Multimodal Graph Learning for Generative Tasks

作者
Minji Yoon,Jing Yu Koh,Bryan Hooi,Ruslan Salakhutdinov
出处
期刊:Cornell University - arXiv [Cornell University]
标识
DOI:10.48550/arxiv.2310.07478
摘要

Multimodal learning combines multiple data modalities, broadening the types and complexity of data our models can utilize: for example, from plain text to image-caption pairs. Most multimodal learning algorithms focus on modeling simple one-to-one pairs of data from two modalities, such as image-caption pairs, or audio-text pairs. However, in most real-world settings, entities of different modalities interact with each other in more complex and multifaceted ways, going beyond one-to-one mappings. We propose to represent these complex relationships as graphs, allowing us to capture data with any number of modalities, and with complex relationships between modalities that can flexibly vary from one sample to another. Toward this goal, we propose Multimodal Graph Learning (MMGL), a general and systematic framework for capturing information from multiple multimodal neighbors with relational structures among them. In particular, we focus on MMGL for generative tasks, building upon pretrained Language Models (LMs), aiming to augment their text generation with multimodal neighbor contexts. We study three research questions raised by MMGL: (1) how can we infuse multiple neighbor information into the pretrained LMs, while avoiding scalability issues? (2) how can we infuse the graph structure information among multimodal neighbors into the LMs? and (3) how can we finetune the pretrained LMs to learn from the neighbor context in a parameter-efficient manner? We conduct extensive experiments to answer these three questions on MMGL and analyze the empirical results to pave the way for future MMGL research.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
充电宝的应助被suzy采纳,获得10
1秒前
盛龙完成签到,获得积分10
1秒前
lky1017完成签到,获得积分10
3秒前
shjddw完成签到,获得积分10
4秒前
情怀的应助被栗子砸采纳,获得10
4秒前
Lucas的应助被XPR采纳,获得10
5秒前
6秒前
orixero的应助被xiaoxia采纳,获得100
6秒前
7秒前
7秒前
yinxinyi发布了新的文献求助40
7秒前
7秒前
7秒前
8秒前
阿伯茨的完成签到,获得积分10
9秒前
shuyiWang发布了新的文献求助10
9秒前
Susuna完成签到 ,获得积分10
10秒前
木头发布了新的文献求助10
10秒前
11秒前
12秒前
时尚的紫蓝完成签到,获得积分10
13秒前
13秒前
yhr发布了新的文献求助10
14秒前
哭泣的凝芙完成签到,获得积分10
14秒前
15秒前
15秒前
geejee完成签到,获得积分10
15秒前
李健的小迷弟的应助被木头采纳,获得10
15秒前
16秒前
研友_ZeoKYL完成签到,获得积分10
16秒前
漫漫驳回了Jasper的应助
16秒前
suzy发布了新的文献求助10
17秒前
wangxiaomin发布了新的文献求助10
18秒前
19秒前
19秒前
卡卡完成签到 ,获得积分10
19秒前
XPR发布了新的文献求助10
19秒前
Owen的应助被CMC智能助手采纳,获得10
19秒前
20秒前
20秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Boundaries and Bodhisattvas 500
高分子基功能界面水蒸发材料与应用研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8181839
求助须知:如何正确求助?哪些是违规求助? 9571537
关于积分的说明 21818552
捐赠科研通 7778091
什么是DOI,文献DOI怎么找? 3433524
关于科研通互助平台的介绍 2557696
邀请新用户注册赠送积分活动 2479621