Exact Subgraph Isomorphism Network with Mixed $L_{0,2}$ Norm Constraint for Predictive Graph Mining
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908824291508224 |
|---|---|
| author | Kojima, Taiga Kajita, Haruto Kohara, Ayato Karasuyama, Masayuki |
| author_facet | Kojima, Taiga Kajita, Haruto Kohara, Ayato Karasuyama, Masayuki |
| contents | In the graph-level prediction task (predict a label for a given graph), the information contained in subgraphs of the input graph plays a key role. In this paper, we propose Exact subgraph Isomorphism Network (EIN), which combines the exact subgraph enumeration, a neural network, and a sparse regularization by the mixed $L_{0,2}$ norm constraint. In general, building a graph-level prediction model achieving high discriminative ability along with interpretability is still a challenging problem. Our combination of the subgraph enumeration and neural network contributes to high discriminative ability about the subgraph structure of the input graph. Further, the sparse regularization in EIN enables us 1) to derive an effective pruning strategy that mitigates computational difficulty of the enumeration while maintaining the prediction performance, and 2) to identify important subgraphs that contributes to high interpretability. We empirically show that EIN has sufficiently high prediction performance compared with standard graph neural network models, and also, we show examples of post-hoc analysis based on the selected subgraphs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_21699 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exact Subgraph Isomorphism Network with Mixed $L_{0,2}$ Norm Constraint for Predictive Graph Mining Kojima, Taiga Kajita, Haruto Kohara, Ayato Karasuyama, Masayuki Machine Learning In the graph-level prediction task (predict a label for a given graph), the information contained in subgraphs of the input graph plays a key role. In this paper, we propose Exact subgraph Isomorphism Network (EIN), which combines the exact subgraph enumeration, a neural network, and a sparse regularization by the mixed $L_{0,2}$ norm constraint. In general, building a graph-level prediction model achieving high discriminative ability along with interpretability is still a challenging problem. Our combination of the subgraph enumeration and neural network contributes to high discriminative ability about the subgraph structure of the input graph. Further, the sparse regularization in EIN enables us 1) to derive an effective pruning strategy that mitigates computational difficulty of the enumeration while maintaining the prediction performance, and 2) to identify important subgraphs that contributes to high interpretability. We empirically show that EIN has sufficiently high prediction performance compared with standard graph neural network models, and also, we show examples of post-hoc analysis based on the selected subgraphs. |
| title | Exact Subgraph Isomorphism Network with Mixed $L_{0,2}$ Norm Constraint for Predictive Graph Mining |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.21699 |