# Fairly Adaptive Negative Sampling for Recommendations

arXiv: https://arxiv.org/abs/2302.08266 · HTML: https://mlsanity.com/paper/2302.08266/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Feb 2023.

## Built on by (most cited first, 22 of 22)

- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [Recommender Systems in the Era of Large Language Models (LLMs)](https://mlsanity.com/paper/2307.02046/) (2023)
- [A Survey of Mamba](https://mlsanity.com/paper/2408.01129/) (2024)
- [TokenRec: Learning to Tokenize ID for LLM-based Generative Recommendation](https://mlsanity.com/paper/2406.10450/) (2024)
- [Graph Machine Learning in the Era of Large Language Models (LLMs)](https://mlsanity.com/paper/2404.14928/) (2024)
- [Linear-Time Graph Neural Networks for Scalable Recommendations](https://mlsanity.com/paper/2402.13973/) (2024)
- [Ensuring User-side Fairness in Dynamic Recommender Systems](https://mlsanity.com/paper/2308.15651/) (2023)
- [Mind the Graph When Balancing Data for Fairness or Robustness](https://mlsanity.com/paper/2406.17433/) (2024)
- [Interdisciplinary Fairness in Imbalanced Research Proposal Topic Inference: A Hierarchical Transformer-based Method with Selective Interpolation](https://mlsanity.com/paper/2309.01717/) (2023)
- [Intersectional Two-sided Fairness in Recommendation](https://mlsanity.com/paper/2402.02816/) (2024)
- [FairDgcl: Fairness-aware Recommendation with Dynamic Graph Contrastive Learning](https://mlsanity.com/paper/2410.17555/) (2024)
- [Evaluating Performance and Bias of Negative Sampling in Large-Scale Sequential Recommendation Models](https://mlsanity.com/paper/2410.17276/) (2024)
- [Membership Inference Attacks on Recommender System: A Survey](https://mlsanity.com/paper/2509.11080/) (2025)
- [Continuous-time Discrete-space Diffusion Model for Recommendation](https://mlsanity.com/paper/2511.12114/) (2025)
- [Fair Augmentation for Graph Collaborative Filtering](https://mlsanity.com/paper/2408.12208/) (2024)
- [Towards a Theoretical Understanding of Two Tower Recommendation Models](https://mlsanity.com/paper/2403.00802/) (2024)
- [Countering Mainstream Bias via End-to-End Adaptive Local Learning](https://mlsanity.com/paper/2404.08887/) (2024)
- [Exploiting Preferences in Loss Functions for Sequential Recommendation via Weak Transitivity](https://mlsanity.com/paper/2408.00326/) (2024)
- [Causal Negative Sampling via Diffusion Model for Out-of-Distribution Recommendation](https://mlsanity.com/paper/2508.07243/) (2025)
- [MedicalRec: Medical recommender system for image classification without retraining](https://mlsanity.com/paper/2606.07553/) (2026)
- [Diffusion Language Model for Recommendation](https://mlsanity.com/paper/2607.21519/) (2026)
- [RecToolBench: Benchmarking Recommendation-Specific Tool Orchestration under Fuzzy User Intent](https://mlsanity.com/paper/2609.30717/) (2026)

## Abstract (arXiv)

Pairwise learning strategies are prevalent for optimizing recommendation models on implicit feedback data, which usually learns user preference by discriminating between positive (i.e., clicked by a user) and negative items (i.e., obtained by negative sampling). However, the size of different item groups (specified by item attribute) is usually unevenly distributed. We empirically find that the commonly used uniform negative sampling strategy for pairwise algorithms (e.g., BPR) can inherit such data bias and oversample the majority item group as negative instances, severely countering group fairness on the item side. In this paper, we propose a Fairly adaptive Negative sampling approach (FairNeg), which improves item group fairness via adaptively adjusting the group-level negative sampling distribution in the training process. In particular, it first perceives the model's unfairness status at each step and then adjusts the group-wise sampling distribution with an adaptive momentum update strategy for better facilitating fairness optimization. Moreover, a negative sampling distribution Mixup mechanism is proposed, which gracefully incorporates existing importance-aware sampling techniques intended for mining informative negative samples, thus allowing for achieving multiple optimization purposes. Extensive experiments on four public datasets show our proposed method's superiority in group fairness enhancement and fairness-utility tradeoff.