Edge Entropy as an Indicator of the Effectiveness of GNNs over CNNs for Node Classification
Graph neural networks (GNNs) extend convolutional neural networks (CNNs) to graph-based data. A question that arises is how much performance improvement does the underlying graph structure in the GNN provide over the CNN (that ignores this graph structure). To address this question, we introduce edge entropy and evaluate how good an indicator it is for possible performance improvement of GNNs over CNNs. Our results on node classification with synthetic and real datasets show that lower values of edge entropy predict larger expected performance gains of GNNs over CNNs, and, conversely, higher edge entropy leads to expected smaller improvement gains.
Code (0)
등록된 구현이 없습니다.
Tasks
Node ClassificationSimilar Papers 제목 키워드 기반
Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophily
Due to the homophily assumption in graph convolution networks (GNNs), a common consensus in the graph node classification task is that GNNs perform well on homophilic graphs but may fail on heterophilic graphs with many …
Node ClassificationUnsupervised Graph Clustering with Deep Structural Entropy
Research on Graph Structure Learning (GSL) provides key insights for graph-based clustering, yet current methods like Graph Neural Networks (GNNs), Graph Attention Networks (GATs), and contrastive learning often rely hea…
ClusteringContrastive LearningGraph AttentionGraph Clustering+1Methods of nonlinear dynamics and the construction of cryptocurrency crisis phenomena precursors
This article demonstrates the possibility of constructing indicators of critical and crisis phenomena in the volatile market of cryptocurrency. For this purpose, the methods of the theory of complex systems such as recur…
Time SeriesTime Series AnalysisHandling Missing Data via Max-Entropy Regularized Graph Autoencoder
Graph neural networks (GNNs) are popular weapons for modeling relational data. Existing GNNs are not specified for attribute-incomplete graphs, making missing attribute imputation a burning issue. Until recently, many wo…
AttributeImputationQuantifying the Knowledge in GNNs for Reliable Distillation into MLPs
To bridge the gaps between topology-aware Graph Neural Networks (GNNs) and inference-efficient Multi-Layer Perceptron (MLPs), GLNN proposes to distill knowledge from a well-trained teacher GNN into a student MLP. Despite…