GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks
| Title: | GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks |
|---|---|
| Authors: | Zhang, Mengmei, Sun, Mingwei, Wang, Peng, Fan, Shen, Mo, Yanhu, Xu, Xiaoxiao, Liu, Hong, Yang, Cheng, Shi, Chuan |
| Publication Year: | 2024 |
| Collection: | Computer Science |
| Subject Terms: | Computer Science - Artificial Intelligence |
| More Details: | Large language models (LLMs) like ChatGPT, exhibit powerful zero-shot and instruction-following capabilities, have catalyzed a revolutionary transformation across diverse fields, especially for open-ended tasks. While the idea is less explored in the graph domain, despite the availability of numerous powerful graph models (GMs), they are restricted to tasks in a pre-defined form. Although several methods applying LLMs to graphs have been proposed, they fail to simultaneously handle the pre-defined and open-ended tasks, with LLM as a node feature enhancer or as a standalone predictor. To break this dilemma, we propose to bridge the pretrained GM and LLM by a Translator, named GraphTranslator, aiming to leverage GM to handle the pre-defined tasks effectively and utilize the extended interface of LLMs to offer various open-ended tasks for GM. To train such Translator, we propose a Producer capable of constructing the graph-text alignment data along node information, neighbor information and model information. By translating node representation into tokens, GraphTranslator empowers an LLM to make predictions based on language instructions, providing a unified perspective for both pre-defined and open-ended tasks. Extensive results demonstrate the effectiveness of our proposed GraphTranslator on zero-shot node classification. The graph question answering experiments reveal our GraphTranslator potential across a broad spectrum of open-ended tasks through language instructions. Our code is available at: https://github.com/alibaba/GraphTranslator. |
| Document Type: | Working Paper |
| Access URL: | http://arxiv.org/abs/2402.07197 |
| Accession Number: | edsarx.2402.07197 |
| Database: | arXiv |
| FullText | Text: Availability: 0 CustomLinks: – Url: http://arxiv.org/abs/2402.07197 Name: EDS - Arxiv Category: fullText Text: View this record from Arxiv MouseOverText: View this record from Arxiv – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20240211&spage=&pages=&title=GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks&atitle=GraphTranslator%3A%20Aligning%20Graph%20Model%20to%20Large%20Language%20Model%20for%20Open-ended%20Tasks&aulast=Zhang%2C%20Mengmei&id=DOI: Name: Full Text Finder (for New FTF UI) (s8985755) Category: fullText Text: Find It @ SCU Libraries MouseOverText: Find It @ SCU Libraries |
|---|---|
| Header | DbId: edsarx DbLabel: arXiv An: edsarx.2402.07197 RelevancyScore: 1085 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 1085.39196777344 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Zhang%2C+Mengmei%22">Zhang, Mengmei</searchLink><br /><searchLink fieldCode="AR" term="%22Sun%2C+Mingwei%22">Sun, Mingwei</searchLink><br /><searchLink fieldCode="AR" term="%22Wang%2C+Peng%22">Wang, Peng</searchLink><br /><searchLink fieldCode="AR" term="%22Fan%2C+Shen%22">Fan, Shen</searchLink><br /><searchLink fieldCode="AR" term="%22Mo%2C+Yanhu%22">Mo, Yanhu</searchLink><br /><searchLink fieldCode="AR" term="%22Xu%2C+Xiaoxiao%22">Xu, Xiaoxiao</searchLink><br /><searchLink fieldCode="AR" term="%22Liu%2C+Hong%22">Liu, Hong</searchLink><br /><searchLink fieldCode="AR" term="%22Yang%2C+Cheng%22">Yang, Cheng</searchLink><br /><searchLink fieldCode="AR" term="%22Shi%2C+Chuan%22">Shi, Chuan</searchLink> – Name: DatePubCY Label: Publication Year Group: Date Data: 2024 – Name: Subset Label: Collection Group: HoldingsInfo Data: Computer Science – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Computer+Science+-+Artificial+Intelligence%22">Computer Science - Artificial Intelligence</searchLink> – Name: Abstract Label: Description Group: Ab Data: Large language models (LLMs) like ChatGPT, exhibit powerful zero-shot and instruction-following capabilities, have catalyzed a revolutionary transformation across diverse fields, especially for open-ended tasks. While the idea is less explored in the graph domain, despite the availability of numerous powerful graph models (GMs), they are restricted to tasks in a pre-defined form. Although several methods applying LLMs to graphs have been proposed, they fail to simultaneously handle the pre-defined and open-ended tasks, with LLM as a node feature enhancer or as a standalone predictor. To break this dilemma, we propose to bridge the pretrained GM and LLM by a Translator, named GraphTranslator, aiming to leverage GM to handle the pre-defined tasks effectively and utilize the extended interface of LLMs to offer various open-ended tasks for GM. To train such Translator, we propose a Producer capable of constructing the graph-text alignment data along node information, neighbor information and model information. By translating node representation into tokens, GraphTranslator empowers an LLM to make predictions based on language instructions, providing a unified perspective for both pre-defined and open-ended tasks. Extensive results demonstrate the effectiveness of our proposed GraphTranslator on zero-shot node classification. The graph question answering experiments reveal our GraphTranslator potential across a broad spectrum of open-ended tasks through language instructions. Our code is available at: https://github.com/alibaba/GraphTranslator. – Name: TypeDocument Label: Document Type Group: TypDoc Data: Working Paper – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2402.07197" linkWindow="_blank">http://arxiv.org/abs/2402.07197</link> – Name: AN Label: Accession Number Group: ID Data: edsarx.2402.07197 |
| PLink | https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2402.07197 |
| RecordInfo | BibRecord: BibEntity: Subjects: – SubjectFull: Computer Science - Artificial Intelligence Type: general Titles: – TitleFull: GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Zhang, Mengmei – PersonEntity: Name: NameFull: Sun, Mingwei – PersonEntity: Name: NameFull: Wang, Peng – PersonEntity: Name: NameFull: Fan, Shen – PersonEntity: Name: NameFull: Mo, Yanhu – PersonEntity: Name: NameFull: Xu, Xiaoxiao – PersonEntity: Name: NameFull: Liu, Hong – PersonEntity: Name: NameFull: Yang, Cheng – PersonEntity: Name: NameFull: Shi, Chuan IsPartOfRelationships: – BibEntity: Dates: – D: 11 M: 02 Type: published Y: 2024 |
| ResultId | 1 |