scholar.google.com › citations
Jan 1, 2023 · In this paper, we propose to use two widely used spectral signatures, the Heat Kernel Signature and the Wave Kernel Signature, to create node embeddings.
In this paper, we propose to use two widely used spectral signatures, the Heat Kernel Signature and the Wave Kernel Signature, to create node embeddings able to ...
In this paper, we propose to use two widely used spectral signatures, the Heat Kernel Signature and the Wave Kernel Signature, to create node embeddings able to ...
A Novel Graph Kernel Based on the Wasserstein Distance and Spectral Signatures. https://doi.org/10.1007/978-3-031-23028-8_13 ·.
Summary: Spectral signatures have been used with great success in computer vision to characterise the local and global topology of 3D meshes.
Oct 7, 2024 · A Novel Graph Kernel Based on the Wasserstein Distance and Spectral Signatures. ... A novel entropy-based graph signature from the average ...
A Novel Graph Kernel Based on the Wasserstein Distance and Spectral Signatures. 2022 | Book chapter. DOI: 10.1007/978-3-031-23028-8_13.
2024. A Novel Graph Kernel Based on the Wasserstein Distance and Spectral Signatures. Y Liu, L Rossi, A Torsello. Joint IAPR International Workshops on ...
Y. Liu, L. Rossi and A. Torsello, A novel graph kernel based on the Wasserstein distance and spectral signatures, S+SSPR, 2022.
In this paper we develop a novel graph kernel by matching the depth-based substructures in graphs. We commence by describing how to compute the Shannon ...