Papers › Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement

Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement

29 Sep 2024arXiv:2409.19732archive 2025-07-28

Zhehao Huang, Xinwen Cheng, JingHao Zheng, Haoran Wang, Zhengbao He, Tao Li, Xiaolin Huang

Machine unlearning (MU) has emerged to enhance the privacy and trustworthiness of deep neural networks. Approximate MU is a practical method for large-scale models. Our investigation into approximate MU starts with identifying the steepest descent direction, minimizing the output Kullback-Leibler divergence to exact MU inside a parameters' neighborhood. This probed direction decomposes into three components: weighted forgetting gradient ascent, fine-tuning retaining gradient descent, and a weight saliency matrix. Such decomposition derived from Euclidean metric encompasses most existing gradient-based MU methods. Nevertheless, adhering to Euclidean space may result in sub-optimal iterative trajectories due to the overlooked geometric structure of the output probability space. We suggest embedding the unlearning update into a manifold rendered by the remaining geometry, incorporating second-order Hessian from the remaining data. It helps prevent effective unlearning from interfering with the retained performance. However, computing the second-order Hessian for large-scale models is intractable. To efficiently leverage the benefits of Hessian modulation, we propose a fast-slow parameter update strategy to implicitly approximate the up-to-date salient unlearning direction. Free from specific modal constraints, our approach is adaptable across computer vision unlearning tasks, including classification and generation. Extensive experiments validate our efficacy and efficiency. Notably, our method successfully performs class-forgetting on ImageNet using DiT and forgets a class on CIFAR-10 using DDPM in just 50 steps, compared to thousands of steps required by previous methods.

PaperPDFCodeCode Syntology ranMethod as code

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.

Syntology holds a reference implementation of Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement, generated from the paper text (not the authors' code), at level 2 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement') (how to connect); the free check have('2409.19732') needs no token.

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

Code

Syntology 26 code samples: 25 from 4 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 26: 17 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 6 samples from 1 repository, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed); found in paper text by Syntology: 19 samples from 3 repositories, 12 ran (5 with no instrument failure; 7 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 17 samples that ran have no recorded date.

k1nght/unified-unlearning-w-remain-geometry mentioned on GitHubpytorchSyntology: not harvested report
lioutang/unlearn-apollo-attack mentioned on GitHubpytorchMITSyntology: 6 samples, 5 ran (0 instrument-failed) · 1 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

26 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 7 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
3ran · our draft was wrong
4ran; the contract check could not run
8ran
9unverified

Licence: 3 of the 26 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 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample is listed last, in a group without a repository. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

