SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.26671 · 2026

Mitigating Forgetting in Continual Learning with Selective Gradient Projection

Kevin Zhu, David Martinez, Anika Singh, Aayush Dhaulakhandi, Varun Chopade, Likhith Malipati

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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; 2 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2603.26671.json · badge: /api/ran/2603.26671.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
anixa-s/sfao canonical (classifier label)
classifier basis: census
2 ran · 0 no recorded run
FunctionStatusWhere it lives
conv3x3 Ran
ran; our contract draft was wrong, not the code
anixa-s/sfao/continual_learning/models/reduced_resnet18.py
pointer only (licence: NONE) · get_code("d2cd695adf5c4268")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, anixa-s/sfao 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.

create_default_args Ran
ran; our contract draft was wrong, not the code
anixa-s/sfao/continual_learning/experiments/utils.py
pointer only (licence: NONE) · get_code("f1ef2ea33696e018")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, anixa-s/sfao 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.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 1 later) and 0 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
conv3x3 74 other papers
73 dated earlier, 1 later · 5 only as an assembly brick
1605.07146 (2016-05)
Wide Residual Networks
1707.01629 (2017-07)
Dual Path Networks
1802.05668 (2018-02)
Model compression via distillation and quantization
and 71 more not named here
create_default_args 1 other paper
1 dated earlier
2405.18069 (2024-05)
An Empirical Analysis of Forgetting in Pre-trained Models with Incremental Low-Rank Updates

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

As neural networks are increasingly deployed in dynamic environments, they face the challenge of catastrophic forgetting, the tendency to overwrite previously learned knowledge when adapting to new tasks, resulting in severe performance degradation on earlier tasks. We propose Selective Forgetting-Aware Optimization (SFAO), a dynamic method that regulates gradient directions via cosine similarity and per-layer gating, enabling controlled forgetting while balancing plasticity and stability. SFAO selectively projects, accepts, or discards updates using a tunable mechanism with efficient Monte Carlo approximation. Experiments on standard continual learning benchmarks show that SFAO achieves competitive accuracy with markedly lower memory cost, a 90% reduction, and improved forgetting on MNIST datasets, making it suitable for resource-constrained scenarios.

For agents

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

get_harvested_code_for_paper("2603.26671")
get_code_for_paper("2603.26671")
have("2603.26671")

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

curl https://syntology.ai/api/ran/2603.26671.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.26671.svg)](https://syntology.ai/paper/2603.26671)

Connect an agent — have() is free.