LGRPool: Hierarchical Graph Pooling Via Local-Global Regularisation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908313952714752 |
|---|---|
| author | Noravesh, Farshad Haffari, Reza Soon, Layki Pal, Arghya |
| author_facet | Noravesh, Farshad Haffari, Reza Soon, Layki Pal, Arghya |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_08530 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LGRPool: Hierarchical Graph Pooling Via Local-Global Regularisation Noravesh, Farshad Haffari, Reza Soon, Layki Pal, Arghya Machine Learning Artificial Intelligence 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. |
| title | LGRPool: Hierarchical Graph Pooling Via Local-Global Regularisation |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2504.08530 |