L^2CL: Embarrassingly Simple Layer-to-Layer Contrastive Learning for Graph Collaborative Filtering

TL;DR

L2CL introduces a simple layer-to-layer contrastive learning framework for graph collaborative filtering that avoids complex data augmentation and deep architectures, effectively capturing semantic structures and improving recommendation performance.

Contribution

The paper proposes L2CL, a novel layer-to-layer contrastive learning method that simplifies graph recommendation models and enhances their ability to learn semantic relationships without noisy augmentations.

Findings

L2CL outperforms state-of-the-art methods on five real-world datasets.

L2CL effectively captures intrinsic semantic structures with a single-hop contrastive paradigm.

Theoretical guarantees show L2CL reduces task-irrelevant information.

Abstract

Graph neural networks (GNNs) have recently emerged as an effective approach to model neighborhood signals in collaborative filtering. Towards this research line, graph contrastive learning (GCL) demonstrates robust capabilities to address the supervision label shortage issue through generating massive self-supervised signals. Despite its effectiveness, GCL for recommendation suffers seriously from two main challenges: i) GCL relies on graph augmentation to generate semantically different views for contrasting, which could potentially disrupt key information and introduce unwanted noise; ii) current works for GCL primarily focus on contrasting representations using sophisticated networks architecture (usually deep) to capture high-order interactions, which leads to increased computational complexity and suboptimal training efficiency. To this end, we propose L2CL, a principled Layer-to-Layer Contrastive Learning framework that contrasts representations from different layers. By aligning the semantic similarities between different layers, L2CL enables the learning of complex structural relationships and gets rid of the noise perturbation in stochastic data augmentation. Surprisingly, we find that L2CL, using only one-hop contrastive learning paradigm, is able to capture intrinsic semantic structures and improve the quality of node representation, leading to a simple yet effective architecture. We also provide theoretical guarantees for L2CL in minimizing task-irrelevant information. Extensive experiments on five real-world datasets demonstrate the superiority of our model over various state-of-the-art collaborative filtering methods. Our code is available at https://github.com/downeykking/L2CL.