Knowledge Commons of Institute of Automation,CAS
TREPH: A Plug-In Topological Layer for Graph Neural Networks | |
Ye, Xue1,2; Sun, Fang3; Xiang, Shiming1,2 | |
发表期刊 | Entropy |
ISSN | 1099-4300 |
2023 | |
卷号 | 25期号:2页码:331 |
文章类型 | 原创性研究 |
摘要 | Topological Data Analysis (TDA) is an approach to analyzing the shape of data using techniques from algebraic topology. The staple of TDA is Persistent Homology (PH). Recent years have seen a trend of combining PH and Graph Neural Networks (GNNs) in an end-to-end manner to capture topological features from graph data. Though effective, these methods are limited by the shortcomings of PH: incomplete topological information and irregular output format. Extended Persistent Homology (EPH), as a variant of PH, addresses these problems elegantly. In this paper, we propose a plug-in topological layer for GNNs, termed Topological Representation with Extended Persistent Homology (TREPH). Taking advantage of the uniformity of EPH, a novel aggregation mechanism is designed to collate topological features of different dimensions to the local positions determining their living processes. The proposed layer is provably differentiable and more expressive than PH-based representations, which in turn is strictly stronger than message-passing GNNs in expressive power. Experiments on real-world graph classification tasks demonstrate the competitiveness of TREPH compared with the state-of-the-art approaches. |
关键词 | graph neural network graph representation learning topological data analysis extended persistent homology |
DOI | https://doi.org/10.3390/e25020331 |
收录类别 | SCIE |
语种 | 英语 |
七大方向——子方向分类 | 人工智能基础理论 |
国重实验室规划方向分类 | 人工智能基础前沿理论 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/52033 |
专题 | 多模态人工智能系统全国重点实验室_先进时空数据分析与学习 |
通讯作者 | Sun, Fang |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 101408, China 3.School of Mathematical Sciences, Capital Normal University, Beijing 100048, China |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Ye, Xue,Sun, Fang,Xiang, Shiming. TREPH: A Plug-In Topological Layer for Graph Neural Networks[J]. Entropy,2023,25(2):331. |
APA | Ye, Xue,Sun, Fang,&Xiang, Shiming.(2023).TREPH: A Plug-In Topological Layer for Graph Neural Networks.Entropy,25(2),331. |
MLA | Ye, Xue,et al."TREPH: A Plug-In Topological Layer for Graph Neural Networks".Entropy 25.2(2023):331. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Ye et al_2023_TREPH.(1918KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论