Towards LLM-guided Efficient and Interpretable Multi-linear Tensor Network Rank Selection
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913545308864512 |
|---|---|
| author | Iacovides, Giorgos Zhou, Wuyang Mandic, Danilo |
| author_facet | Iacovides, Giorgos Zhou, Wuyang Mandic, Danilo |
| contents | We propose a novel framework that leverages large language models (LLMs) to guide the rank selection in tensor network models for higher-order data analysis. By utilising the intrinsic reasoning capabilities and domain knowledge of LLMs, our approach offers enhanced interpretability of the rank choices and can effectively optimise the objective function. This framework enables users without specialised domain expertise to utilise tensor network decompositions and understand the underlying rationale within the rank selection process. Experimental results validate our method on financial higher-order datasets, demonstrating interpretable reasoning, strong generalisation to unseen test data, and its potential for self-enhancement over successive iterations. This work is placed at the intersection of large language models and higher-order data analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_10728 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards LLM-guided Efficient and Interpretable Multi-linear Tensor Network Rank Selection Iacovides, Giorgos Zhou, Wuyang Mandic, Danilo Machine Learning Artificial Intelligence We propose a novel framework that leverages large language models (LLMs) to guide the rank selection in tensor network models for higher-order data analysis. By utilising the intrinsic reasoning capabilities and domain knowledge of LLMs, our approach offers enhanced interpretability of the rank choices and can effectively optimise the objective function. This framework enables users without specialised domain expertise to utilise tensor network decompositions and understand the underlying rationale within the rank selection process. Experimental results validate our method on financial higher-order datasets, demonstrating interpretable reasoning, strong generalisation to unseen test data, and its potential for self-enhancement over successive iterations. This work is placed at the intersection of large language models and higher-order data analysis. |
| title | Towards LLM-guided Efficient and Interpretable Multi-linear Tensor Network Rank Selection |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2410.10728 |