LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation

6 Feb 2020 Xiangnan He Kuan Deng Xiang Wang Yan Li Yongdong Zhang Meng Wang

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... (read more)

PDF Abstract

Datasets


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Recommendation Systems Gowalla LightGCN Recall@20 0.1830 # 3
nDCG@20 0.1554 # 1

Methods used in the Paper


METHOD TYPE
Convolution
Convolutions
GCN
Graph Models