Customizing Graph Neural Networks using Path Reweighting

2 code implementations • 21 Jun 2021 • Jianpeng Chen, Yujing Wang, Ming Zeng, Zongyi Xiang, Bitan Hou, Yunhai Tong, Ole J. Mengshoel, Yazhou Ren

Specifically, the proposed CustomGNN can automatically learn the high-level semantics for specific downstream tasks to highlight semantically relevant paths as well to filter out task-irrelevant noises in a graph.

Data Augmentation Graph Attention +1