Heterogeneous Graph Neural Network

计算机科学 随机梯度下降算法 理论计算机科学 图嵌入 嵌入 图形 特征学习 异构网络 杠杆(统计) 人工神经网络 节点(物理) 人工智能 无线网络 电信 结构工程 工程类 无线
作者
Chuxu Zhang,Dongjin Song,Chao Huang,Ananthram Swami,Nitesh V. Chawla
标识
DOI:10.1145/3292500.3330961
摘要

Representation learning in heterogeneous graphs aims to pursue a meaningful vector representation for each node so as to facilitate downstream applications such as link prediction, personalized recommendation, node classification, etc. This task, however, is challenging not only because of the demand to incorporate heterogeneous structural (graph) information consisting of multiple types of nodes and edges, but also due to the need for considering heterogeneous attributes or contents (e.g., text or image) associated with each node. Despite a substantial amount of effort has been made to homogeneous (or heterogeneous) graph embedding, attributed graph embedding as well as graph neural networks, few of them can jointly consider heterogeneous structural (graph) information as well as heterogeneous contents information of each node effectively. In this paper, we propose HetGNN, a heterogeneous graph neural network model, to resolve this issue. Specifically, we first introduce a random walk with restart strategy to sample a fixed size of strongly correlated heterogeneous neighbors for each node and group them based upon node types. Next, we design a neural network architecture with two modules to aggregate feature information of those sampled neighboring nodes. The first module encodes "deep" feature interactions of heterogeneous contents and generates content embedding for each node. The second module aggregates content (attribute) embeddings of different neighboring groups (types) and further combines them by considering the impacts of different groups to obtain the ultimate node embedding. Finally, we leverage a graph context loss and a mini-batch gradient descent procedure to train the model in an end-to-end manner. Extensive experiments on several datasets demonstrate that HetGNN can outperform state-of-the-art baselines in various graph mining tasks, i.e., link prediction, recommendation, node classification & clustering and inductive node classification & clustering.
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
PDF的下载单位、IP信息已删除 (2025-6-4)

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
1秒前
qingchenwuhou完成签到 ,获得积分10
1秒前
XXX完成签到,获得积分10
2秒前
锡嘻完成签到 ,获得积分10
2秒前
3秒前
彗星入梦完成签到 ,获得积分10
3秒前
恋恋青葡萄完成签到,获得积分10
3秒前
隐形万言完成签到,获得积分10
5秒前
Time完成签到,获得积分10
5秒前
土木研学僧完成签到,获得积分10
6秒前
yjy完成签到 ,获得积分10
6秒前
A溶大美噶完成签到,获得积分10
6秒前
yar应助萨尔莫斯采纳,获得10
7秒前
Will发布了新的文献求助10
7秒前
美好的鹏笑完成签到,获得积分10
9秒前
啦啦啦啦啦完成签到,获得积分10
9秒前
LYegoist完成签到,获得积分10
11秒前
可爱的小丸子完成签到,获得积分10
11秒前
一川烟叶完成签到,获得积分10
13秒前
13秒前
16秒前
iFan完成签到 ,获得积分10
16秒前
萨尔莫斯完成签到,获得积分10
16秒前
合适靖儿完成签到 ,获得积分10
18秒前
林林林完成签到,获得积分10
19秒前
斯琪欣完成签到,获得积分10
20秒前
21秒前
MQQ完成签到 ,获得积分10
21秒前
meng发布了新的文献求助10
21秒前
22秒前
zxc167完成签到,获得积分10
22秒前
研友_nVWP2Z完成签到 ,获得积分10
24秒前
俭朴的半雪完成签到 ,获得积分10
25秒前
大橙子发布了新的文献求助10
26秒前
meng完成签到,获得积分10
27秒前
28秒前
28秒前
科研韭菜完成签到 ,获得积分10
28秒前
SYLJ完成签到,获得积分10
30秒前
灵巧的十八完成签到 ,获得积分10
31秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Handbook of Industrial Diamonds.Vol2 1100
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
热门求助领域 (近24小时)
化学 材料科学 医学 生物 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 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038201
求助须知:如何正确求助?哪些是违规求助? 3575940
关于积分的说明 11373987
捐赠科研通 3305747
什么是DOI,文献DOI怎么找? 1819274
邀请新用户注册赠送积分活动 892662
科研通“疑难数据库(出版商)”最低求助积分说明 815022