Papers › Revisiting Neural Networks for Continual Learning: An Architectural Perspective

Revisiting Neural Networks for Continual Learning: An Architectural Perspective

23 Apr 2024arXiv:2404.14829archive 2025-07-28

Aojun Lu, Tao Feng, Hangjie Yuan, Xiaotian Song, Yanan sun

Efforts to overcome catastrophic forgetting have primarily centered around developing more effective Continual Learning (CL) methods. In contrast, less attention was devoted to analyzing the role of network architecture design (e.g., network depth, width, and components) in contributing to CL. This paper seeks to bridge this gap between network architecture design and CL, and to present a holistic study on the impact of network architectures on CL. This work considers architecture design at the network scaling level, i.e., width and depth, and also at the network components, i.e., skip connections, global pooling layers, and down-sampling. In both cases, we first derive insights through systematically exploring how architectural designs affect CL. Then, grounded in these insights, we craft a specialized search space for CL and further propose a simple yet effective ArchCraft method to steer a CL-friendly architecture, namely, this method recrafts AlexNet/ResNet into AlexAC/ResAC. Experimental validation across various CL settings and scenarios demonstrates that improved architectures are parameter-efficient, achieving state-of-the-art performance of CL while being 86%, 61%, and 97% more compact in terms of parameters than the naive CL architecture in Task IL and Class IL. Code is available at https://github.com/byyx666/ArchCraft.

PaperPDFCodeCode 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="2404.14829")

Code

Syntology Ran 13 of 19 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 4 ran · our draft was wrong; 9 ran with no contract checked.

By repository: official repository: 19 samples from 1 repository, 13 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

byyx666/archcraft officialmentioned in paperpytorch 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

19 samples harvested; 13 ran; 0 honoured the contract we drafted; 6 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 · our draft was wrong
9ran
6unverified

Licence: 19 of the 19 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 byyx666/ArchCraft. “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.

BasicBlock byyx666/ArchCraft/task_il/networks/arch_craft.py official repository ran fingerprinted no licence file found · pointer only · 9447851a9454a03a · report
BasicBlockRes byyx666/ArchCraft/task_il/networks/arch_craft.py official repository ran no licence file found · pointer only · 7ab8bd831d4c5b9e · report
DownsampleB byyx666/ArchCraft/task_il/networks/arch_craft.py official repository ran fingerprinted no licence file found · pointer only · 8a7d5641e4d53e3b · report
Net byyx666/ArchCraft/task_il/networks/arch_craft.py official repository ran no licence file found · pointer only · 54ceb19348d05def · report
conv1x1 byyx666/archcraft/class_il/convs/memo_resnet.py official repository ran · our draft was wrong no licence file found · pointer only · d9def42110729a85 · report
conv3x3 byyx666/archcraft/class_il/convs/memo_resnet.py official repository ran · our draft was wrong no licence file found · pointer only · 160bb14bd76201b4 · report
conv3x3 byyx666/archcraft/class_il/convs/modified_represnet.py official repository ran · our draft was wrong no licence file found · pointer only · 1907f2ae25449f39 · report
conv_block byyx666/archcraft/class_il/convs/conv_imagenet.py official repository ran · our draft was wrong no licence file found · pointer only · 9d556d61294bb0a8 · report
first_block byyx666/archcraft/class_il/convs/conv_imagenet.py official repository ran no licence file found · pointer only · 5af62c5da8dacdb2 · report
mutate byyx666/archcraft/class_il/model_code.py official repository ran no licence file found · pointer only · 371888147f2affb4 · report
params_clip byyx666/archcraft/class_il/model_code.py official repository ran no licence file found · pointer only · febede461fb34d1b · report
params_count byyx666/archcraft/class_il/model_code.py official repository ran no licence file found · pointer only · d53cc8bbad3e59cc · report
params_count byyx666/archcraft/task_il/model_code.py official repository ran no licence file found · pointer only · 84c526fa04bd55ba · report
mutate byyx666/archcraft/task_il/model_code.py official repository unverified no licence file found · pointer only · aa97e32681792f9f · report
resnet10 byyx666/archcraft/class_il/convs/resnet.py official repository unverified no licence file found · pointer only · b8e5c22b79010344 · report
resnet18 byyx666/archcraft/class_il/convs/ucir_resnet.py official repository unverified no licence file found · pointer only · 4742faeabce1f66b · report
resnet18_cbam byyx666/archcraft/class_il/convs/resnet_cbam.py official repository unverified no licence file found · pointer only · 9d7277889d69cf2d · report
resnet18_rep byyx666/archcraft/class_il/convs/modified_represnet.py official repository unverified no licence file found · pointer only · ecaa7ca05d715804 · report
resnet34_cbam byyx666/archcraft/class_il/convs/resnet_cbam.py official repository unverified no licence file found · pointer only · 9eb3d43ee2e8ae7d · report

Tasks

Class Incremental LearningContinual LearningIncremental Learning

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