Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2508.06663 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911100285485056 |
|---|---|
| author | Chao, Yuan-Hung Lu, Chia-Hsun Shen, Chih-Ya |
| author_facet | Chao, Yuan-Hung Lu, Chia-Hsun Shen, Chih-Ya |
| contents | Graph Neural Networks (GNNs) have shown strong performance on graph-structured data, but their reliance on graph connectivity often limits scalability and efficiency. Kolmogorov-Arnold Networks (KANs), a recent architecture with learnable univariate functions, offer strong nonlinear expressiveness and efficient inference. In this work, we integrate KANs into three popular GNN architectures-GAT, SGC, and APPNP-resulting in three new models: KGAT, KSGC, and KAPPNP. We further adopt a multi-teacher knowledge amalgamation framework, where knowledge from multiple KAN-based GNNs is distilled into a graph-independent KAN student model. Experiments on benchmark datasets show that the proposed models improve node classification accuracy, and the knowledge amalgamation approach significantly boosts student model performance. Our findings highlight the potential of KANs for enhancing GNN expressiveness and for enabling efficient, graph-free inference. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_06663 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Transferring Social Network Knowledge from Multiple GNN Teachers to Kolmogorov-Arnold Networks Chao, Yuan-Hung Lu, Chia-Hsun Shen, Chih-Ya Machine Learning Graph Neural Networks (GNNs) have shown strong performance on graph-structured data, but their reliance on graph connectivity often limits scalability and efficiency. Kolmogorov-Arnold Networks (KANs), a recent architecture with learnable univariate functions, offer strong nonlinear expressiveness and efficient inference. In this work, we integrate KANs into three popular GNN architectures-GAT, SGC, and APPNP-resulting in three new models: KGAT, KSGC, and KAPPNP. We further adopt a multi-teacher knowledge amalgamation framework, where knowledge from multiple KAN-based GNNs is distilled into a graph-independent KAN student model. Experiments on benchmark datasets show that the proposed models improve node classification accuracy, and the knowledge amalgamation approach significantly boosts student model performance. Our findings highlight the potential of KANs for enhancing GNN expressiveness and for enabling efficient, graph-free inference. |
| title | Transferring Social Network Knowledge from Multiple GNN Teachers to Kolmogorov-Arnold Networks |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2508.06663 |