</> Code with Papers by Syntology

Papers › Git: Clustering Based on Graph of Intensity Topology

Git: Clustering Based on Graph of Intensity Topology

4 Oct 2021arXiv:2110.01274archive 2025-07-28

Zhangyang Gao, Haitao Lin, Cheng Tan, Lirong Wu, Stan. Z Li

\textbf{A}ccuracy, \textbf{R}obustness to noises and scales, \textbf{I}nterpretability, \textbf{S}peed, and \textbf{E}asy to use (ARISE) are crucial requirements of a good clustering algorithm. However, achieving these goals simultaneously is challenging, and most advanced approaches only focus on parts of them. Towards an overall consideration of these aspects, we propose a novel clustering algorithm, namely GIT (Clustering Based on \textbf{G}raph of \textbf{I}ntensity \textbf{T}opology). GIT considers both local and global data structures: firstly forming local clusters based on intensity peaks of samples, and then estimating the global topological graph (topo-graph) between these local clusters. We use the Wasserstein Distance between the predicted and prior class proportions to automatically cut noisy edges in the topo-graph and merge connected local clusters as final clusters. Then, we compare GIT with seven competing algorithms on five synthetic datasets and nine real-world datasets. With fast local cluster detection, robust topo-graph construction and accurate edge-cutting, GIT shows attractive ARISE performance and significantly exceeds other non-convex clustering methods. For example, GIT outperforms its counterparts about 10% (F1-score) on MNIST and FashionMNIST. Code is available at \color{red}{https://github.com/gaozhangyang/GIT}.

