Disentangled Graph Collaborative Filtering

Abstract

Learning informative representations of users and items from the interaction data is of crucial importance to collaborative filtering (CF). Present embedding functions exploit user-item relationships to enrich the representations, evolving from a single user-item instance to the holistic interaction graph. Nevertheless, they largely model the relationships in a uniform manner, while neglecting the diversity of user intents on adopting the items, which could be to pass time, for interest, or shopping for others like families. Such uniform approach to model user interests easily results in suboptimal representations, failing to model diverse relationships and disentangle user intents in representations. In this work, we pay special attention to user-item relationships at the finer granularity of user intents. We hence devise a new model, Disentangled Graph Collaborative Filtering (DGCF), to disentangle these factors and yield disentangled representations. Specifically, by modeling a distribution over intents for each user-item interaction, we iteratively refine the intent-aware interaction graphs and representations. Meanwhile, we encourage independence of different intents. This leads to disentangled representations, effectively distilling information pertinent to each intent. We conduct extensive experiments on three benchmark datasets, and DGCF achieves significant improvements over several state-of-the-art models like NGCF, DisenGCN, and MacridVAE. Further analyses offer insights into the advantages of DGCF on the disentanglement of user intents and interpretability of representations. Our codes are available in https://github.com/xiangwang1223/disentangled_graph_collaborative_filtering.

SIGIR 2020

References in corpus (5)

• Neural Graph Collaborative Filtering
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• KGAT: Knowledge Graph Attention Network for Recommendation
• Collaborative Memory Network for Recommendation Systems
• Reinforced Negative Sampling over Knowledge Graph for Recommendation

Cited by in corpus (50)

• Learning Intents behind Interactions with Knowledge Graph for Recommendation
• Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning
• Hypergraph Contrastive Collaborative Filtering
• A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation
• A Comprehensive Survey on Deep Graph Representation Learning
• Towards Representation Alignment and Uniformity in Collaborative Filtering
• Deconfounded Recommendation for Alleviating Bias Amplification
• Self-Supervised Hypergraph Transformer for Recommender Systems
• Disentangled Contrastive Collaborative Filtering
• Automated Self-Supervised Learning for Recommendation
• Disentangling Long and Short-Term Interests for Recommendation
• Multi-Behavior Recommendation with Cascading Graph Convolution Networks
• DisenPOI: Disentangling Sequential and Geographical Influence for Point-of-Interest Recommendation
• DisenKGAT: Knowledge Graph Embedding with Disentangled Graph Attention Network
• Graph Transformer for Recommendation
• Multi-Behavior Enhanced Recommendation with Cross-Interaction Collaborative Relation Modeling
• A Diffusion model for POI recommendation
• Learning Graph ODE for Continuous-Time Sequential Recommendation
• Graph-less Collaborative Filtering
• MEGCF: Multimodal Entity Graph Collaborative Filtering for Personalized Recommendation
• Invariant Collaborative Filtering to Popularity Distribution Shift
• Personalized Graph Signal Processing for Collaborative Filtering
• It Is Different When Items Are Older: Debiasing Recommendations When Selection Bias and User Preferences Are Dynamic
• Unifying Graph Convolution and Contrastive Learning in Collaborative Filtering
• DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluation
• A Survey on Intent-aware Recommender Systems
• Domain Disentanglement with Interpolative Data Augmentation for Dual-Target Cross-Domain Recommendation
• Knowledge Enhanced Multi-intent Transformer Network for Recommendation
• Graph-based Alignment and Uniformity for Recommendation
• INMO: A Model-Agnostic and Scalable Module for Inductive Collaborative Filtering
• Bipartite Graph Convolutional Hashing for Effective and Efficient Top-N Search in Hamming Space
• LightGNN: Simple Graph Neural Network for Recommendation
• Towards Faithful and Consistent Explanations for Graph Neural Networks
• Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis
• Context-aware Event Forecasting via Graph Disentanglement
• Towards Mitigating Dimensional Collapse of Representations in Collaborative Filtering
• Intent Disentanglement and Feature Self-supervision for Novel Recommendation
• Revisiting Neighborhood-based Link Prediction for Collaborative Filtering
• Initialization Matters: Regularizing Manifold-informed Initialization for Neural Recommendation Systems
• FairSample: Training Fair and Accurate Graph Convolutional Neural Networks Efficiently
• HGCH: A Hyperbolic Graph Convolution Network Model for Heterogeneous Collaborative Graph Recommendation
• User Invariant Preference Learning for Multi-Behavior Recommendation
• Intent Propagation Contrastive Collaborative Filtering
• A Worrying Reproducibility Study of Intent-Aware Recommendation Models
• Determinable and interpretable network representation for link prediction
• Enhancing Transferability and Consistency in Cross-Domain Recommendations via Supervised Disentanglement
• Causality-aware Graph Aggregation Weight Estimator for Popularity Debiasing in Top-K Recommendation
• CROWN: A Novel Approach to Comprehending Users' Preferences for Accurate Personalized News Recommendation
• Synergizing Implicit and Explicit User Interests: A Multi-Embedding Retrieval Framework at Pinterest
• Can Offline Metrics Measure Explanation Goals? A Comparative Survey Analysis of Offline Explanation Metrics in Recommender Systems