LightGCN

TLDR

Graph Convolution Networks have become state‑of‑the‑art for collaborative filtering, yet their effectiveness remains poorly understood and prior work lacks thorough ablation of GCN components originally designed for graph classification. Our experiments show that feature transformation and nonlinear activation in GCNs add little benefit to recommendation, increase training difficulty, and actually degrade performance.

Abstract

Graph Convolution Network (GCN) has become new state-of-the-art for collaborative filtering. Nevertheless, the reasons of its effectiveness for recommendation are not well understood. Existing work that adapts GCN to recommendation lacks thorough ablation analyses on GCN, which is originally designed for graph classification tasks and equipped with many neural network operations. However, we empirically find that the two most common designs in GCNs -- feature transformation and nonlinear activation -- contribute little to the performance of collaborative filtering. Even worse, including them adds to the difficulty of training and degrades recommendation performance.