paper-with-me

Papers

AlignPxtr: Aligning Predicted Behavior Distributions for Bias-Free Video Recommendations

2025-03-10 · Chengzhi Lin, Chuyuan Wang, Annan Xie, Wuhong Wang, Ziye Zhang, Canguang Ruan, Yuancai Huang, Yongqi Liu

In video recommendation systems, user behaviors such as watch time, likes, and follows are commonly used to infer user interest. However, these behaviors are influenced by various biases, including duration bias, demographic biases, and content category biases, which obscure true user preferences. In this paper, we hypothesize that biases and user interest are independent of each other. Based on this assumption, we propose a novel method that aligns predicted behavior distributions across different bias conditions using quantile mapping, theoretically guaranteeing zero mutual information between bias variables and the true user interest. By explicitly modeling the conditional distributions of user behaviors under different biases and mapping these behaviors to quantiles, we effectively decouple user interest from the confounding effects of various biases. Our approach uniquely handles both continuous signals (e.g., watch time) and discrete signals (e.g., likes, comments), while simultaneously addressing multiple bias dimensions. Additionally, we introduce a computationally efficient mean alignment alternative technique for practical real-time inference in large-scale systems. We validate our method through online A/B testing on two major video platforms: Kuaishou Lite and Kuaishou. The results demonstrate significant improvements in user engagement and retention, with \textbf{cumulative lifts of 0.267\% and 0.115\% in active days, and 1.102\% and 0.131\% in average app usage time}, respectively. The results demonstrate that our approach consistently achieves significant improvements in long-term user retention and substantial gains in average app usage time across different platforms. Our core code will be publised at https://github.com/justopit/CQE.

📄 PDF Abstract BibTeX arXiv:2503.06920

Code (0)

등록된 구현이 없습니다.

Tasks

Recommendation Systems

Similar Papers 제목 키워드 기반

Self-CTRL: Self-Consistency Training with Reinforcement Learning

2026-06-16 · Itamar Pres, Laura Ruis, Melat Ghebreselassie, Belinda Z. Li 외 arxiv

Language models (LMs) that faithfully describe their own behavior can more easily be audited, understood, and trusted by users. This paper describes Self-Consistency Training with Reinforcement Learning (Self-CTRL), a me…

Reinforcement Learning

Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning

2020-07-17 · NeurIPS 2020 12 · Jaehyung Kim, Youngbum Hur, Sejun Park, Eunho Yang 외

While semi-supervised learning (SSL) has proven to be a promising way for leveraging unlabeled data when labeled data is scarce, the existing SSL algorithms typically assume that training class distributions are balanced…

Pseudo Label

Factored Causal Representation Learning for Robust Reward Modeling in RLHF

2026-01-29 · Yupei Yang, Lin Yang, Wanxi Deng, Lin Qu 외 arxiv

A reliable reward model is essential for aligning large language models with human preferences through reinforcement learning from human feedback. However, standard reward models are susceptible to spurious features that…

Representation LearningReinforcement Learning

LumaGuide: Distribution Shaping for Training-Free HDR Generation in Diffusion Models

2026-07-28 · Bowen Chen, Shreshth Saini, Balu Adsumilli, Alan C. Bovik arxiv

Pretrained diffusion models generate realistic images but are constrained by the statistical biases of their training data, limiting their ability to produce high dynamic range (HDR) content. In this work, we introduce L…

Video Generation

LLM Bias Detection and Mitigation through the Lens of Desired Distributions

2025-10-07 · Ingroj Shrestha, Padmini Srinivasan arxiv

Although prior work on bias mitigation has focused on promoting social equality and demographic parity, less attention has been given to aligning LLM's outputs to desired distributions. For example, we might want to alig…

Bias Detection