Dimension Independent Mixup for Hard Negative Sample in Collaborative Filtering

By Xi Wu et al

Published on Oct. 21, 2023

Read the original document by opening this link in a new tab.

Table of Contents

1. Introduction
2. Preliminaries
3. Proposed Method
3.1 Hard Boundary Definition
3.2 Dimension Independent Mixup
3.3 Multi-hop Pooling
4. Experimental Validation
5. Related Works
6. Conclusion

Summary

Collaborative filtering (CF) is a widely employed technique that predicts user preferences based on past interactions. Negative sampling plays a vital role in training CF-based models with implicit feedback. In this paper, the authors propose a novel perspective based on the sampling area to revisit existing sampling methods. They introduce Dimension Independent Mixup for Hard Negative Sampling (DINS) as the first Area-wise sampling method for training CF-based models. DINS comprises three modules: Hard Boundary Definition, Dimension Independent Mixup, and Multi-hop Pooling. Experimental results demonstrate that DINS outperforms other negative sampling methods, establishing its effectiveness and superiority. The work contributes a new perspective, introduces Area-wise sampling, and presents DINS as a novel approach achieving state-of-the-art performance.