paper-with-me

Papers

Edge Entropy as an Indicator of the Effectiveness of GNNs over CNNs for Node Classification

2020-12-16 · Lavender Yao Jiang, John Shi, Mark Cheung, Oren Wright, José M. F. Moura

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.

📄 PDF Abstract BibTeX arXiv:2012.08698

Code (0)

등록된 구현이 없습니다.

Tasks

Node Classification

Similar Papers 제목 키워드 기반

Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophily

2022-03-19 · Jie Chen, Shouzhen Chen, Junbin Gao, Zengfeng Huang 외

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 Classification

Unsupervised Graph Clustering with Deep Structural Entropy

2025-05-20 · Jingyun Zhang, Hao Peng, Li Sun, Guanlin Wu 외

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+1

Methods of nonlinear dynamics and the construction of cryptocurrency crisis phenomena precursors

2018-07-20

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 Analysis

Handling Missing Data via Max-Entropy Regularized Graph Autoencoder

2022-11-30 · Ziqi Gao, Yifan Niu, Jiashun Cheng, Jianheng Tang 외

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…

AttributeImputation

Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs

2023-06-09 · Lirong Wu, Haitao Lin, Yufei Huang, Stan Z. Li

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…