DeGNN: Characterizing and Improving Graph Neural Networks with Graph Decomposition
Despite the wide application of Graph Convolutional Network (GCN), one major limitation is that it does not benefit from the increasing depth and suffers from the oversmoothing problem. In this work, we first characterize this phenomenon from the information-theoretic perspective and show that under certain conditions, the mutual information between the output after $l$ layers and the input of GCN converges to 0 exponentially with respect to $l$. We also show that, on the other hand, graph decomposition can potentially weaken the condition of such convergence rate, which enabled our analysis for GraphCNN. While different graph structures can only benefit from the corresponding decomposition, in practice, we propose an automatic connectivity-aware graph decomposition algorithm, DeGNN, to improve the performance of general graph neural networks. Extensive experiments on widely adopted benchmark datasets demonstrate that DeGNN can not only significantly boost the performance of corresponding GNNs, but also achieves the state-of-the-art performances.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph Neural NetworkMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DEGNN: Dual Experts Graph Neural Network Handling Both Edge and Node Feature Noise
Graph Neural Networks (GNNs) have achieved notable success in various applications over graph data. However, recent research has revealed that real-world graphs often contain noise, and GNNs are susceptible to noise in t…
Graph Neural NetworkGraph structure learningSelf-Supervised LearningRelaxing Continuous Constraints of Equivariant Graph Neural Networks for Physical Dynamics Learning
Incorporating Euclidean symmetries (e.g. rotation equivariance) as inductive biases into graph neural networks has improved their generalization ability and data efficiency in unbounded physical dynamics modeling. Howeve…
Graph Neural NetworkMultiple Graph Learning for Scalable Multi-view Clustering
Graph-based multi-view clustering has become an active topic due to the efficiency in characterizing both the complex structure and relationship between multimedia data. However, existing methods have the following short…
Clusteringgraph constructionGraph LearningCompressed Dynamic Mode Decomposition for Background Modeling
We introduce the method of compressed dynamic mode decomposition (cDMD) for background modeling. The dynamic mode decomposition (DMD) is a regression technique that integrates two of the leading data analysis methods in …
compressed sensingComputational EfficiencyGPUEffective and Efficient Graph Learning for Multi-view Clustering
Despite the impressive clustering performance and efficiency in characterizing both the relationship between data and cluster structure, existing graph-based multi-view clustering methods still have the following drawbac…
ClusteringGraph Learning