Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.20324 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909870510309376 |
|---|---|
| author | Berndt, Torben Walker, Benjamin Qin, Tiexin Stühmer, Jan Kormilitzin, Andrey |
| author_facet | Berndt, Torben Walker, Benjamin Qin, Tiexin Stühmer, Jan Kormilitzin, Andrey |
| contents | Dynamic graphs exhibit complex temporal dynamics due to the interplay between evolving node features and changing network structures. Recently, Graph Neural Controlled Differential Equations (Graph Neural CDEs) successfully adapted Neural CDEs from paths on Euclidean domains to paths on graph domains. Building on this foundation, we introduce Permutation Equivariant Neural Graph CDEs, which project Graph Neural CDEs onto permutation equivariant function spaces. This significantly reduces the model's parameter count without compromising representational power, resulting in more efficient training and improved generalisation. We empirically demonstrate the advantages of our approach through experiments on simulated dynamical systems and real-world tasks, showing improved performance in both interpolation and extrapolation scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_20324 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Permutation Equivariant Neural Controlled Differential Equations for Dynamic Graph Representation Learning Berndt, Torben Walker, Benjamin Qin, Tiexin Stühmer, Jan Kormilitzin, Andrey Machine Learning Dynamic graphs exhibit complex temporal dynamics due to the interplay between evolving node features and changing network structures. Recently, Graph Neural Controlled Differential Equations (Graph Neural CDEs) successfully adapted Neural CDEs from paths on Euclidean domains to paths on graph domains. Building on this foundation, we introduce Permutation Equivariant Neural Graph CDEs, which project Graph Neural CDEs onto permutation equivariant function spaces. This significantly reduces the model's parameter count without compromising representational power, resulting in more efficient training and improved generalisation. We empirically demonstrate the advantages of our approach through experiments on simulated dynamical systems and real-world tasks, showing improved performance in both interpolation and extrapolation scenarios. |
| title | Permutation Equivariant Neural Controlled Differential Equations for Dynamic Graph Representation Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2506.20324 |