Unifying Graph Convolution and Contrastive Learning in Collaborative Filtering

TL;DR

This paper provides a theoretical framework linking graph convolution and contrastive learning in collaborative filtering, revealing that high-order connectivity can be captured without graph convolutional layers, and introduces a simple effective algorithm called SCCF.

Contribution

It offers a novel theoretical analysis connecting graph convolution and contrastive learning, and proposes a simple, effective collaborative filtering algorithm based on these insights.

Findings

Graph convolutional layers are not essential for high-order connectivity.

Modified contrastive loss improves collaborative filtering performance.

SCCF outperforms baseline models on multiple datasets.

Abstract

Graph-based models and contrastive learning have emerged as prominent methods in Collaborative Filtering (CF). While many existing models in CF incorporate these methods in their design, there seems to be a limited depth of analysis regarding the foundational principles behind them. This paper bridges graph convolution, a pivotal element of graph-based models, with contrastive learning through a theoretical framework. By examining the learning dynamics and equilibrium of the contrastive loss, we offer a fresh lens to understand contrastive learning via graph theory, emphasizing its capability to capture high-order connectivity. Building on this analysis, we further show that the graph convolutional layers often used in graph-based models are not essential for high-order connectivity modeling and might contribute to the risk of oversmoothing. Stemming from our findings, we introduce Simple Contrastive Collaborative Filtering (SCCF), a simple and effective algorithm based on a naive embedding model and a modified contrastive loss. The efficacy of the algorithm is demonstrated through extensive experiments across four public datasets. The experiment code is available at \url{https://github.com/wu1hong/SCCF}. \end{abstract}