LightGNN: Simple Graph Neural Network for Recommendation

TL;DR

LightGNN is a lightweight, distillation-based graph neural network framework that significantly reduces model complexity for recommendation tasks while maintaining high accuracy, addressing scalability and robustness issues in large-scale, noisy datasets.

Contribution

We introduce LightGNN, a novel GNN pruning framework that combines adaptive edge and embedding removal with hierarchical knowledge distillation for efficient recommendation.

Findings

Achieves 80% reduction in edges and 90% in embeddings.

Maintains comparable recommendation accuracy to state-of-the-art models.

Improves computational efficiency significantly.

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.