@inproceedings{ai-etal-2024-advancement,
title = "Advancement in Graph Understanding: A Multimodal Benchmark and Fine-Tuning of Vision-Language Models",
author = "Ai, Qihang and
Li, Jiafan and
Dai, Jincheng and
Zhou, Jianwu and
Liu, Lemao and
Jiang, Haiyun and
Shi, Shuming",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.404",
doi = "10.18653/v1/2024.acl-long.404",
pages = "7485--7501",
abstract = "Graph data organizes complex relationships and interactions between objects, facilitating advanced analysis and decision-making across different fields. In this paper, we propose a new paradigm for interactive and instructional graph data understanding and reasoning.Instead of adopting complex graph neural models or heuristic graph-to-text instruction design, we leverage Vision-Language Models (VLMs) to encode the graph images with varying structures across different domains. This paper first evaluates the capabilities of public VLMs in graph learning from multiple aspects. Then it introduces a novel instruction-following dataset for multimodal graph understanding and reasoning in English and Chinese. Besides, by fine-tuning MiniGPT-4 and LLaVA on our dataset, we achieved an accuracy increase of 5{\%}-15{\%} compared to baseline models, with the best-performing model attaining scores comparable to Gemini in GPT-asissted Evaluation. This research not only showcases the potential of integrating VLMs with graph data but also opens new avenues for advancements in graph data understanding.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ai-etal-2024-advancement">
<titleInfo>
<title>Advancement in Graph Understanding: A Multimodal Benchmark and Fine-Tuning of Vision-Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qihang</namePart>
<namePart type="family">Ai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiafan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jincheng</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianwu</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lemao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haiyun</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuming</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Graph data organizes complex relationships and interactions between objects, facilitating advanced analysis and decision-making across different fields. In this paper, we propose a new paradigm for interactive and instructional graph data understanding and reasoning.Instead of adopting complex graph neural models or heuristic graph-to-text instruction design, we leverage Vision-Language Models (VLMs) to encode the graph images with varying structures across different domains. This paper first evaluates the capabilities of public VLMs in graph learning from multiple aspects. Then it introduces a novel instruction-following dataset for multimodal graph understanding and reasoning in English and Chinese. Besides, by fine-tuning MiniGPT-4 and LLaVA on our dataset, we achieved an accuracy increase of 5%-15% compared to baseline models, with the best-performing model attaining scores comparable to Gemini in GPT-asissted Evaluation. This research not only showcases the potential of integrating VLMs with graph data but also opens new avenues for advancements in graph data understanding.</abstract>
<identifier type="citekey">ai-etal-2024-advancement</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.404</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.404</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>7485</start>
<end>7501</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Advancement in Graph Understanding: A Multimodal Benchmark and Fine-Tuning of Vision-Language Models
%A Ai, Qihang
%A Li, Jiafan
%A Dai, Jincheng
%A Zhou, Jianwu
%A Liu, Lemao
%A Jiang, Haiyun
%A Shi, Shuming
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F ai-etal-2024-advancement
%X Graph data organizes complex relationships and interactions between objects, facilitating advanced analysis and decision-making across different fields. In this paper, we propose a new paradigm for interactive and instructional graph data understanding and reasoning.Instead of adopting complex graph neural models or heuristic graph-to-text instruction design, we leverage Vision-Language Models (VLMs) to encode the graph images with varying structures across different domains. This paper first evaluates the capabilities of public VLMs in graph learning from multiple aspects. Then it introduces a novel instruction-following dataset for multimodal graph understanding and reasoning in English and Chinese. Besides, by fine-tuning MiniGPT-4 and LLaVA on our dataset, we achieved an accuracy increase of 5%-15% compared to baseline models, with the best-performing model attaining scores comparable to Gemini in GPT-asissted Evaluation. This research not only showcases the potential of integrating VLMs with graph data but also opens new avenues for advancements in graph data understanding.
%R 10.18653/v1/2024.acl-long.404
%U https://aclanthology.org/2024.acl-long.404
%U https://doi.org/10.18653/v1/2024.acl-long.404
%P 7485-7501
Markdown (Informal)
[Advancement in Graph Understanding: A Multimodal Benchmark and Fine-Tuning of Vision-Language Models](https://aclanthology.org/2024.acl-long.404) (Ai et al., ACL 2024)
ACL