IntentGC: a Scalable Graph Convolution Framework Fusing Heterogeneous Information for Recommendation

Abstract

The remarkable progress of network embedding has led to state-of-the-art algorithms in recommendation. However, the sparsity of user-item interactions (i.e., explicit preferences) on websites remains a big challenge for predicting users' behaviors. Although research efforts have been made in utilizing some auxiliary information (e.g., social relations between users) to solve the problem, the existing rich heterogeneous auxiliary relationships are still not fully exploited. Moreover, previous works relied on linearly combined regularizers and suffered parameter tuning. In this work, we collect abundant relationships from common user behaviors and item information, and propose a novel framework named IntentGC to leverage both explicit preferences and heterogeneous relationships by graph convolutional networks. In addition to the capability of modeling heterogeneity, IntentGC can learn the importance of different relationships automatically by the neural model in a nonlinear sense. To apply IntentGC to web-scale applications, we design a faster graph convolutional model named IntentNet by avoiding unnecessary feature interactions. Empirical experiments on two large-scale real-world datasets and online A/B tests in Alibaba demonstrate the superiority of our method over state-of-the-art algorithms.

KDD2019

References in corpus (10)

• DeepWalk: Online Learning of Social Representations
• Semi-Supervised Classification with Graph Convolutional Networks
• LINE: Large-scale Information Network Embedding
• Inductive Representation Learning on Large Graphs
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• Spectral Networks and Locally Connected Networks on Graphs
• Graph Embedding Techniques, Applications, and Performance: A Survey
• Deep Learning based Recommender System: A Survey and New Perspectives
• xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems
• Easing Embedding Learning by Comprehensive Transcription of Heterogeneous Information Networks

Cited by in corpus (18)

• When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities
• Deep Learning on Knowledge Graph for Recommender System: A Survey
• Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network
• DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluation
• A Survey on Knowledge Graph-Based Recommender Systems
• TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning
• Recommending on graphs: a comprehensive review from a data perspective
• Unify Local and Global Information for Top-$N$ Recommendation
• NudgeRank: Digital Algorithmic Nudging for Personalized Health
• Modeling Dual Period-Varying Preferences for Takeaway Recommendation
• Heterogeneous Graph Neural Networks for Large-Scale Bid Keyword Matching
• Basket Recommendation with Multi-Intent Translation Graph Neural Network
• Tree Structure-Aware Graph Representation Learning via Integrated Hierarchical Aggregation and Relational Metric Learning
• A Unified Framework for Cross-Domain and Cross-System Recommendations
• Single-Layer Graph Convolutional Networks For Recommendation
• Lightweight representation learning for efficient and scalable recommendation
• Pre-training Recommender Systems via Reinforced Attentive Multi-relational Graph Neural Network
• When Product Search Meets Collaborative Filtering: A Hierarchical Heterogeneous Graph Neural Network Approach