Exploring the Role of Node Diversity in Directed Graph Representation Learning

Code

• github.com/huangJC0429/NDDGNN
  pytorch★ 3

Abstract

Manymethods of Directed Graph Neural Networks (DGNNs) are designed to equally treat nodes in the same neighbor set (i.e., out-neighbor set and in-neighbor set) for every node, without consider ing the node diversity in directed graphs, so they are often unavailable to adaptively acquire suitable information from neighbors of different directions. To alleviate this issue, in this paper, we investigate a new way to first consider node diversity for rep resentation learning on directed graphs, i.e., neigh bor diversity and degree diversity, and then propose a new NDDGNN framework to adaptively assign weights to both outgoing information and incom ing information at the node level. Extensive ex periments on seven real-world datasets validate the superior performance of our method compared to state-of-the-art methods in terms of both node clas sification and link prediction tasks.

Tasks

Reproductions