Topological Network Field Preservation for Heterogeneous Graph Embedding

计算机科学 中心性 拓扑(电路) 图嵌入 拓扑图论 嵌入 理论计算机科学 图形 人工智能 数学 电压图 折线图 组合数学
作者
Jiale Xu,Ouxia Du,Siyu Liu,Ya Li
出处
期刊:Lecture Notes in Computer Science 卷期号:: 466-480
标识
DOI:10.1007/978-981-99-7254-8_36
摘要

Heterogeneous graph (HG) embedding, aiming to represent the nodes in the graph as a low-dimensional vector form for further reasoning to better implement downstream tasks, has attracted considerable attention in recent years. Most existing HG embedding methods use the meta-paths to preserve the proximity or adapt graph neural networks (GNNs) to facilitate the message-passing process. However, these methods neglect to analyze the shape properties of nodes and the influence of each node from a topological perspective, thus cannot fully explore the information on higher-order connectivity of HG and be effectively support more complex tasks of network analysis. In this paper, a novel HG embedding model (TNFE) is proposed to capture the topological link structure and the higher-order interactive information between nodes simultaneously. Specifically, persistent homology is used to reconstruct the connection between nodes in HG. Then the neighborhoods of the nodes are aggregated based on a graph convolutional network. Moreover, modular topology centrality is defined to sample the topological network field structure of each node. Finally, multi-task learning task is built to preserve the topology connectivity and the topological network field proximity simultaneously. The extensive experiments on three real-world datasets show that our method outperforms the state-of-the-art approaches on node classification and clustering task.
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
曾经的真发布了新的文献求助10
1秒前
封典完成签到,获得积分10
1秒前
1秒前
Iceberg完成签到 ,获得积分10
2秒前
2秒前
搜集达人应助啦熊采纳,获得10
2秒前
今后应助羔羊采纳,获得10
2秒前
高雯发布了新的文献求助10
3秒前
3秒前
洁净斑马完成签到,获得积分10
3秒前
4秒前
Jingshuiliushen完成签到,获得积分10
5秒前
5秒前
5秒前
6秒前
谨慎的铭完成签到 ,获得积分10
6秒前
6秒前
6秒前
研友_n0DWDn发布了新的文献求助10
7秒前
丘比特应助蕙心采纳,获得20
7秒前
就叫柠檬吧完成签到,获得积分10
8秒前
Lazyazy_完成签到 ,获得积分10
8秒前
8秒前
8秒前
8秒前
研友_Z345g8发布了新的文献求助10
9秒前
合规部完成签到,获得积分10
9秒前
光亮元枫发布了新的文献求助10
9秒前
Faith发布了新的文献求助10
10秒前
11秒前
DengShili发布了新的文献求助10
11秒前
量子星尘发布了新的文献求助10
11秒前
浅笑成风完成签到,获得积分10
12秒前
科研通AI2S应助执着卿采纳,获得10
12秒前
13秒前
深情安青应助高雯采纳,获得10
13秒前
13秒前
小巧老鼠发布了新的文献求助10
14秒前
14秒前
axin发布了新的文献求助10
15秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 360
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 3970949
求助须知:如何正确求助?哪些是违规求助? 3515634
关于积分的说明 11179061
捐赠科研通 3250769
什么是DOI,文献DOI怎么找? 1795474
邀请新用户注册赠送积分活动 875831
科研通“疑难数据库(出版商)”最低求助积分说明 805188