CoATA jointly augments topology and attributes, enriching features by propagation and reconstructing edges with Personalized PageRank on a node-attribute bipartite graph, to improve node classification on six of seven benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CoATA: Effective Co-Augmentation of Topology and Attribute for Graph Neural Networks
CoATA jointly augments topology and attributes, enriching features by propagation and reconstructing edges with Personalized PageRank on a node-attribute bipartite graph, to improve node classification on six of seven benchmarks.