paper

Graph Neural Network leveraging Higher-order Class Label Connectivity for Heterophilous Graphs

paperactiveprovisionalgraph-neural-network-leveraging-higher-order-class-label-connectivity-for-heterophilous-graphs-134f1f7d·1 events·first seen 9d ago

Aliases: Graph Neural Network leveraging Higher-order Class Label Connectivity for Heterophilous Graphs

Co-occurring entities

Label Context Classifier

More like this (12)

Graph Neural Networks Graph Structure Learning Graph Neural Network Encoder E(3) equivariant graph neural network Graph Classification Multi-hop Graph Retrieval Hierarchical Graph Memory E(3)-equivariant GNN Graph-LLaDA Topological Neural Operators heterogeneous graph memory Understanding Truncated Positional Encodings for Graph Neural Networks

Recent events (1)

3arXiv · cs.AI·9d ago·source ↗

Label Context Classifier (LCC) improves GNN node classification on heterophilous graphs

A new arXiv preprint proposes the Label Context Classifier (LCC), a method for improving node classification in graph neural networks on heterophilous graphs where connected nodes tend to have different class labels. LCC generates label context embeddings via four types of directed walks to capture higher-order class label connectivity, and can be integrated with any existing GNN architecture. Experiments show GNNs augmented with LCC outperform state-of-the-art methods on heterophilous directed graphs.

Graph Neural Network leveraging Higher-order Class Label Connectivity for Heterophilous Graphs Label Context Classifier