Papers › Exploring a Principled Framework for Deep Subspace Clustering

Exploring a Principled Framework for Deep Subspace Clustering

21 Mar 2025International Conference on Learning Representations 2025 1arXiv:2503.17288archive 2025-07-28

Xianghan Meng, Zhiyuan Huang, wei he, Xianbiao Qi, Rong Xiao, Chun-Guang Li

Subspace clustering is a classical unsupervised learning task, built on a basic assumption that high-dimensional data can be approximated by a union of subspaces (UoS). Nevertheless, the real-world data are often deviating from the UoS assumption. To address this challenge, state-of-the-art deep subspace clustering algorithms attempt to jointly learn UoS representations and self-expressive coefficients. However, the general framework of the existing algorithms suffers from a catastrophic feature collapse and lacks a theoretical guarantee to learn desired UoS representation. In this paper, we present a Principled fRamewOrk for Deep Subspace Clustering (PRO-DSC), which is designed to learn structured representations and self-expressive coefficients in a unified manner. Specifically, in PRO-DSC, we incorporate an effective regularization on the learned representations into the self-expressive model, prove that the regularized self-expressive model is able to prevent feature space collapse, and demonstrate that the learned optimal representations under certain condition lie on a union of orthogonal subspaces. Moreover, we provide a scalable and efficient approach to implement our PRO-DSC and conduct extensive experiments to verify our theoretical findings and demonstrate the superior performance of our proposed deep subspace clustering approach. The code is available at https://github.com/mengxianghan123/PRO-DSC.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2503.17288")

Code

Syntology Ran 4 of 4 code samples harvested from 2 repositories linked to this paper; 0 have no recorded run. Of those that ran: 4 ran with no contract checked.

By repository: official repository: 3 samples from 1 repository, 3 ran; found in paper text by Syntology: 1 sample from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

mengxianghan123/PRO-DSC officialmentioned in papermentioned on GitHubpytorch 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

4 samples harvested; 4 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

4ran

Licence: 4 of the 4 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

Conv2dSamePad mengxianghan123/PRO-DSC/model/DSCNet.py official repository ran · metamorphic tier: invariant fingerprinted licence not identified · pointer only · 026ba5d4f98ba452 · report
ConvAE mengxianghan123/PRO-DSC/model/DSCNet.py official repository ran · metamorphic tier: invariant fingerprinted licence not identified · pointer only · 7b78024d302d46c9 · report
PRO_DSC mengxianghan123/PRO-DSC/model/DSCNet.py official repository ran licence not identified · pointer only · 5255dd8c9c50f26d · report
CPPNet LeslieTrue/CPP/model/CPP_model.py found in paper text by Syntology ran no licence file found · pointer only · 3394a9a515d052e2 · report

Tasks

Clustering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Clustering CIFAR-10 PRO-DSC Accuracy 0.972 #3 of 40 Archive leaderboard report
Image Clustering CIFAR-10 PRO-DSC NMI 0.928 #3 of 40 Archive leaderboard report
Image Clustering CIFAR-100 PRO-DSC Accuracy 0.773 #3 of 30 Archive leaderboard report
Image Clustering CIFAR-100 PRO-DSC NMI 0.824 #3 of 30 Archive leaderboard report
Image Clustering ImageNet PRO-DSC Accuracy 65.0 #3 of 12 Archive leaderboard report
Image Clustering ImageNet PRO-DSC NMI 83.4 #3 of 12 Archive leaderboard report
Image Clustering Imagenet-dog-15 PRO-DSC Accuracy 0.840 #3 of 20 Archive leaderboard report
Image Clustering Imagenet-dog-15 PRO-DSC NMI 0.812 #3 of 20 Archive leaderboard report
Image Clustering Tiny-ImageNet PRO-DSC Accuracy 0.698 #1 of 14 Archive leaderboard report
Image Clustering Tiny-ImageNet PRO-DSC NMI 0.805 #1 of 14 Archive leaderboard report
Unsupervised Image Classification CIFAR-20 PRO-DSC Accuracy 71.6 #2 of 14 Archive leaderboard report
Unsupervised Image Classification CIFAR-20 PRO-DSC NMI 73.2 #2 of 14 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