Contrastive Meta Learning with Behavior Multiplicity for Recommendation

Abstract

A well-informed recommendation framework could not only help users identify their interested items, but also benefit the revenue of various online platforms (e.g., e-commerce, social media). Traditional recommendation models usually assume that only a single type of interaction exists between user and item, and fail to model the multiplex user-item relationships from multi-typed user behavior data, such as page view, add-to-favourite and purchase. While some recent studies propose to capture the dependencies across different types of behaviors, two important challenges have been less explored: i) Dealing with the sparse supervision signal under target behaviors (e.g., purchase). ii) Capturing the personalized multi-behavior patterns with customized dependency modeling. To tackle the above challenges, we devise a new model CML, Contrastive Meta Learning (CML), to maintain dedicated cross-type behavior dependency for different users. In particular, we propose a multi-behavior contrastive learning framework to distill transferable knowledge across different types of behaviors via the constructed contrastive loss. In addition, to capture the diverse multi-behavior patterns, we design a contrastive meta network to encode the customized behavior heterogeneity for different users. Extensive experiments on three real-world datasets indicate that our method consistently outperforms various state-of-the-art recommendation methods. Our empirical studies further suggest that the contrastive meta learning paradigm offers great potential for capturing the behavior multiplicity in recommendation. We release our model implementation at: https://github.com/weiwei1206/CML.git.

Published as a full paper at WSDM 2022 and Awarded as Best Paper Candidate

References in corpus (10)

• KGAT: Knowledge Graph Attention Network for Recommendation
• Self-supervised Graph Learning for Recommendation
• Graph Contrastive Learning with Adaptive Augmentation
• Graph Contrastive Learning with Augmentations
• GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
• Session-based Social Recommendation via Dynamic Graph Attention Networks
• Graph Meta Network for Multi-Behavior Recommendation
• Multiplex Behavioral Relation Learning for Recommendation via Memory Augmented Transformer Network
• Social Recommendation with Self-Supervised Metagraph Informax Network
• Recent Advances in Heterogeneous Relation Learning for Recommendation

Cited by in corpus (23)

• Knowledge Graph Contrastive Learning for Recommendation
• Hypergraph Contrastive Collaborative Filtering
• Heterogeneous Graph Contrastive Learning for Recommendation
• Multi-Modal Self-Supervised Learning for Recommendation
• Multi-Behavior Hypergraph-Enhanced Transformer for Sequential Recommendation
• Disentangled Contrastive Collaborative Filtering
• Automated Self-Supervised Learning for Recommendation
• Knowledge Enhancement for Contrastive Multi-Behavior Recommendation
• Multiplex Heterogeneous Graph Convolutional Network
• Spatial-Temporal Hypergraph Self-Supervised Learning for Crime Prediction
• Multi-behavior Self-supervised Learning for Recommendation
• Multi-Behavior Sequential Recommendation with Temporal Graph Transformer
• Multi-Behavior Graph Neural Networks for Recommender System
• Graph Masked Autoencoder for Sequential Recommendation
• Graph-less Collaborative Filtering
• Meta-optimized Contrastive Learning for Sequential Recommendation
• SSLRec: A Self-Supervised Learning Framework for Recommendation
• Improving Implicit Feedback-Based Recommendation through Multi-Behavior Alignment
• A Comprehensive Survey on Self-Supervised Learning for Recommendation
• Multi-queue Momentum Contrast for Microvideo-Product Retrieval
• Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis
• Bootstrapping Contrastive Learning Enhanced Music Cold-Start Matching
• Hierarchical Graph Information Bottleneck for Multi-Behavior Recommendation