ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2207.04216
23
8

Wasserstein Graph Distance Based on L1L_1L1​-Approximated Tree Edit Distance between Weisfeiler-Lehman Subtrees

9 July 2022
Zhongxi Fang
Jianming Huang
Xun Su
Hiroyuki Kasai
ArXivPDFHTML
Abstract

The Weisfeiler-Lehman (WL) test is a widely used algorithm in graph machine learning, including graph kernels, graph metrics, and graph neural networks. However, it focuses only on the consistency of the graph, which means that it is unable to detect slight structural differences. Consequently, this limits its ability to capture structural information, which also limits the performance of existing models that rely on the WL test. This limitation is particularly severe for traditional metrics defined by the WL test, which cannot precisely capture slight structural differences. In this paper, we propose a novel graph metric called the Wasserstein WL Subtree (WWLS) distance to address this problem. Our approach leverages the WL subtree as structural information for node neighborhoods and defines node metrics using the L1L_1L1​-approximated tree edit distance (L1L_1L1​-TED) between WL subtrees of nodes. Subsequently, we combine the Wasserstein distance and the L1L_1L1​-TED to define the WWLS distance, which can capture slight structural differences that may be difficult to detect using conventional metrics. We demonstrate that the proposed WWLS distance outperforms baselines in both metric validation and graph classification experiments.

View on arXiv
Comments on this paper