LLM Enhancers for GNNs: An Analysis from the Perspective of Causal Mechanism Identification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908403413024768 |
|---|---|
| author | Gao, Hang Huang, Wenxuan Wu, Fengge Zhao, Junsuo Zheng, Changwen Liu, Huaping |
| author_facet | Gao, Hang Huang, Wenxuan Wu, Fengge Zhao, Junsuo Zheng, Changwen Liu, Huaping |
| contents | The use of large language models (LLMs) as feature enhancers to optimize node representations, which are then used as inputs for graph neural networks (GNNs), has shown significant potential in graph representation learning. However, the fundamental properties of this approach remain underexplored. To address this issue, we propose conducting a more in-depth analysis of this issue based on the interchange intervention method. First, we construct a synthetic graph dataset with controllable causal relationships, enabling precise manipulation of semantic relationships and causal modeling to provide data for analysis. Using this dataset, we conduct interchange interventions to examine the deeper properties of LLM enhancers and GNNs, uncovering their underlying logic and internal mechanisms. Building on the analytical results, we design a plug-and-play optimization module to improve the information transfer between LLM enhancers and GNNs. Experiments across multiple datasets and models validate the proposed module. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_08265 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLM Enhancers for GNNs: An Analysis from the Perspective of Causal Mechanism Identification Gao, Hang Huang, Wenxuan Wu, Fengge Zhao, Junsuo Zheng, Changwen Liu, Huaping Machine Learning Artificial Intelligence The use of large language models (LLMs) as feature enhancers to optimize node representations, which are then used as inputs for graph neural networks (GNNs), has shown significant potential in graph representation learning. However, the fundamental properties of this approach remain underexplored. To address this issue, we propose conducting a more in-depth analysis of this issue based on the interchange intervention method. First, we construct a synthetic graph dataset with controllable causal relationships, enabling precise manipulation of semantic relationships and causal modeling to provide data for analysis. Using this dataset, we conduct interchange interventions to examine the deeper properties of LLM enhancers and GNNs, uncovering their underlying logic and internal mechanisms. Building on the analytical results, we design a plug-and-play optimization module to improve the information transfer between LLM enhancers and GNNs. Experiments across multiple datasets and models validate the proposed module. |
| title | LLM Enhancers for GNNs: An Analysis from the Perspective of Causal Mechanism Identification |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2505.08265 |