The Tsetlin Machine Goes Deep: Logical Learning and Reasoning With Graphs
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909015089348608 |
|---|---|
| author | Granmo, Ole-Christoffer Abdelwahab, Youmna Andersen, Per-Arne Borgersen, Karl Audun K. Clarke, Paul F. A. Dumbre, Kunal Grønningsæter, Ylva Halenka, Vojtech Helin, Runar Jiao, Lei Khalid, Ahmed Omslandseter, Rebekka Saha, Rupsa Shende, Mayur Zhang, Xuan |
| author_facet | Granmo, Ole-Christoffer Abdelwahab, Youmna Andersen, Per-Arne Borgersen, Karl Audun K. Clarke, Paul F. A. Dumbre, Kunal Grønningsæter, Ylva Halenka, Vojtech Helin, Runar Jiao, Lei Khalid, Ahmed Omslandseter, Rebekka Saha, Rupsa Shende, Mayur Zhang, Xuan |
| contents | Pattern recognition with concise and flat AND-rules makes the Tsetlin Machine (TM) both interpretable and efficient, while the power of Tsetlin automata enables accuracy comparable to deep learning on an increasing number of datasets. We introduce the Graph Tsetlin Machine (GraphTM) for learning interpretable deep clauses from graph-structured input. Moving beyond flat, fixed-length input, the GraphTM gets more versatile, supporting sequences, grids, relations, and multimodality. Through message passing, the GraphTM builds nested deep clauses to recognize sub-graph patterns with exponentially fewer clauses, increasing both interpretability and data utilization. For image classification, GraphTM preserves interpretability and achieves 3.86%-points higher accuracy on CIFAR-10 than a convolutional TM. For tracking action coreference, faced with increasingly challenging tasks, GraphTM outperforms other reinforcement learning methods by up to 20.6%-points. In recommendation systems, it tolerates increasing noise to a great extent, similar to a GCN. Finally, for viral genome sequence data, GraphTM is competitive with BiLSTM-CNN and GCN accuracy-wise, training ~2.5x faster than GCN. The GraphTM's application to these varied fields demonstrates how graph representation learning and deep clauses bring new possibilities for TM learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_14874 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Tsetlin Machine Goes Deep: Logical Learning and Reasoning With Graphs Granmo, Ole-Christoffer Abdelwahab, Youmna Andersen, Per-Arne Borgersen, Karl Audun K. Clarke, Paul F. A. Dumbre, Kunal Grønningsæter, Ylva Halenka, Vojtech Helin, Runar Jiao, Lei Khalid, Ahmed Omslandseter, Rebekka Saha, Rupsa Shende, Mayur Zhang, Xuan Machine Learning Artificial Intelligence Pattern recognition with concise and flat AND-rules makes the Tsetlin Machine (TM) both interpretable and efficient, while the power of Tsetlin automata enables accuracy comparable to deep learning on an increasing number of datasets. We introduce the Graph Tsetlin Machine (GraphTM) for learning interpretable deep clauses from graph-structured input. Moving beyond flat, fixed-length input, the GraphTM gets more versatile, supporting sequences, grids, relations, and multimodality. Through message passing, the GraphTM builds nested deep clauses to recognize sub-graph patterns with exponentially fewer clauses, increasing both interpretability and data utilization. For image classification, GraphTM preserves interpretability and achieves 3.86%-points higher accuracy on CIFAR-10 than a convolutional TM. For tracking action coreference, faced with increasingly challenging tasks, GraphTM outperforms other reinforcement learning methods by up to 20.6%-points. In recommendation systems, it tolerates increasing noise to a great extent, similar to a GCN. Finally, for viral genome sequence data, GraphTM is competitive with BiLSTM-CNN and GCN accuracy-wise, training ~2.5x faster than GCN. The GraphTM's application to these varied fields demonstrates how graph representation learning and deep clauses bring new possibilities for TM learning. |
| title | The Tsetlin Machine Goes Deep: Logical Learning and Reasoning With Graphs |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.14874 |