UltraGCN: Ultra Simplification of Graph Convolutional Networks for Recommendation

Abstract

With the recent success of graph convolutional networks (GCNs), they have been widely applied for recommendation, and achieved impressive performance gains. The core of GCNs lies in its message passing mechanism to aggregate neighborhood information. However, we observed that message passing largely slows down the convergence of GCNs during training, especially for large-scale recommender systems, which hinders their wide adoption. LightGCN makes an early attempt to simplify GCNs for collaborative filtering by omitting feature transformations and nonlinear activations. In this paper, we take one step further to propose an ultra-simplified formulation of GCNs (dubbed UltraGCN), which skips infinite layers of message passing for efficient recommendation. Instead of explicit message passing, UltraGCN resorts to directly approximate the limit of infinite-layer graph convolutions via a constraint loss. Meanwhile, UltraGCN allows for more appropriate edge weight assignments and flexible adjustment of the relative importances among different types of relationships. This finally yields a simple yet effective UltraGCN model, which is easy to implement and efficient to train. Experimental results on four benchmark datasets show that UltraGCN not only outperforms the state-of-the-art GCN models but also achieves more than 10x speedup over LightGCN. Our source code will be available at https://reczoo.github.io/UltraGCN.

Accepted by CIKM 2021. Code available at: https://reczoo.github.io/UltraGCN

References in corpus (5)

• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Simplifying Graph Convolutional Networks
• Graph Convolutional Matrix Completion
• Simple and Deep Graph Convolutional Networks
• M2GRL: A Multi-task Multi-view Graph Representation Learning Framework for Web-scale Recommender Systems

Cited by in corpus (12)

• Multi-View Graph Convolutional Network for Multimedia Recommendation
• DGRec: Graph Neural Network for Recommendation with Diversified Embedding Generation
• Multi-Behavior Recommendation with Cascading Graph Convolution Networks
• MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering
• HICF: Hyperbolic Informative Collaborative Filtering
• Invariant Collaborative Filtering to Popularity Distribution Shift
• Personalized Graph Signal Processing for Collaborative Filtering
• Contemporary Recommendation Systems on Big Data and Their Applications: A Survey
• Robust Collaborative Filtering to Popularity Distribution Shift
• Graph-based Alignment and Uniformity for Recommendation
• Pareto Invariant Representation Learning for Multimedia Recommendation
• Towards Mitigating Dimensional Collapse of Representations in Collaborative Filtering