Graph Denoising is a computational framework within graph-based learning that specifically addresses the identification and removal of noise in graph-structured data by preserving the underlying topological and feature-level integrity of the original graph.
86
Publications
4.9K
Citations
289
Authors
142
Institutions
Publications per year
2017–2026
62
Parents
Publications
86
Autoregressive Moving Average Graph Filtering
Elvin Isufi, Andreas Loukas, Andrea Simonetto et al. · IEEE Transactions on Signal Processing · 2016 · 259 citations · Full text
Learning to Drop: Robust Graph Neural Network via Topological Denoising
Dongsheng Luo, Wei Cheng, Wenchao Yu et al. · 2021 · 238 citations
1–5 of 86
Authors
289
- YT
4
h-index
- AO
3
h-index
- JK
3
h-index
- WC
3
h-index
- WY
3
h-index
1–5 of 289
Institutions
142
École Polytechnique Fédérale de Lausanne
Lausanne, Switzerland
6 h-index
12 publications
1.3K citations
Tokyo University of Agriculture and Technology
Tokyo, Japan
4 h-index
8 publications
602 citations
Princeton University
Princeton, United States
3 h-index
11 publications
1.4K citations
Sichuan University
Chengdu, China
3 h-index
4 publications
121 citations
University of Hong Kong
Pok Fu Lam, Hong Kong
3 h-index
5 publications
149 citations
Carnegie Mellon University
Pittsburgh, United States
3 h-index
7 publications
657 citations
University of Southern California
Los Angeles, United States
3 h-index
6 publications
334 citations
Harbin Institute of Technology
Harbin, China
3 h-index
5 publications
119 citations
1–8 of 142
Venues
- arXiv (Cornell University)
Repository · 8 publications · 431 citations
8
h-index
- IEEE Transactions on Signal Processing
8 publications · 1.1K citations
8
h-index
- IEEE Transactions on Signal and Information Processing over Networks
3 publications · 183 citations
3
h-index
- IEEE Signal Processing Magazine
3 publications · 148 citations
3
h-index
- IEEE Transactions on Image Processing
2 publications · 141 citations
2
h-index
1–5