HGNN+: General Hypergraph Neural Networks

超图 计算机科学 理论计算机科学 图形 数据类型 人工智能 数学 离散数学 程序设计语言
作者
Yue Gao,Yifan Feng,Shuyi Ji,Rongrong Ji
出处
期刊:IEEE Transactions on Pattern Analysis and Machine Intelligence [Institute of Electrical and Electronics Engineers]
卷期号:45 (3): 3181-3199 被引量:119
标识
DOI:10.1109/tpami.2022.3182052
摘要

Graph Neural Networks have attracted increasing attention in recent years. However, existing GNN frameworks are deployed based upon simple graphs, which limits their applications in dealing with complex data correlation of multi-modal/multi-type data in practice. A few hypergraph-based methods have recently been proposed to address the problem of multi-modal/multi-type data correlation by directly concatenating the hypergraphs constructed from each single individual modality/type, which is difficult to learn an adaptive weight for each modality/type. In this paper, we extend the original conference version HGNN, and introduce a general high-order multi-modal/multi-type data correlation modeling framework called HGNN + to learn an optimal representation in a single hypergraph based framework. It is achieved by bridging multi-modal/multi-type data and hyperedge with hyperedge groups. Specifically, in our method, hyperedge groups are first constructed to represent latent high-order correlations in each specific modality/type with explicit or implicit graph structures. An adaptive hyperedge group fusion strategy is then used to effectively fuse the correlations from different modalities/types in a unified hypergraph. After that a new hypergraph convolution scheme performed in spatial domain is used to learn a general data representation for various tasks. We have evaluated this framework on several popular datasets and compared it with recent state-of-the-art methods. The comprehensive evaluations indicate that the proposed HGNN + framework can consistently outperform existing methods with a significant margin, especially when modeling implicit data correlations. We also release a toolbox called THU-DeepHypergraph for the proposed framework, which can be used for various of applications, such as data classification, retrieval and recommendation.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

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
饱满的大碗完成签到 ,获得积分10
刚刚
毛毛完成签到,获得积分10
刚刚
kk发布了新的文献求助10
3秒前
研友_ndDGVn完成签到 ,获得积分10
4秒前
jinni完成签到,获得积分10
5秒前
诚心的醉卉完成签到 ,获得积分10
7秒前
天涯明月完成签到,获得积分10
8秒前
积极的尔竹完成签到,获得积分10
10秒前
wujiwuhui完成签到 ,获得积分10
11秒前
kk完成签到,获得积分10
11秒前
八点必起完成签到,获得积分10
12秒前
糊涂的沛山完成签到 ,获得积分10
12秒前
12秒前
13秒前
AireenBeryl531应助米六采纳,获得10
13秒前
Xunr完成签到 ,获得积分10
14秒前
Zjn-完成签到 ,获得积分10
15秒前
15秒前
彭于彦祖应助芒果采纳,获得30
16秒前
端庄白猫完成签到,获得积分10
16秒前
活泼新儿发布了新的文献求助10
17秒前
蔡从安发布了新的文献求助10
18秒前
luckygirl发布了新的文献求助10
20秒前
苗条的嘉熙完成签到 ,获得积分10
21秒前
iWatchTheMoon应助荣冥幽采纳,获得10
22秒前
应夏山完成签到 ,获得积分10
22秒前
mumufan完成签到,获得积分10
23秒前
科研小白完成签到,获得积分10
24秒前
思源应助安静的小蚂蚁采纳,获得10
26秒前
蔡从安发布了新的文献求助10
28秒前
蒋海完成签到 ,获得积分10
30秒前
蝶舞天涯完成签到,获得积分10
30秒前
32秒前
斯文败类应助Leo采纳,获得10
33秒前
生产队的建设者完成签到 ,获得积分10
34秒前
34秒前
搞怪的怀蕊完成签到,获得积分10
34秒前
37秒前
yishufanhua发布了新的文献求助10
38秒前
Jasper应助maclogos采纳,获得10
42秒前
高分求助中
Evolution 10000
ISSN 2159-8274 EISSN 2159-8290 1000
Becoming: An Introduction to Jung's Concept of Individuation 600
Ore genesis in the Zambian Copperbelt with particular reference to the northern sector of the Chambishi basin 500
A new species of Coccus (Homoptera: Coccoidea) from Malawi 500
A new species of Velataspis (Hemiptera Coccoidea Diaspididae) from tea in Assam 500
PraxisRatgeber: Mantiden: Faszinierende Lauerjäger 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3162519
求助须知:如何正确求助?哪些是违规求助? 2813377
关于积分的说明 7900197
捐赠科研通 2472938
什么是DOI,文献DOI怎么找? 1316595
科研通“疑难数据库(出版商)”最低求助积分说明 631375
版权声明 602175