Papers › Deep Unlearning via Randomized Conditionally Independent Hessians

Deep Unlearning via Randomized Conditionally Independent Hessians

15 Apr 2022CVPR 2022 1arXiv:2204.07655archive 2025-07-28

Ronak Mehta, Sourav Pal, Vikas Singh, Sathya N. Ravi

Recent legislation has led to interest in machine unlearning, i.e., removing specific training samples from a predictive model as if they never existed in the training dataset. Unlearning may also be required due to corrupted/adversarial data or simply a user's updated privacy requirement. For models which require no training (k-NN), simply deleting the closest original sample can be effective. But this idea is inapplicable to models which learn richer representations. Recent ideas leveraging optimization-based updates scale poorly with the model dimension d, due to inverting the Hessian of the loss function. We use a variant of a new conditional independence coefficient, L-CODEC, to identify a subset of the model parameters with the most semantic overlap on an individual sample level. Our approach completely avoids the need to invert a (possibly) huge matrix. By utilizing a Markov blanket selection, we premise that L-CODEC is also suitable for deep unlearning, as well as other applications in vision. Compared to alternatives, L-CODEC makes approximate unlearning possible in settings that would otherwise be infeasible, including vision models used for face recognition, person re-identification and NLP models that may require unlearning samples identified for exclusion. Code can be found at https://github.com/vsingh-group/LCODEC-deep-unlearning/

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 15 samples from 1 repository, 6 ran (6 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

vsingh-group/LCODEC-deep-unlearning officialmentioned in paperpytorchMITSyntology: 15 samples, 6 ran (0 instrument-failed) · 9 unverified 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

15 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

6ran
9unverified

Licence: 0 of the 15 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 vsingh-group/LCODEC-deep-unlearning. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

vsingh-group/LCODEC-deep-unlearning official repository 15 samples, 6 ran (0 instrument-failed) · 9 unverified
imagedata_kwargs in 7 papers scrub/deep-person-reid-master/projects/OSNet_AIN/default_config.py ran MIT (permissive) · 561c35d94c883194 · report fixture: signature cfg:Config/0/? · returned dict · level recorded 2026-09-25
inceptionv4 in 8 papers scrub/deep-person-reid-master/torchreid/models/inceptionv4.py ran MIT (permissive) · 2bcd3828691ac1d1 · report fixture: signature num_classes:int/0/int, pretrained:bool/0/bool, in_channels:int/0/int · returned InceptionV4 · level recorded 2026-09-25
mlfn in 6 papers scrub/deep-person-reid-master/torchreid/models/mlfn.py ran MIT (permissive) · 7f228eb824b42db8 · report fixture: signature num_classes:int/0/int, loss:str/0/str, groups:int/0/int, channels:list/1/int, embed_dim:int/0/int · returned MLFN · level recorded 2026-09-24
optimizer_kwargs in 13 papers scrub/deep-person-reid-master/projects/OSNet_AIN/default_config.py ran MIT (permissive) · d3e1b4b879ea0786 · report fixture: signature cfg:SimpleNamespace/0/? · returned dict · level recorded 2026-09-25
osnet_nas scrub/deep-person-reid-master/projects/OSNet_AIN/osnet_search.py ran MIT (permissive) · 3e4d009ac7f89ad8 · report fixture: signature x:Tensor/4/float · returned OSNet · level recorded 2026-09-25
videodata_kwargs in 7 papers scrub/deep-person-reid-master/projects/OSNet_AIN/default_config.py ran MIT (permissive) · 0951e0d511f67f90 · report fixture: signature cfg:MockConfig/0/? · returned dict · level recorded 2026-09-25
build_model in 469 papers scrub/deep-person-reid-master/projects/OSNet_AIN/osnet_child.py unverified MIT (permissive) · 80c5da68bda0fa8c · report
build_model in 469 papers scrub/deep-person-reid-master/projects/OSNet_AIN/osnet_search.py unverified MIT (permissive) · d81cb662094c9cbf · report
densenet121 in 43 papers scrub/deep-person-reid-master/torchreid/models/densenet.py unverified MIT (permissive) · 8e96abe9674da973 · report
densenet169 in 42 papers scrub/deep-person-reid-master/torchreid/models/densenet.py unverified MIT (permissive) · 54d10942ab6a6650 · report
densenet201 in 21 papers scrub/deep-person-reid-master/torchreid/models/densenet.py unverified MIT (permissive) · 372747120f68c12f · report
inceptionresnetv2 in 10 papers scrub/deep-person-reid-master/torchreid/models/inceptionresnetv2.py unverified MIT (permissive) · 968ff7bf292adbec · report
mobilenetv2_x1_0 in 7 papers scrub/deep-person-reid-master/torchreid/models/mobilenetv2.py unverified MIT (permissive) · 113c7b54049663fa · report
mobilenetv2_x1_4 in 7 papers scrub/deep-person-reid-master/torchreid/models/mobilenetv2.py unverified MIT (permissive) · 3faa700e370230b2 · report
osnet_ain_x1_0 scrub/deep-person-reid-master/projects/OSNet_AIN/osnet_child.py unverified MIT (permissive) · f3256be9107fa785 · report

Tasks

Face RecognitionMachine UnlearningPerson Re-Identification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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