Revisiting Neighborhood Aggregation in Graph Neural Networks for Node Classification using Statistical Signal Processing
We delve into the issue of node classification within graphs, specifically reevaluating the concept of neighborhood aggregation, which is a fundamental component in graph neural networks (GNNs). Our analysis reveals conceptual flaws within certain benchmark GNN models when operating under the assumption of edge-independent node labels, a condition commonly observed in benchmark graphs employed for node classification. Approaching neighborhood aggregation from a statistical signal processing perspective, our investigation provides novel insights which may be used to design more efficient GNN models.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationNode ClassificationSimilar Papers 제목 키워드 기반
GraphAIR: Graph Representation Learning with Neighborhood Aggregation and Interaction
Graph representation learning is of paramount importance for a variety of graph analytical tasks, ranging from node classification to community detection. Recently, graph convolutional networks (GCNs) have been successfu…
Community DetectionGeneral ClassificationGraph Representation LearningLink Prediction+2Just Jump: Dynamic Neighborhood Aggregation in Graph Neural Networks
We propose a dynamic neighborhood aggregation (DNA) procedure guided by (multi-head) attention for representation learning on graphs. In contrast to current graph neural networks which follow a simple neighborhood aggreg…
General ClassificationNode ClassificationRepresentation LearningNeighborhood Convolutional Network: A New Paradigm of Graph Neural Networks for Node Classification
The decoupled Graph Convolutional Network (GCN), a recent development of GCN that decouples the neighborhood aggregation and feature transformation in each convolutional layer, has shown promising performance for graph r…
Graph Representation LearningNode ClassificationRepresentation LearningTowards Powerful Graph Neural Networks: Diversity Matters
Graph neural networks (GNNs) offer us an effective framework for graph representation learning via layer-wise neighborhood aggregation. Their success is attributed to their expressive power at learning representation of …
DiversityGraph Representation LearningNode ClassificationRepresentation LearningOn Local Aggregation in Heterophilic Graphs
Many recent works have studied the performance of Graph Neural Networks (GNNs) in the context of graph homophily - a label-dependent measure of connectivity. Traditional GNNs generate node embeddings by aggregating infor…
Node Classification