Node classification in heterogeneous graphs, where nodes and/or edges have multiple types.
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
In this paper, we focus on graph representation learning of heterogeneous information network (HIN), in which various types of vertices are connected by various types of relations.
The derived node representations can be used to serve various downstream tasks, such as node classification and node clustering.
Ranked #7 on Heterogeneous Node Classification on DBLP (PACT) 14k
In this way, it leverages both local and non-local information simultaneously.
Ranked #1 on Heterogeneous Node Classification on DBLP (PACT) 14k (Macro-F1 (60% training data) metric)
The task of classifying multi-relational data spans a wide range of domains such as document classification in citation networks, classification of emails, and protein labeling in proteins interaction graphs.