-
- KAWANO Keisuke
- Toyota Central R&D Labs., Inc.
-
- KOIDE Satoshi
- Toyota Central R&D Labs., Inc.
-
- SHIOKAWA Hiroaki
- Center for Computational Sciences, University of Tsukuba
-
- AMAGASA Toshiyuki
- Center for Computational Sciences, University of Tsukuba
抄録
<p>Graph dissimilarities provide a powerful and ubiquitous approach for applying machine learning algorithms to edge-attributed graphs. However, conventional optimal transport-based dissimilarities cannot handle edge-attributes. In this paper, we propose an optimal transport-based dissimilarity between graphs with edge-attributes. The proposed method, multi-dimensional fused Gromov-Wasserstein discrepancy (MFGW), naturally incorporates the mismatch of edge-attributes into the optimal transport theory. Unlike conventional optimal transport-based dissimilarities, MFGW can directly handle edge-attributes in addition to structural information of graphs. Furthermore, we propose an iterative algorithm, which can be computed on GPUs, to solve non-convex quadratic programming problems involved in MFGW. Experimentally, we demonstrate that MFGW outperforms the conventional optimal transport-based dissimilarity in several machine learning applications including supervised classification, subgraph matching, and graph barycenter calculation.</p>
収録刊行物
-
- IEICE Transactions on Information and Systems
-
IEICE Transactions on Information and Systems E107.D (5), 683-693, 2024-05-01
一般社団法人 電子情報通信学会
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1390018518956417152
-
- ISSN
- 17451361
- 09168532
-
- 本文言語コード
- en
-
- データソース種別
-
- JaLC
- Crossref
-
- 抄録ライセンスフラグ
- 使用不可