A Transitive Aligned Weisfeiler-Lehman Subtree Kernel

被引：0

作者：

Bai, Lu ^{[1
]}

Rossi, Luca ^{[2
]}

Cui, Lixin ^{[1
]}

Hancock, Edwin R. ^{[3
]}

机构：

[1] Cent Univ Finance & Econ, Sch Informat, 39 South Coll Rd, Beijing, Peoples R China

[2] Aston Univ, Sch Engn & Appl Sci, Birmingham B4 7ET, W Midlands, England

[3] Univ York, Dept Comp Sci, York YO10 5DD, N Yorkshire, England

来源：

2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR) | 2016年

基金：

中国国家自然科学基金;

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we develop a new transitive aligned Weisfeiler-Lehman subtree kernel. This kernel not only overcomes the shortcoming of ignoring correspondence information between isomorphic substructures that arises in existing R-convolution kernels, but also guarantees the transitivity between the correspondence information that is not available for existing matching kernels. Our kernel outperforms state-of-the-art graph kernels in terms of classification accuracy on standard graph datasets.

引用

页码：396 / 401

页数：6

共 50 条

[31] Gaussian process regression with Sliced Wasserstein Weisfeiler-Lehman graph kernels
Perez, Raphael Carpintero
Da Veiga, Sebastien
Garnier, Josselin
Staber, Brian
INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 238, 2024, 238
[32] Predicting Drug-Target Interactions Using Weisfeiler-Lehman Neural Network
Manoochehri, Hafez Eslami
Kadiyala, Susmitha Sri
Nourani, Mehrdad
2019 IEEE EMBS INTERNATIONAL CONFERENCE ON BIOMEDICAL & HEALTH INFORMATICS (BHI), 2019,
[33] Link Prediction Evaluation Using Palette Weisfeiler-Lehman Graph Labelling Algorithm
Devi, Salam Jayachitra
Singh, Buddha
Raza, Haider
INTERNATIONAL JOURNAL OF KNOWLEDGE AND SYSTEMS SCIENCE, 2019, 10 (01) : 1 - 20
[34] Extending the Design Space of Graph Neural Networks by Rethinking Folklore Weisfeiler-Lehman
Feng, Jiarui
Kong, Lecheng
Liu, Hao
Tao, Dacheng
Li, Fuhai
Zhang, Muhan
Chen, Yixin
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
[35] THE PWLR GRAPH REPRESENTATION: A PERSISTENT WEISFEILER-LEHMAN SCHEME WITH RANDOM WALKS FOR GRAPH CLASSIFICATION
Park, Sun Woo
Choi, Yun Young
Joe, Dosang
Woo, Youngho
Choi, U. Jin
TOPOLOGICAL, ALGEBRAIC AND GEOMETRIC LEARNING WORKSHOPS 2022, VOL 196, 2022, 196
[36] Glocalized Weisfeiler-Lehman Graph Kernels: Global-Local Feature Maps of Graphs
Morris, Christopher
Kersting, Kristian
Mutzel, Petra
2017 17TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM), 2017, : 327 - 336
[37] 基于Weisfeiler-Lehman图核算法的装配体模型比较方法
左咪
邓兰
薛婷
闫起源
机械设计与制造, 2020, (11) : 228 - 231
[38] LWP-WL: Link weight prediction based on CNNs and the Weisfeiler-Lehman algorithm
Zulaika, Unai
Sanchez-Corcuera, Ruben
Almeida, Aitor
Lopez-de-Ipina, Diego
APPLIED SOFT COMPUTING, 2022, 120
[39] An Aligned Subtree Kernel for Weighted Graphs
Bai, Lu
Rossi, Luca
Zhang, Zhihong
Hancock, Edwin R.
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 37, 2015, 37 : 30 - 39
[40] Towards Efficient and Expressive GNNs for Graph Classification via Subgraph-aware Weisfeiler-Lehman
Wang, Zhaohui
Cao, Qi
Shen, Huawei
Xu, Bingbing
Zhang, Muhan
Cheng, Xueqi
LEARNING ON GRAPHS CONFERENCE, VOL 198, 2022, 198

← 1 2 3 4 5 →