lioutang/unlearn-apollo-attack community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
DistillLoss unlearn/bad_teacher.py ran MIT (permissive) · 3d829155d40ef755 · report fixture: signature outputs:Tensor/2/float, unlearn_labels:Tensor/1/float, full_teacher_logits:Tensor/2/float, unlearning_teacher_logits:Tensor/2/float, KL_temperature:float/0/float · returned Tensor · level recorded 2026-09-24
batched_models_ attacks/Apollo.py ran MIT (permissive) · 2c9afdad86950b96 · report fixture: signature models_list:list/1/callable · returned tuple · level recorded 2026-09-24
get_idx_loaders attack.py ran MIT (permissive) · 323d03d62e0533c7 · report fixture: signature split:dict/0/?, dataset:MinimalDataset/0/? · returned tuple · level recorded 2026-09-24
proj in 38 papers attacks/Apollo.py ran MIT (permissive) · 0d878f551236258c · report fixture: signature A:Tensor/2/float, B:Tensor/2/float, r:float/0/float, type:str/0/str · returned Tensor · level recorded 2026-09-24
setminus in 7 papers attack.py ran fingerprinted MIT (permissive) · f1ab27640c7765be · report fixture: signature A:ndarray/1/int, B:ndarray/1/int · returned ndarray · level recorded 2026-09-24
batched_loss_ attacks/Apollo.py unverified MIT (permissive) · 900e51f145a62a95 · report
OPTML-Group/Unlearn-Saliency found in paper text by Syntology 6 samples, 3 ran (3 instrument-failed) · 3 unverified
GA in 5 papers Classification/unlearn/GA_prune.py ran; the contract check could not run (RAISES) MIT (permissive) · 1b3f6a248551b312 · report fixture: returned float · level recorded 2026-09-22
get_x_y_from_data_dict Classification/unlearn/GA_prune.py ran · our draft was wrong MIT (permissive) · c7ae957080f6f740 · report fixture: signature data:dict/0/?, device:str/0/str · returned tuple · level recorded 2026-09-22
validate in 313 papers Classification/unlearn/GA_prune.py ran; the contract check could not run (RAISES) MIT (permissive) · def64f7467ecb30c · report fixture: returned float · level recorded 2026-09-22
GA_prune Classification/unlearn/GA_prune.py unverified MIT (permissive) · 28baf7f344ef0caa · report
save_checkpoint in 36 papers Classification/unlearn/GA_prune.py unverified MIT (permissive) · 632b4796f64ea2f5 · report
warmup_lr Classification/unlearn/GA_prune.py unverified MIT (permissive) · f1e544cbc00ca5fd · report
meghdadk/SCRUB found in paper text by Syntology 2 samples, 1 ran (0 instrument-failed) · 1 unverified
l2_penalty main_merged.py ran · honoured contract licence not identified · pointer only · 0885bc1a1a34f5eb · report fixture: signature model:callable/0/?, model_init:callable/0/?, weight_decay:float/0/float · returned Tensor · level recorded 2026-09-22
run_epoch in 18 papers main_merged.py unverified licence not identified · pointer only · 9510c6df76e617f1 · report
clear-nus/selective-amnesia found in paper text by Syntology 11 samples, 8 ran (4 instrument-failed) · 3 unverified
GetImageFolderLoader ddpm/classifier_evaluation.py ran MIT (permissive) · 29136f2953d790e8 · report fixture: signature path:str/0/str, data_type:str/0/str, img_size:int/0/int, batch_size:int/0/int · returned DataLoader · level recorded 2026-09-24
get_dataset_image_folder ddpm/train_classifier.py ran · our draft was wrong MIT (permissive) · 66de5a5babf9c9d8 · report fixture: signature args:Args/0/? · returned tuple · level recorded 2026-09-24
get_timestep_embedding in 138 papers
census: 11 implementations from 15 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind int, dtype int64
ddpm/models/diffusion.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · cb49209c125de1b4 · report fixture: signature timesteps:Tensor/1/int, embedding_dim:int/0/int · returned Tensor · level recorded, date not recorded
loss_function in 62 papers
census: 7 implementations from 6 papers, 7 distinct outputs across 2 buckets, one shared input per bucket
vae/model.py ran MIT (permissive) · 372b74ad7eb6ab5d · report fixture: signature recon_x:Tensor/2/float, x:Tensor/2/float, mu:Tensor/2/float, log_var:Tensor/2/float · returned Tensor · level recorded 2026-09-24
noise_estimation_loss in 19 papers ddpm/functions/losses.py ran MIT (permissive) · 36a45cceb1209d2f · report fixture: signature model:callable/0/?, x0:Tensor/4/float, t:Tensor/1/int, e:Tensor/4/float, b:Tensor/1/float, keepdim:bool/0/bool · returned Tensor · level recorded 2026-09-24
nonlinearity in 140 papers
census: 4 implementations from 11 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
ddpm/models/diffusion.py ran · our draft was wrong fingerprinted MIT (permissive) · 3137073275f8c21a · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
prob_mask_like in 16 papers ddpm/models/diffusion.py ran; the contract check could not run (RAISES) MIT (permissive) · 3c6433dd421724e0 · report fixture: signature shape:tuple/1/int, prob:float/0/float, device:device/0/? · returned Tensor · level recorded 2026-09-22
read_images_folder ddpm/evaluator.py ran · honoured contract MIT (permissive) · 0bae0d076b1ae674 · report fixture: signature folder_path:str/0/str · returned ndarray · level recorded 2026-09-24
all_but_one_class_dataset ddpm/save_base_dataset.py unverified MIT (permissive) · d278a27b738c2136 · report
get_dataset in 285 papers ddpm/train_classifier.py unverified MIT (permissive) · 403a67ad5e70ec17 · report
noise_estimation_loss_conditional ddpm/functions/losses.py unverified MIT (permissive) · 657432e743b32d39 · report
Repository not located 1 sample, 0 ran · 1 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
repository not located unverified licence of this copy not recorded · f0c9a29156911331 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another. Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

3 assemblies on this paper: 2 harvested, 1 generated, listed in 2 groups (siblings lifted in one batch form one group).

generated Assembly for Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement (graph method: Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).

label matches by construction: the code was generated for this method (not judged by a model)

  1. compute_weight_saliency_mask entry · level 2 · ran · a4f6ac7fba6e91e34c3c22d535df3251d6de2e68508298b1e376a7a7541e9db1

2 sibling assemblies for Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement (graph method: Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement). 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. run_epoch entry · level 0 · unverified · 9510c6df76e617f1
  2. l2_penalty loss · level 1 · ran · honoured contract · 0885bc1a1a34f5eb

harvested Assembly for Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement (graph method: Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement). 8 bricks; individually on a fixture: 4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. GA_prune entry · level 0 · unverified · 28baf7f344ef0caa
  2. GA update_rule · level 1 · ran; the contract check could not run (RAISES) · 1b3f6a248551b312
  3. save_checkpoint helper · level 0 · unverified · 632b4796f64ea2f5
  4. validate helper · level 1 · ran; the contract check could not run (RAISES) · def64f7467ecb30c
  5. AverageMeter metric · level 1 · ran · 9355efdc819d943e
  6. accuracy helper · level 0 · unverified · f0c9a29156911331
  7. warmup_lr helper · level 0 · unverified · f1e544cbc00ca5fd
  8. get_x_y_from_data_dict helper · level 1 · ran · our draft was wrong · c7ae957080f6f740

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2409.19732") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Machine Unlearning

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