SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.00761 · 2023

Deep Unlearning: Fast and Efficient Gradient-free Approach to Class Forgetting

arXiv · PDF · Open in the Atlas

Code that ran

10 of 17 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 10 failures of our instrument; 7 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2312.00761.json · badge: /api/ran/2312.00761.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
sangamesh-kodge/class_forgetting canonical (classifier label)
classifier basis: census
10 ran · 7 no recorded run
FunctionStatusWhere it lives
calc_importance Ran
ran; our contract draft was wrong, not the code
sangamesh-kodge/class_forgetting/analysis/runtime.py
pointer only (licence: NONE) · get_code("3af2910671822920")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sangamesh-kodge/class_forgetting when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compute_conv_output_size Ran
ran; our contract draft was wrong, not the code
sangamesh-kodge/class_forgetting/models/model_utils.py
pointer only (licence: NONE) · get_code("cec2ecd572648904")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sangamesh-kodge/class_forgetting when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

forward_cache_activations Ran
ran; our contract draft was wrong, not the code
sangamesh-kodge/class_forgetting/models/model_utils.py
pointer only (licence: NONE) · get_code("4644048ebc1d3c4e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sangamesh-kodge/class_forgetting when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_likelihood_ratio Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sangamesh-kodge/class_forgetting/analysis/interclass_confusion.py
pointer only (licence: NONE) · get_code("6dbc8e4c893ad5e3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sangamesh-kodge/class_forgetting when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_projection_matrix Ran
ran; our contract draft was wrong, not the code
sangamesh-kodge/class_forgetting/analysis/missing_class.py
pointer only (licence: NONE) · get_code("a416d8fda6cbebe2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sangamesh-kodge/class_forgetting when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_retain_forget_partition Ran
ran; our contract draft was wrong, not the code
sangamesh-kodge/class_forgetting/utils.py
pointer only (licence: NONE) · get_code("42fabf02e43fc9e3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sangamesh-kodge/class_forgetting when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

interpolate_embeddings Ran
ran; our contract draft was wrong, not the code
sangamesh-kodge/class_forgetting/models/vit.py
pointer only (licence: NONE) · get_code("e9cd32628e2a4c34")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sangamesh-kodge/class_forgetting when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

likelihood Ran
ran; our contract draft was wrong, not the code
sangamesh-kodge/class_forgetting/analysis/interclass_confusion.py
pointer only (licence: NONE) · get_code("223cc02f83103318")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sangamesh-kodge/class_forgetting when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

make_layers Ran
ran; our contract draft was wrong, not the code
sangamesh-kodge/class_forgetting/models/vgg.py
pointer only (licence: NONE) · get_code("ac62432dc5134b0d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sangamesh-kodge/class_forgetting when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

reshape_conv_input_activation Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sangamesh-kodge/class_forgetting/models/model_utils.py
pointer only (licence: NONE) · get_code("3e56c8da424bea73")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sangamesh-kodge/class_forgetting when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ResNet18 Not yet run
unverified (harvested, no recorded run)
sangamesh-kodge/class_forgetting/models/resnet.py
pointer only (licence: NONE) · get_code("9e4fdf529e5eb35a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sangamesh-kodge/class_forgetting when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

ResNet34 Not yet run
unverified (harvested, no recorded run)
sangamesh-kodge/class_forgetting/models/resnet.py
pointer only (licence: NONE) · get_code("b0429bb7e020f5fb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sangamesh-kodge/class_forgetting when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

ResNet50 Not yet run
unverified (harvested, no recorded run)
sangamesh-kodge/class_forgetting/models/resnet.py
pointer only (licence: NONE) · get_code("ec4196f891e7dfe7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sangamesh-kodge/class_forgetting when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_dataset Not yet run
unverified (harvested, no recorded run)
sangamesh-kodge/class_forgetting/utils.py
pointer only (licence: NONE) · get_code("8b15af7b68969b28")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sangamesh-kodge/class_forgetting when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
sangamesh-kodge/class_forgetting/analysis/shadow_train.py
pointer only (licence: NONE) · get_code("38d8b2e3aa6d1cc5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sangamesh-kodge/class_forgetting when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

vgg11 Not yet run
unverified (harvested, no recorded run)
sangamesh-kodge/class_forgetting/models/vgg.py
pointer only (licence: NONE) · get_code("89caa00e82add35d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sangamesh-kodge/class_forgetting when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

vgg11_bn Not yet run
unverified (harvested, no recorded run)
sangamesh-kodge/class_forgetting/models/vgg.py
pointer only (licence: NONE) · get_code("ea6c4b4731920685")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sangamesh-kodge/class_forgetting when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 3 later) and 14 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
make_layers 59 other papers
43 dated earlier, 3 the same month, 12 later, 1 same year, order not determinable
1411.4038 (2014-11)
Fully Convolutional Networks for Semantic Segmentation
1511.00561 (2015-11)
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
1511.05950 (2015-11)
Staleness-aware Async-SGD for Distributed Deep Learning
and 56 more not named here
compute_conv_output_size 1 other paper
1 later
aaai_33972 (2025 (year only))
SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustness
interpolate_embeddings 1 other paper
1 later
aaai_33972 (2025 (year only))
SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustness

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Machine unlearning is a prominent and challenging field, driven by regulatory demands for user data deletion and heightened privacy awareness. Existing approaches involve retraining model or multiple finetuning steps for each deletion request, often constrained by computational limits and restricted data access. In this work, we introduce a novel class unlearning algorithm designed to strategically eliminate specific classes from the learned model. Our algorithm first estimates the Retain and the Forget Spaces using Singular Value Decomposition on the layerwise activations for a small subset of samples from the retain and unlearn classes, respectively. We then compute the shared information between these spaces and remove it from the forget space to isolate class-discriminatory feature space. Finally, we obtain the unlearned model by updating the weights to suppress the class discriminatory features from the activation spaces. We demonstrate our algorithm's efficacy on ImageNet using a Vision Transformer with only $\sim 1.5\%$ drop in retain accuracy compared to the original model while maintaining under $1\%$ accuracy on the unlearned class samples. Furthermore, our algorithm exhibits competitive unlearning performance and resilience against Membership Inference Attacks (MIA). Compared to baselines, it achieves an average accuracy improvement of $1.38\%$ on the ImageNet dataset while requiring up to $10 \times$ fewer samples for unlearning. Additionally, under stronger MIA attacks on the CIFAR-100 dataset using a ResNet18 architecture, our approach outperforms the best baseline by $1.8\%$. Our code is available at https://github.com/sangamesh-kodge/class_forgetting.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2312.00761")
get_code_for_paper("2312.00761")
have("2312.00761")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2312.00761.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2312.00761.svg)](https://syntology.ai/paper/2312.00761)

Connect an agent — have() is free.