LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation

TL;DR

LightGCL introduces a simple graph contrastive learning method using SVD for recommendation systems, improving robustness and performance over existing augmentation techniques, especially in sparse and biased data scenarios.

Contribution

It proposes a novel contrastive augmentation method based on SVD that preserves semantic structures and enhances robustness in GNN-based recommender systems.

Findings

Significant performance improvements over state-of-the-art methods.

Enhanced robustness against data sparsity and popularity bias.

Effective structural refinement through SVD-based augmentation.

Abstract

Graph neural network (GNN) is a powerful learning approach for graph-based recommender systems. Recently, GNNs integrated with contrastive learning have shown superior performance in recommendation with their data augmentation schemes, aiming at dealing with highly sparse data. Despite their success, most existing graph contrastive learning methods either perform stochastic augmentation (e.g., node/edge perturbation) on the user-item interaction graph, or rely on the heuristic-based augmentation techniques (e.g., user clustering) for generating contrastive views. We argue that these methods cannot well preserve the intrinsic semantic structures and are easily biased by the noise perturbation. In this paper, we propose a simple yet effective graph contrastive learning paradigm LightGCL that mitigates these issues impairing the generality and robustness of CL-based recommenders. Our model exclusively utilizes singular value decomposition for contrastive augmentation, which enables the unconstrained structural refinement with global collaborative relation modeling. Experiments conducted on several benchmark datasets demonstrate the significant improvement in performance of our model over the state-of-the-arts. Further analyses demonstrate the superiority of LightGCL's robustness against data sparsity and popularity bias. The source code of our model is available at https://github.com/HKUDS/LightGCL.