Towards Representation Alignment and Uniformity in Collaborative Filtering

Abstract

Collaborative filtering (CF) plays a critical role in the development of recommender systems. Most CF methods utilize an encoder to embed users and items into the same representation space, and the Bayesian personalized ranking (BPR) loss is usually adopted as the objective function to learn informative encoders. Existing studies mainly focus on designing more powerful encoders (e.g., graph neural network) to learn better representations. However, few efforts have been devoted to investigating the desired properties of representations in CF, which is important to understand the rationale of existing CF methods and design new learning objectives. In this paper, we measure the representation quality in CF from the perspective of alignment and uniformity on the hypersphere. We first theoretically reveal the connection between the BPR loss and these two properties. Then, we empirically analyze the learning dynamics of typical CF methods in terms of quantified alignment and uniformity, which shows that better alignment or uniformity both contribute to higher recommendation performance. Based on the analyses results, a learning objective that directly optimizes these two properties is proposed, named DirectAU. We conduct extensive experiments on three public datasets, and the proposed learning framework with a simple matrix factorization model leads to significant performance improvements compared to state-of-the-art CF methods. Our implementations are publicly available at https://github.com/THUwangcy/DirectAU.

arXiv commentAccepted by KDD'2022

References in corpus (12)

• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Bootstrap your own latent: A new approach to self-supervised Learning
• Neural Graph Collaborative Filtering
• Session-based Recommendation with Graph Neural Networks
• Facial Expression Analysis under Partial Occlusion: A Survey
• Barlow Twins: Self-Supervised Learning via Redundancy Reduction
• Disentangled Graph Collaborative Filtering
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
• Unsupervised Learning by Predicting Noise
• RecVAE: a New Variational Autoencoder for Top-N Recommendations with Implicit Feedback
• Contrastive Learning for Recommender System
• SimpleX: A Simple and Strong Baseline for Collaborative Filtering

Cited by in corpus (21)

• Multi-View Graph Convolutional Network for Multimedia Recommendation
• RecDCL: Dual Contrastive Learning for Recommendation
• Neighborhood-Enhanced Supervised Contrastive Learning for Collaborative Filtering
• SSLRec: A Self-Supervised Learning Framework for Recommendation
• Unifying Graph Convolution and Contrastive Learning in Collaborative Filtering
• Augmented Negative Sampling for Collaborative Filtering
• Graph-based Alignment and Uniformity for Recommendation
• A Comprehensive Survey on Self-Supervised Learning for Recommendation
• LightGNN: Simple Graph Neural Network for Recommendation
• How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspective
• Adapting Job Recommendations to User Preference Drift with Behavioral-Semantic Fusion Learning
• Towards Mitigating Dimensional Collapse of Representations in Collaborative Filtering
• Toward a Better Understanding of Loss Functions for Collaborative Filtering
• Masked Graph Transformer for Large-Scale Recommendation
• Unlocking the Hidden Treasures: Enhancing Recommendations with Unlabeled Data
• Multi-view Intent Learning and Alignment with Large Language Models for Session-based Recommendation
• Collaboration and Transition: Distilling Item Transitions into Multi-Query Self-Attention for Sequential Recommendation
• Fair Augmentation for Graph Collaborative Filtering
• MixRec: Individual and Collective Mixing Empowers Data Augmentation for Recommender Systems
• Leave No One Behind: Fairness-Aware Cross-Domain Recommender Systems for Non-Overlapping Users
• Prototypical Contrastive Learning through Alignment and Uniformity for Recommendation