SelfCF: A Simple Framework for Self-supervised Collaborative Filtering

Abstract

Collaborative filtering (CF) is widely used to learn informative latent representations of users and items from observed interactions. Existing CF-based methods commonly adopt negative sampling to discriminate different items. Training with negative sampling on large datasets is computationally expensive. Further, negative items should be carefully sampled under the defined distribution, in order to avoid selecting an observed positive item in the training dataset. Unavoidably, some negative items sampled from the training dataset could be positive in the test set. In this paper, we propose a self-supervised collaborative filtering framework (SelfCF), that is specially designed for recommender scenario with implicit feedback. The proposed SelfCF framework simplifies the Siamese networks and can be easily applied to existing deep-learning based CF models, which we refer to as backbone networks. The main idea of SelfCF is to augment the output embeddings generated by backbone networks, because it is infeasible to augment raw input of user/item ids. We propose and study three output perturbation techniques that can be applied to different types of backbone networks including both traditional CF models and graph-based models. The framework enables learning informative representations of users and items without negative samples, and is agnostic to the encapsulated backbones. We conduct comprehensive experiments on four datasets to show that our framework may achieve even better recommendation accuracy than the encapsulated supervised counterpart with a 2$\times$--4$\times$ faster training speed. We also show that SelfCF can boost up the accuracy by up to 17.79% on average, compared with a self-supervised framework BUIR.

Accepted to ACM Transactions on Recommender Systems (TORS). Code: https://github.com/enoche/SelfCF

References in corpus (12)

• Barlow Twins: Self-Supervised Learning via Redundancy Reduction
• Graph Self-Supervised Learning: A Survey
• Bootstrap Latent Representations for Multi-modal Recommendation
• A Tale of Two Graphs: Freezing and Denoising Graph Structures for Multimodal Recommendation
• Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendation
• Self-Supervised Learning for Recommender Systems: A Survey
• Modeling Dynamic User Preference via Dictionary Learning for Sequential Recommendation
• Inductive Graph Transformer for Delivery Time Estimation
• Multimodal Pre-training Framework for Sequential Recommendation via Contrastive Learning
• Enhancing Dyadic Relations with Homogeneous Graphs for Multimodal Recommendation
• Layer-refined Graph Convolutional Networks for Recommendation
• Dual Graph Multitask Framework for Imbalanced Delivery Time Estimation

Cited by in corpus (8)

• A Tale of Two Graphs: Freezing and Denoising Graph Structures for Multimodal Recommendation
• CrossCBR: Cross-view Contrastive Learning for Bundle Recommendation
• MMRec: Simplifying Multimodal Recommendation
• CL4CTR: A Contrastive Learning Framework for CTR Prediction
• Spectrum-based Modality Representation Fusion Graph Convolutional Network for Multimodal Recommendation
• A Comprehensive Survey on Self-Supervised Learning for Recommendation
• Capturing Popularity Trends: A Simplistic Non-Personalized Approach for Enhanced Item Recommendation
• A Survey of Latent Factor Models in Recommender Systems