Supervised Contrastive Learning for Recommendation

TL;DR

This paper introduces supervised contrastive learning (SCL) tailored for recommendation systems, enhancing graph neural networks by incorporating similarity-based positive samples and a novel data augmentation method, node replication.

Contribution

It proposes a new SCL paradigm for recommendation systems, integrating similarity-based positives and node replication augmentation to improve accuracy and robustness.

Findings

SCL improves recommendation accuracy on multiple datasets.

Node replication enhances robustness to interactive noise.

Ablation studies validate the effectiveness of proposed methods.

Abstract

In this work, we aim to consider the application of contrastive learning in the scenario of the recommendation system adequately, making it more suitable for recommendation task. We propose a learning paradigm called supervised contrastive learning(SCL) to support the graph convolutional neural network. Specifically, we will calculate the similarity between different nodes in user side and item side respectively during data preprocessing, and then when applying contrastive learning, not only will the augmented views be regarded as the positive samples, but also a certain number of similar samples will be regarded as the positive samples, which is different with SimCLR that treats other samples in a batch as negative samples. We apply SCL on the most advanced LightGCN. In addition, in order to consider the uncertainty of node interaction, we also propose a new data augment method called node replication. Empirical research and ablation study on Gowalla, Yelp2018, Amazon-Book datasets prove the effectiveness of SCL and node replication, which improve the accuracy of recommendations and robustness to interactive noise.