Multi-View Subgraph Neural Networks: Self-Supervised Learning with Scarce Labeled Data

arXiv:2404.12569v1 Announce Type: new
Abstract: While graph neural networks (GNNs) have become the de-facto standard for graph-based node classification, they impose a strong assumption on the availability of sufficient labeled samples. This assumption restricts the classification performance of prevailing GNNs on many real-world applications suffering from low-data regimes. Specifically, features extracted from scarce labeled nodes could not provide sufficient supervision for the unlabeled samples, leading to severe over-fitting. In this work, we point out that leveraging subgraphs to capture long-range …

abstract applications arxiv availability become classification cs.ai cs.lg data features gnns graph graph-based graph neural networks low networks neural networks node performance samples self-supervised learning standard supervised learning type view world