LGRPool: Hierarchical Graph Pooling Via Local-Global Regularisation
Not on the map. Why?
Abstract (arXiv)
Hierarchical graph pooling(HGP) are designed to consider the fact that conventional graph neural networks(GNN) are inherently flat and are also not multiscale. However, most HGP methods suffer not only from lack of considering global topology of the graph and focusing on the feature learning aspect, but also they do not align local and global features since graphs should inherently be analyzed in a multiscale way. LGRPool is proposed in the present paper as a HGP in the framework of expectation maximization in machine learning that aligns local and global aspects of message passing with each other using a regularizer to force the global topological information to be inline with the local message passing at different scales through the representations at different layers of HGP. Experimental results on some graph classification benchmarks show that it slightly outperforms some baselines.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 45 references that are in the map. First posted on arXiv 11 Apr 2025.
Builds on
36 of 45 references.
References · 36
- 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
- 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
- 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 595
- 2019Graph U-Netscited by 492
- 2019Self-Attention Graph Poolingcited by 421
- 2019Diffusion Improves Graph Learningcited by 414
- 2020Towards Deeper Graph Neural Networkscited by 296
- 2020Scaling Graph Neural Networks with Approximate PageRankcited by 174
- 2020Graph Clustering with Graph Neural Networkscited by 163
- 2021Accurate Learning of Graph Representations with Graph Multiset Poolingcited by 120
- 2020Implicit Graph Neural Networkscited by 100
- 2022Structural Entropy Guided Graph Hierarchical Poolingcited by 62
24 more
- 2023Locality-Aware Graph-Rewiring in GNNscited by 56
- 2019Edge Contraction Pooling for Graph Neural Networkscited by 53
- 2022KerGNNs: Interpretable Graph Neural Networks with Graph Kernelscited by 50
- 2020Convolutional Kernel Networks for Graph-Structured Datacited by 38
- 2022Rewiring with Positional Encodings for Graph Neural Networkscited by 36
- 2018RetGK: Graph Kernels based on Return Probabilities of Random Walkscited by 32
- 2023Graph Positional Encoding via Random Feature Propagationcited by 31
- 2023DGCLUSTER: A Neural Framework for Attributed Graph Clustering via Modularity Maximizationcited by 21
- 2021Theoretically Improving Graph Neural Networks via Anonymous Walk Graph Kernelscited by 19
- 2022pathGCN: Learning General Graph Spatial Operators from Pathscited by 15
- 2019Learning Graph Pooling and Hybrid Convolutional Operations for Text Representationscited by 13
- 2021Graph Kernel Neural Networkscited by 13
- 2022Transforming PageRank into an Infinite-Depth Graph Neural Networkcited by 11
- 2022From Local to Global: Spectral-Inspired Graph Neural Networkscited by 11
- 2023General Graph Random Featurescited by 10
- 2024CKGConv: General Graph Convolution with Continuous Kernelscited by 5
- 2024Global-Local Graph Neural Networks for Node-Classificationcited by 4
- 2022LiftPool: Lifting-based Graph Pooling for Hierarchical Graph Representation Learningcited by 3
- 2024Optimal Time Complexity Algorithms for Computing General Random Walk Graph Kernels on Sparse Graphscited by 3
- 2021Layer-wise Adaptive Graph Convolution Networks Using Generalized Pagerankcited by 2
- 2023Can strong structural encoding reduce the importance of Message Passing?cited by 2
- 2024SSHPool: The Separated Subgraph-based Hierarchical Poolingcited by 1
- 2024ENADPool: The Edge-Node Attention-based Differentiable Pooling for Graph Neural Networkscited by 1
- 2024Edge-Based Graph Component Poolingcited by 1
Built on by
Not cited yet.