Long-tail Augmented Graph Contrastive Learning for Recommendation

TL;DR

This paper introduces LAGCL, a novel graph contrastive learning method that enhances tail node representations in recommendation systems by using learnable augmentation, auto drop, knowledge transfer, and GANs, leading to improved long-tail performance.

Contribution

The paper proposes a learnable long-tail augmentation framework with auto drop and knowledge transfer modules, addressing degree disparity in GCN-based recommendation models.

Findings

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

Enhanced uniformity of learned representations.

Superior long-tail recommendation performance.

Abstract

Graph Convolutional Networks (GCNs) has demonstrated promising results for recommender systems, as they can effectively leverage high-order relationship. However, these methods usually encounter data sparsity issue in real-world scenarios. To address this issue, GCN-based recommendation methods employ contrastive learning to introduce self-supervised signals. Despite their effectiveness, these methods lack consideration of the significant degree disparity between head and tail nodes. This can lead to non-uniform representation distribution, which is a crucial factor for the performance of contrastive learning methods. To tackle the above issue, we propose a novel Long-tail Augmented Graph Contrastive Learning (LAGCL) method for recommendation. Specifically, we introduce a learnable long-tail augmentation approach to enhance tail nodes by supplementing predicted neighbor information, and generate contrastive views based on the resulting augmented graph. To make the data augmentation schema learnable, we design an auto drop module to generate pseudo-tail nodes from head nodes and a knowledge transfer module to reconstruct the head nodes from pseudo-tail nodes. Additionally, we employ generative adversarial networks to ensure that the distribution of the generated tail/head nodes matches that of the original tail/head nodes. Extensive experiments conducted on three benchmark datasets demonstrate the significant improvement in performance of our model over the state-of-the-arts. Further analyses demonstrate the uniformity of learned representations and the superiority of LAGCL on long-tail performance. Code is publicly available at https://github.com/im0qianqian/LAGCL