Multi-domain Knowledge Graph Collaborative Pre-training and Prompt Tuning for Diverse Downstream Tasks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916255248678912 |
|---|---|
| author | Zhang, Yichi Hu, Binbin Chen, Zhuo Guo, Lingbing Liu, Ziqi Zhang, Zhiqiang Liang, Lei Chen, Huajun Zhang, Wen |
| author_facet | Zhang, Yichi Hu, Binbin Chen, Zhuo Guo, Lingbing Liu, Ziqi Zhang, Zhiqiang Liang, Lei Chen, Huajun Zhang, Wen |
| contents | Knowledge graphs (KGs) provide reliable external knowledge for a wide variety of AI tasks in the form of structured triples. Knowledge graph pre-training (KGP) aims to pre-train neural networks on large-scale KGs and provide unified interfaces to enhance different downstream tasks, which is a key direction for KG management, maintenance, and applications. Existing works often focus on purely research questions in open domains, or they are not open source due to data security and privacy in real scenarios. Meanwhile, existing studies have not explored the training efficiency and transferability of KGP models in depth. To address these problems, We propose a framework MuDoK to achieve multi-domain collaborative pre-training and efficient prefix prompt tuning to serve diverse downstream tasks like recommendation and text understanding. Our design is a plug-and-play prompt learning approach that can be flexibly adapted to different downstream task backbones. In response to the lack of open-source benchmarks, we constructed a new multi-domain KGP benchmark called KPI with two large-scale KGs and six different sub-domain tasks to evaluate our method and open-sourced it for subsequent research. We evaluated our approach based on constructed KPI benchmarks using diverse backbone models in heterogeneous downstream tasks. The experimental results show that our framework brings significant performance gains, along with its generality, efficiency, and transferability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_13085 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-domain Knowledge Graph Collaborative Pre-training and Prompt Tuning for Diverse Downstream Tasks Zhang, Yichi Hu, Binbin Chen, Zhuo Guo, Lingbing Liu, Ziqi Zhang, Zhiqiang Liang, Lei Chen, Huajun Zhang, Wen Computation and Language Artificial Intelligence Knowledge graphs (KGs) provide reliable external knowledge for a wide variety of AI tasks in the form of structured triples. Knowledge graph pre-training (KGP) aims to pre-train neural networks on large-scale KGs and provide unified interfaces to enhance different downstream tasks, which is a key direction for KG management, maintenance, and applications. Existing works often focus on purely research questions in open domains, or they are not open source due to data security and privacy in real scenarios. Meanwhile, existing studies have not explored the training efficiency and transferability of KGP models in depth. To address these problems, We propose a framework MuDoK to achieve multi-domain collaborative pre-training and efficient prefix prompt tuning to serve diverse downstream tasks like recommendation and text understanding. Our design is a plug-and-play prompt learning approach that can be flexibly adapted to different downstream task backbones. In response to the lack of open-source benchmarks, we constructed a new multi-domain KGP benchmark called KPI with two large-scale KGs and six different sub-domain tasks to evaluate our method and open-sourced it for subsequent research. We evaluated our approach based on constructed KPI benchmarks using diverse backbone models in heterogeneous downstream tasks. The experimental results show that our framework brings significant performance gains, along with its generality, efficiency, and transferability. |
| title | Multi-domain Knowledge Graph Collaborative Pre-training and Prompt Tuning for Diverse Downstream Tasks |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2405.13085 |