Hypergraph-enhanced Dual Semi-supervised Graph Classification

arXiv:2405.04773v1 Announce Type: new
Abstract: In this paper, we study semi-supervised graph classification, which aims at accurately predicting the categories of graphs in scenarios with limited labeled graphs and abundant unlabeled graphs. Despite the promising capability of graph neural networks (GNNs), they typically require a large number of costly labeled graphs, while a wealth of unlabeled graphs fail to be effectively utilized. Moreover, GNNs are inherently limited to encoding local neighborhood information using message-passing mechanisms, thus lacking the ability to …

abstract arxiv capability classification cs.ai cs.ir cs.lg cs.si gnns graph graph neural networks graphs hypergraph networks neural networks paper semi semi-supervised study type wealth while