PaperPDFCode

Code

gaozhangyang/git officialmentioned in papermentioned on GitHub report
gaozhangyang/DGC mentioned on GitHubpytorch report
2024-MindSpore-1/Code2 mindspore report
yangyucheng000/University mindspore report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ClusteringClustering Algorithms Evaluation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Clustering Algorithms Evaluation Fashion-MNIST AE+GIT ARI 49% #1 of 6 Archive leaderboard report
Clustering Algorithms Evaluation Fashion-MNIST AE+GIT F1-score 65% #1 of 6 Archive leaderboard report
Clustering Algorithms Evaluation Fashion-MNIST AE+GIT NMI 61% #1 of 6 Archive leaderboard report
Clustering Algorithms Evaluation Fashion-MNIST k-Means++ ARI 35% #2 of 6 Archive leaderboard report
Clustering Algorithms Evaluation Fashion-MNIST k-Means++ F1-score 39% #2 of 6 Archive leaderboard report
Clustering Algorithms Evaluation Fashion-MNIST k-Means++ NMI 51% #2 of 6 Archive leaderboard report
Clustering Algorithms Evaluation Fashion-MNIST Spectral Clustering ARI 34% #3 of 6 Archive leaderboard report
Clustering Algorithms Evaluation Fashion-MNIST Spectral Clustering F1-score 43% #3 of 6 Archive leaderboard report
Clustering Algorithms Evaluation Fashion-MNIST Spectral Clustering NMI 49% #3 of 6 Archive leaderboard report
Clustering Algorithms Evaluation Fashion-MNIST GIT ARI 32% #4 of 6 Archive leaderboard report
Clustering Algorithms Evaluation Fashion-MNIST GIT F1-score 56% #4 of 6 Archive leaderboard report
Clustering Algorithms Evaluation Fashion-MNIST GIT NMI 51% #4 of 6 Archive leaderboard report
Clustering Algorithms Evaluation Fashion-MNIST SpectACI ARI 29% #5 of 6 Archive leaderboard report
Clustering Algorithms Evaluation Fashion-MNIST SpectACI F1-score 47% #5 of 6 Archive leaderboard report
Clustering Algorithms Evaluation Fashion-MNIST SpectACI NMI 45% #5 of 6 Archive leaderboard report
Clustering Algorithms Evaluation Fashion-MNIST QuickShiftPP ARI 16% #6 of 6 Archive leaderboard report
Clustering Algorithms Evaluation Fashion-MNIST QuickShiftPP F1-score 42% #6 of 6 Archive leaderboard report
Clustering Algorithms Evaluation Fashion-MNIST QuickShiftPP NMI 41% #6 of 6 Archive leaderboard report
Clustering Algorithms Evaluation MNIST AE+GIT ARI 77% #1 of 6 Archive leaderboard report
Clustering Algorithms Evaluation MNIST AE+GIT F1-score 88% #1 of 6 Archive leaderboard report
Clustering Algorithms Evaluation MNIST AE+GIT NMI 81% #1 of 6 Archive leaderboard report
Clustering Algorithms Evaluation MNIST GIT ARI 42% #2 of 6 Archive leaderboard report
Clustering Algorithms Evaluation MNIST GIT F1-score 59% #2 of 6 Archive leaderboard report
Clustering Algorithms Evaluation MNIST GIT NMI 53% #2 of 6 Archive leaderboard report
Clustering Algorithms Evaluation MNIST k-Means++ ARI 36% #3 of 6 Archive leaderboard report
Clustering Algorithms Evaluation MNIST k-Means++ F1-score 50% #3 of 6 Archive leaderboard report
Clustering Algorithms Evaluation MNIST k-Means++ NMI 45% #3 of 6 Archive leaderboard report
Clustering Algorithms Evaluation MNIST Spectral Clustering ARI 33% #4 of 6 Archive leaderboard report
Clustering Algorithms Evaluation MNIST Spectral Clustering F1-score 41% #4 of 6 Archive leaderboard report
Clustering Algorithms Evaluation MNIST Spectral Clustering NMI 44% #4 of 6 Archive leaderboard report
Clustering Algorithms Evaluation MNIST SpectACI ARI 17% #5 of 6 Archive leaderboard report
Clustering Algorithms Evaluation MNIST SpectACI F1-score 40% #5 of 6 Archive leaderboard report
Clustering Algorithms Evaluation MNIST SpectACI NMI 33% #5 of 6 Archive leaderboard report
Clustering Algorithms Evaluation MNIST QuickShiftPP ARI 13% #6 of 6 Archive leaderboard report
Clustering Algorithms Evaluation MNIST QuickShiftPP F1-score 45% #6 of 6 Archive leaderboard report
Clustering Algorithms Evaluation MNIST QuickShiftPP NMI 45% #6 of 6 Archive leaderboard report
Clustering Algorithms Evaluation Olivetti face GIT ARI 45% #1 of 5 Archive leaderboard report
Clustering Algorithms Evaluation Olivetti face GIT F1-score 62% #1 of 5 Archive leaderboard report
Clustering Algorithms Evaluation Olivetti face GIT NMI 78% #1 of 5 Archive leaderboard report
Clustering Algorithms Evaluation Olivetti face QuickShiftPP ARI 38% #2 of 5 Archive leaderboard report
Clustering Algorithms Evaluation Olivetti face QuickShiftPP F1-score 60% #2 of 5 Archive leaderboard report
Clustering Algorithms Evaluation Olivetti face QuickShiftPP NMI 79% #2 of 5 Archive leaderboard report
Clustering Algorithms Evaluation Olivetti face k-Means++ ARI 38% #3 of 5 Archive leaderboard report
Clustering Algorithms Evaluation Olivetti face k-Means++ F1-score 52% #3 of 5 Archive leaderboard report
Clustering Algorithms Evaluation Olivetti face k-Means++ NMI 74% #3 of 5 Archive leaderboard report
Clustering Algorithms Evaluation Olivetti face Spectral Clustering ARI 19% #4 of 5 Archive leaderboard report
Clustering Algorithms Evaluation Olivetti face Spectral Clustering F1-score 37% #4 of 5 Archive leaderboard report
Clustering Algorithms Evaluation Olivetti face Spectral Clustering NMI 66% #4 of 5 Archive leaderboard report
Clustering Algorithms Evaluation Olivetti face SpectACI ARI 21% #5 of 5 Archive leaderboard report
Clustering Algorithms Evaluation Olivetti face SpectACI F1-score 34% #5 of 5 Archive leaderboard report
Clustering Algorithms Evaluation Olivetti face SpectACI NMI 61% #5 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections