# Reinforced Negative Sampling over Knowledge Graph for Recommendation

arXiv: https://arxiv.org/abs/2003.05753 · HTML: https://mlsanity.com/paper/2003.05753/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Mar 2020.

## Built on by (most cited first, 30 of 40)

- [Advances and Challenges in Conversational Recommender Systems: A Survey](https://mlsanity.com/paper/2101.09459/) (2021)
- [Learning Intents behind Interactions with Knowledge Graph for Recommendation](https://mlsanity.com/paper/2102.07057/) (2021)
- [A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation](https://mlsanity.com/paper/2104.13030/) (2021)
- [NativE: Multi-modal Knowledge Graph Completion in the Wild](https://mlsanity.com/paper/2406.17605/) (2024)
- [A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions](https://mlsanity.com/paper/2109.03540/) (2021)
- [DSKReG: Differentiable Sampling on Knowledge Graph for Recommendation with Relational GNN](https://mlsanity.com/paper/2108.11883/) (2021)
- [On the Theories Behind Hard Negative Sampling for Recommendation](https://mlsanity.com/paper/2302.03472/) (2023)
- [Learning Robust Recommenders through Cross-Model Agreement](https://mlsanity.com/paper/2105.09605/) (2021)
- [Does Negative Sampling Matter? A Review with Insights into its Theory and Applications](https://mlsanity.com/paper/2402.17238/) (2024)
- [Rethinking Collaborative Metric Learning: Toward an Efficient Alternative without Negative Sampling](https://mlsanity.com/paper/2206.11549/) (2022)
- [Reinforced Path Reasoning for Counterfactual Explainable Recommendation](https://mlsanity.com/paper/2207.06674/) (2022)
- [Knowledge-Enhanced Top-K Recommendation in Poincar'e Ball](https://mlsanity.com/paper/2101.04852/) (2021)
- [KRACL: Contrastive Learning with Graph Context Modeling for Sparse Knowledge Graph Completion](https://mlsanity.com/paper/2208.07622/) (2022)
- [FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings](https://mlsanity.com/paper/2205.00313/) (2022)
- [Improved Diversity-Promoting Collaborative Metric Learning for Recommendation](https://mlsanity.com/paper/2409.01012/) (2024)
- [Recommender systems based on graph embedding techniques: A comprehensive review](https://mlsanity.com/paper/2109.09587/) (2021)
- [MetaKG: Meta-learning on Knowledge Graph for Cold-start Recommendation](https://mlsanity.com/paper/2202.03851/) (2022)
- [Debiased Explainable Pairwise Ranking from Implicit Feedback](https://mlsanity.com/paper/2107.14768/) (2021)
- [Enhancing Cognitive Diagnosis using Un-interacted Exercises: A Collaboration-aware Mixed Sampling Approach](https://mlsanity.com/paper/2312.10110/) (2023)
- [Online POI Recommendation: Learning Dynamic Geo-Human Interactions in Streams](https://mlsanity.com/paper/2201.10983/) (2022)
- [Reinforcement Learning based Path Exploration for Sequential Explainable Recommendation](https://mlsanity.com/paper/2111.12262/) (2021)
- [Debiasing the Cloze Task in Sequential Recommendation with Bidirectional Transformers](https://mlsanity.com/paper/2301.09210/) (2023)
- [Three Kinds of Negation in Knowledge and Their Mathematical Foundations](https://mlsanity.com/paper/2505.24422/) (2025)
- [Adapting Triplet Importance of Implicit Feedback for Personalized Recommendation](https://mlsanity.com/paper/2208.01709/) (2022)
- [Dual Policy Learning for Aggregation Optimization in Graph Neural Network-based Recommender Systems](https://mlsanity.com/paper/2302.10567/) (2023)
- [Dimension Independent Mixup for Hard Negative Sample in Collaborative Filtering](https://mlsanity.com/paper/2306.15905/) (2023)
- [Dual-embedding based Neural Collaborative Filtering for Recommender Systems](https://mlsanity.com/paper/2102.02549/) (2021)
- [Bayesian Negative Sampling for Recommendation](https://mlsanity.com/paper/2204.06520/) (2022)
- [Boosting Protein Language Models with Negative Sample Mining](https://mlsanity.com/paper/2405.17902/) (2024)
- [Scalable Personalised Item Ranking through Parametric Density Estimation](https://mlsanity.com/paper/2105.04769/) (2021)

## Abstract (arXiv)

Properly handling missing data is a fundamental challenge in recommendation. Most present works perform negative sampling from unobserved data to supply the training of recommender models with negative signals. Nevertheless, existing negative sampling strategies, either static or adaptive ones, are insufficient to yield high-quality negative samples --- both informative to model training and reflective of user real needs. In this work, we hypothesize that item knowledge graph (KG), which provides rich relations among items and KG entities, could be useful to infer informative and factual negative samples. Towards this end, we develop a new negative sampling model, Knowledge Graph Policy Network (KGPolicy), which works as a reinforcement learning agent to explore high-quality negatives. Specifically, by conducting our designed exploration operations, it navigates from the target positive interaction, adaptively receives knowledge-aware negative signals, and ultimately yields a potential negative item to train the recommender. We tested on a matrix factorization (MF) model equipped with KGPolicy, and it achieves significant improvements over both state-of-the-art sampling methods like DNS and IRGAN, and KG-enhanced recommender models like KGAT. Further analyses from different angles provide insights of knowledge-aware sampling. We release the codes and datasets at https://github.com/xiangwang1223/kgpolicy.