Collaborative Filtering with Graph-based Implicit Feedback

TL;DR

This paper introduces graph-based models for collaborative filtering that incorporate both user and item implicit feedback, with learned weighting to better capture user preferences, outperforming existing methods.

Contribution

It proposes novel GCF, W-GCF, and A-GCF models that extend implicit feedback utilization to item-side and learn feedback weights, enhancing recommendation accuracy.

Findings

Models outperform state-of-the-art methods.

Additional gains in sparse feedback scenarios.

Effective use of step-two implicit feedback.

Abstract

Introducing consumed items as users' implicit feedback in matrix factorization (MF) method, SVD++ is one of the most effective collaborative filtering methods for personalized recommender systems. Though powerful, SVD++ has two limitations: (i). only user-side implicit feedback is utilized, whereas item-side implicit feedback, which can also enrich item representations, is not leveraged;(ii). in SVD++, the interacted items are equally weighted when combining the implicit feedback, which can not reflect user's true preferences accurately. To tackle the above limitations, in this paper we propose Graph-based collaborative filtering (GCF) model, Weighted Graph-based collaborative filtering (W-GCF) model and Attentive Graph-based collaborative filtering (A-GCF) model, which (i). generalize the implicit feedback to item side based on the user-item bipartite graph; (ii). flexibly learn the weights of individuals in the implicit feedback hence improve the model's capacity. Comprehensive experiments show that our proposed models outperform state-of-the-art models.For sparse implicit feedback scenarios, additional improvement is further achieved by leveraging the step-two implicit feedback information.