Symbolic Graph Intelligence: Hypervector Message Passing for Learning Graph-Level Patterns with Tsetlin Machines
Fuente:
arXiv
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915404704645120 |
|---|---|
| author | Blakely, Christian D. |
| author_facet | Blakely, Christian D. |
| contents | We propose a multilayered symbolic framework for general graph classification that leverages sparse binary hypervectors and Tsetlin Machines. Each graph is encoded through structured message passing, where node, edge, and attribute information are bound and bundled into a symbolic hypervector. This process preserves the hierarchical semantics of the graph through layered binding from node attributes to edge relations to structural roles resulting in a compact, discrete representation. We also formulate a local interpretability framework which lends itself to a key advantage of our approach being locally interpretable. We validate our method on TUDataset benchmarks, demonstrating competitive accuracy with strong symbolic transparency compared to neural graph models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_16537 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Symbolic Graph Intelligence: Hypervector Message Passing for Learning Graph-Level Patterns with Tsetlin Machines Blakely, Christian D. Machine Learning Artificial Intelligence We propose a multilayered symbolic framework for general graph classification that leverages sparse binary hypervectors and Tsetlin Machines. Each graph is encoded through structured message passing, where node, edge, and attribute information are bound and bundled into a symbolic hypervector. This process preserves the hierarchical semantics of the graph through layered binding from node attributes to edge relations to structural roles resulting in a compact, discrete representation. We also formulate a local interpretability framework which lends itself to a key advantage of our approach being locally interpretable. We validate our method on TUDataset benchmarks, demonstrating competitive accuracy with strong symbolic transparency compared to neural graph models. |
| title | Symbolic Graph Intelligence: Hypervector Message Passing for Learning Graph-Level Patterns with Tsetlin Machines |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.16537 |