A Hierarchical Language Model For Interpretable Graph Reasoning
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_ | 1866912093960142848 |
|---|---|
| author | Khurana, Sambhav Li, Xiner Gui, Shurui Ji, Shuiwang |
| author_facet | Khurana, Sambhav Li, Xiner Gui, Shurui Ji, Shuiwang |
| contents | Large language models (LLMs) are being increasingly explored for graph tasks. Despite their remarkable success in text-based tasks, LLMs' capabilities in understanding explicit graph structures remain limited, particularly with large graphs. In this work, we introduce Hierarchical Language Model for Graph (HLM-G), which employs a two-block architecture to capture node-centric local information and interaction-centric global structure, effectively enhancing graph structure understanding abilities. The proposed scheme allows LLMs to address various graph queries with high efficacy, efficiency, and robustness, while reducing computational costs on large-scale graph tasks. Furthermore, we demonstrate the interpretability of our model using intrinsic attention weights and established explainers. Comprehensive evaluations across diverse graph reasoning and real-world tasks of node, link, and graph-levels highlight the superiority of our method, marking a significant advancement in the application of LLMs to graph understanding. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_22372 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Hierarchical Language Model For Interpretable Graph Reasoning Khurana, Sambhav Li, Xiner Gui, Shurui Ji, Shuiwang Machine Learning Artificial Intelligence Large language models (LLMs) are being increasingly explored for graph tasks. Despite their remarkable success in text-based tasks, LLMs' capabilities in understanding explicit graph structures remain limited, particularly with large graphs. In this work, we introduce Hierarchical Language Model for Graph (HLM-G), which employs a two-block architecture to capture node-centric local information and interaction-centric global structure, effectively enhancing graph structure understanding abilities. The proposed scheme allows LLMs to address various graph queries with high efficacy, efficiency, and robustness, while reducing computational costs on large-scale graph tasks. Furthermore, we demonstrate the interpretability of our model using intrinsic attention weights and established explainers. Comprehensive evaluations across diverse graph reasoning and real-world tasks of node, link, and graph-levels highlight the superiority of our method, marking a significant advancement in the application of LLMs to graph understanding. |
| title | A Hierarchical Language Model For Interpretable Graph Reasoning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2410.22372 |