Graph Partial Label Learning with Potential Cause Discovering

arXiv:2403.11449v1 Announce Type: new
Abstract: Graph Neural Networks (GNNs) have gained considerable attention for their potential in addressing challenges posed by complex graph-structured data in diverse domains. However, accurately annotating graph data for training is difficult due to the inherent complexity and interconnectedness of graphs. To tackle this issue, we propose a novel graph representation learning method that enables GNN models to effectively learn discriminative information even in the presence of noisy labels within the context of Partially Labeled Learning …

abstract arxiv attention challenges complexity cs.lg data diverse domains gnns graph graph data graph neural networks graphs however issue networks neural networks structured data training type