Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2402.12984 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910337442250752 |
|---|---|
| author | Huang, Xuanwen Han, Kaiqiao Yang, Yang Bao, Dezheng Tao, Quanjin Chai, Ziwei Zhu, Qi |
| author_facet | Huang, Xuanwen Han, Kaiqiao Yang, Yang Bao, Dezheng Tao, Quanjin Chai, Ziwei Zhu, Qi |
| contents | Recently, large language models (LLMs) have demonstrated superior capabilities in understanding and zero-shot learning on textual data, promising significant advances for many text-related domains. In the graph domain, various real-world scenarios also involve textual data, where tasks and node features can be described by text. These text-attributed graphs (TAGs) have broad applications in social media, recommendation systems, etc. Thus, this paper explores how to utilize LLMs to model TAGs. Previous methods for TAG modeling are based on million-scale LMs. When scaled up to billion-scale LLMs, they face huge challenges in computational costs. Additionally, they also ignore the zero-shot inference capabilities of LLMs. Therefore, we propose GraphAdapter, which uses a graph neural network (GNN) as an efficient adapter in collaboration with LLMs to tackle TAGs. In terms of efficiency, the GNN adapter introduces only a few trainable parameters and can be trained with low computation costs. The entire framework is trained using auto-regression on node text (next token prediction). Once trained, GraphAdapter can be seamlessly fine-tuned with task-specific prompts for various downstream tasks. Through extensive experiments across multiple real-world TAGs, GraphAdapter based on Llama 2 gains an average improvement of approximately 5\% in terms of node classification. Furthermore, GraphAdapter can also adapt to other language models, including RoBERTa, GPT-2. The promising results demonstrate that GNNs can serve as effective adapters for LLMs in TAG modeling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_12984 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Can GNN be Good Adapter for LLMs? Huang, Xuanwen Han, Kaiqiao Yang, Yang Bao, Dezheng Tao, Quanjin Chai, Ziwei Zhu, Qi Computation and Language Artificial Intelligence Recently, large language models (LLMs) have demonstrated superior capabilities in understanding and zero-shot learning on textual data, promising significant advances for many text-related domains. In the graph domain, various real-world scenarios also involve textual data, where tasks and node features can be described by text. These text-attributed graphs (TAGs) have broad applications in social media, recommendation systems, etc. Thus, this paper explores how to utilize LLMs to model TAGs. Previous methods for TAG modeling are based on million-scale LMs. When scaled up to billion-scale LLMs, they face huge challenges in computational costs. Additionally, they also ignore the zero-shot inference capabilities of LLMs. Therefore, we propose GraphAdapter, which uses a graph neural network (GNN) as an efficient adapter in collaboration with LLMs to tackle TAGs. In terms of efficiency, the GNN adapter introduces only a few trainable parameters and can be trained with low computation costs. The entire framework is trained using auto-regression on node text (next token prediction). Once trained, GraphAdapter can be seamlessly fine-tuned with task-specific prompts for various downstream tasks. Through extensive experiments across multiple real-world TAGs, GraphAdapter based on Llama 2 gains an average improvement of approximately 5\% in terms of node classification. Furthermore, GraphAdapter can also adapt to other language models, including RoBERTa, GPT-2. The promising results demonstrate that GNNs can serve as effective adapters for LLMs in TAG modeling. |
| title | Can GNN be Good Adapter for LLMs? |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2402.12984 |