LightGNN: Simple Graph Neural Network for Recommendation

Abstract

Graph neural networks (GNNs) have demonstrated superior performance in collaborative recommendation through their ability to conduct high-order representation smoothing, effectively capturing structural information within users' interaction patterns. However, existing GNN paradigms face significant challenges in scalability and robustness when handling large-scale, noisy, and real-world datasets. To address these challenges, we present LightGNN, a lightweight and distillation-based GNN pruning framework designed to substantially reduce model complexity while preserving essential collaboration modeling capabilities. Our LightGNN framework introduces a computationally efficient pruning module that adaptively identifies and removes redundant edges and embedding entries for model compression. The framework is guided by a resource-friendly hierarchical knowledge distillation objective, whose intermediate layer augments the observed graph to maintain performance, particularly in high-rate compression scenarios. Extensive experiments on public datasets demonstrate LightGNN's effectiveness, significantly improving both computational efficiency and recommendation accuracy. Notably, LightGNN achieves an 80% reduction in edge count and 90% reduction in embedding entries while maintaining performance comparable to more complex state-of-the-art baselines. The implementation of our LightGNN framework is available at the github repository: https://github.com/HKUDS/LightGNN.

Accepted to WSDM 2025

References in corpus (18)

• Neural Graph Collaborative Filtering
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• Self-supervised Graph Learning for Recommendation
• The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
• Disentangled Graph Collaborative Filtering
• Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning
• Hypergraph Contrastive Collaborative Filtering
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
• Denoising Implicit Feedback for Recommendation
• Towards Representation Alignment and Uniformity in Collaborative Filtering
• Automated Self-Supervised Learning for Recommendation
• Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendation
• Graph-less Collaborative Filtering
• Unbiased Knowledge Distillation for Recommendation
• Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation
• A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions
• A Unified Lottery Ticket Hypothesis for Graph Neural Networks
• Incorporating Bias-aware Margins into Contrastive Loss for Collaborative Filtering