to target behaviors, HNT identifies similar auxiliary behaviors that did not trigger the target behavior.<n> Experiments on three real-world datasets demonstrate that HNT improves HR@10 and NDCG@10 by 12.57% and 14.37%, respectively.
  arXiv  Detail & Related papers  (2025-11-08T02:45:32Z)
• Rethinking Purity and Diversity in Multi-Behavior Sequential Recommendation from the Frequency Perspective [48.60281642851056]
  In recommendation systems, users often exhibit multiple behaviors, such as browsing, clicking, and purchasing.<n>Some behavior data will also bring inevitable noise to the modeling of user interests.<n>These studies indicate that low-frequency information tends to be valuable and reliable, while high-frequency information is often associated with noise.
  arXiv  Detail & Related papers  (2025-08-28T04:55:02Z)
• Personalized Denoising Implicit Feedback for Robust Recommender System [60.719158008403376]
  We show that for a given user, there is a clear distinction between normal and noisy interactions in the user's personal loss distribution.<n>We propose a resampling strategy to Denoise using the user's Personal Loss distribution, named PLD, which reduces the probability of noisy interactions being optimized.
  arXiv  Detail & Related papers  (2025-02-01T07:13:06Z)
• Cross Pairwise Ranking for Unbiased Item Recommendation [57.71258289870123]
  We develop a new learning paradigm named Cross Pairwise Ranking (CPR) CPR achieves unbiased recommendation without knowing the exposure mechanism. We prove in theory that this way offsets the influence of user/item propensity on the learning.
  arXiv  Detail & Related papers  (2022-04-26T09:20:27Z)

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.