LightGNN: Simple Graph Neural Network for Recommendation

2025-01-06

AI Summary

To address the high computational cost and deployment challenges of Graph Neural Network (GNN)-based recommender systems on large-scale, sparse, and noisy interaction data, this paper proposes LightGNN—a lightweight GNN architecture. Methodologically, LightGNN introduces three key innovations: (1) an enhanced observation graph to mitigate data noise; (2) a joint adaptive pruning mechanism that simultaneously reduces graph edges and embedding dimensions; and (3) hierarchical knowledge distillation to guide the pruning process. Under aggressive compression—80% edge pruning and 90% embedding dimension reduction—LightGNN maintains state-of-the-art (SOTA) recommendation accuracy. Experimental results demonstrate significant improvements in inference efficiency and recommendation quality, enabling practical deployment on resource-constrained edge devices. The implementation is publicly available.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Data Mining & Knowledge Management: Recommender Systems
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Graph Neural Networks
• Efficiency
• Recommendation Systems

Innovation

• LightGNN
• Simplified Graph Neural Network
• Recommendation System Optimization