Papers › Graph Degree Linkage: Agglomerative Clustering on a Directed Graph

Graph Degree Linkage: Agglomerative Clustering on a Directed Graph

25 Aug 2012arXiv:1208.5092archive 2025-07-28

Wei Zhang, Xiaogang Wang, Deli Zhao, Xiaoou Tang

This paper proposes a simple but effective graph-based agglomerative algorithm, for clustering high-dimensional data. We explore the different roles of two fundamental concepts in graph theory, indegree and outdegree, in the context of clustering. The average indegree reflects the density near a sample, and the average outdegree characterizes the local geometry around a sample. Based on such insights, we define the affinity measure of clusters via the product of average indegree and average outdegree. The product-based affinity makes our algorithm robust to noise. The algorithm has three main advantages: good performance, easy implementation, and high computational efficiency. We test the algorithm on two fundamental computer vision problems: image clustering and object matching. Extensive experiments demonstrate that it outperforms the state-of-the-arts in both applications.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

waynezhanghk/gacluster pytorchBSD-2-Clause 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

ClusteringComputational EfficiencyImage Clustering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Clustering Coil-20 AGDL Accuracy 0.858 #3 of 6 Archive leaderboard report
Image Clustering Coil-20 AGDL NMI 0.937 #3 of 6 Archive leaderboard report
Image Clustering Coil-20 GDL-U NMI 0.746 #5 of 6 Archive leaderboard report
Image Clustering Coil-20 GDL Accuracy 0.858 #6 of 6 Archive leaderboard report
Image Clustering Extended Yale-B GDL-U NMI 0.91 #8 of 9 Archive leaderboard report
Image Clustering Extended Yale-B AGDL NMI 0.91 #9 of 9 Archive leaderboard report
Image Clustering Fashion-MNIST GDL Accuracy 0.627 #8 of 13 Archive leaderboard report
Image Clustering Fashion-MNIST GDL NMI 0.66 #8 of 13 Archive leaderboard report
Image Clustering MNIST-full GDL Accuracy 0.965 #14 of 16 Archive leaderboard report
Image Clustering MNIST-full GDL NMI 0.913 #14 of 16 Archive leaderboard report
Image Clustering MNIST-test GDL NMI 0.91 #7 of 11 Archive leaderboard report
Image Clustering MNIST-test AGDL NMI 0.844 #11 of 11 Archive leaderboard report
Image Clustering USPS AGDL NMI 0.824 #15 of 16 Archive leaderboard report
Image Clustering coil-100 GDL-U NMI 0.929 #6 of 10 Archive leaderboard report
Image Clustering coil-100 GDL Accuracy 0.731 #9 of 10 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