paper-with-me

Papers

Outlier-Robust Gromov-Wasserstein for Graph Data

2023-02-09 · NeurIPS 2023 11 · Lemin Kong, Jiajin Li, Jianheng Tang, Anthony Man-Cho So

Gromov-Wasserstein (GW) distance is a powerful tool for comparing and aligning probability distributions supported on different metric spaces. Recently, GW has become the main modeling technique for aligning heterogeneous data for a wide range of graph learning tasks. However, the GW distance is known to be highly sensitive to outliers, which can result in large inaccuracies if the outliers are given the same weight as other samples in the objective function. To mitigate this issue, we introduce a new and robust version of the GW distance called RGW. RGW features optimistically perturbed marginal constraints within a Kullback-Leibler divergence-based ambiguity set. To make the benefits of RGW more accessible in practice, we develop a computationally efficient and theoretically provable procedure using Bregman proximal alternating linearized minimization algorithm. Through extensive experimentation, we validate our theoretical results and demonstrate the effectiveness of RGW on real-world graph learning tasks, such as subgraph matching and partial shape correspondence.

📄 PDF Abstract BibTeX arXiv:2302.04610

Code (1)

lmkong020/outlier-robust-gw 공식 구현 pytorch

Tasks

Graph Learning

Similar Papers 제목 키워드 기반

Learning Graphons via Structured Gromov-Wasserstein Barycenters

2020-12-10 · Hongteng Xu, Dixin Luo, Lawrence Carin, Hongyuan Zha

We propose a novel and principled method to learn a nonparametric graph model called graphon, which is defined in an infinite-dimensional space and represents arbitrary-size graphs. Based on the weak regularity lemma fro…

LEMMA

Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matching

2019-05-18 · NeurIPS 2019 12 · Hongteng Xu, Dixin Luo, Lawrence Carin

We propose a scalable Gromov-Wasserstein learning (S-GWL) method and establish a novel and theoretically-supported paradigm for large-scale graph analysis. The proposed method is based on the fact that Gromov-Wasserstein…

ClusteringGraph Matchinggraph partitioning

Gromov-Wasserstein Learning for Graph Matching and Node Embedding

2019-01-17 · Hongteng Xu, Dixin Luo, Hongyuan Zha, Lawrence Carin

A novel Gromov-Wasserstein learning framework is proposed to jointly match (align) graphs and learn embedding vectors for the associated graph nodes. Using Gromov-Wasserstein discrepancy, we measure the dissimilarity bet…

Graph Matching

Partial Gromov-Wasserstein Learning for Partial Graph Matching

2020-12-02 · Weijie Liu, Chao Zhang, Jiahao Xie, Zebang Shen 외

Graph matching finds the correspondence of nodes across two graphs and is a basic task in graph-based machine learning. Numerous existing methods match every node in one graph to one node in the other graph whereas two g…

Graph Matching

Fast Gradient Computation for Gromov-Wasserstein Distance

2024-04-13 · Wei zhang, ZiHao Wang, Jie Fan, Hao Wu 외

The Gromov-Wasserstein distance is a notable extension of optimal transport. In contrast to the classic Wasserstein distance, it solves a quadratic assignment problem that minimizes the pair-wise distance distortion unde…