SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.14829 · IJCAI · 2024

Revisiting Neural Networks for Continual Learning: An Architectural Perspective

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

arXiv · PDF · Open in the Atlas

Code that ran

14 of 19 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 8 failures of our instrument; 5 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/2404.14829.json · badge: /api/ran/2404.14829.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
byyx666/archcraft canonical (classifier label)
classifier basis: census
10 ran · 5 no recorded run
byyx666/ArchCraft community
Papers with Code archive
4 ran · 0 no recorded run
FunctionStatusWhere it lives
BasicBlock Ran
ran on a synthesized input · constructed an object; no result was computed
byyx666/ArchCraft/task_il/networks/arch_craft.py
pointer only (licence: NONE) · get_code("9447851a9454a03a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, byyx666/ArchCraft 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.

BasicBlockRes Ran
ran on a synthesized input · constructed an object; no result was computed
byyx666/ArchCraft/task_il/networks/arch_craft.py
pointer only (licence: NONE) · get_code("7ab8bd831d4c5b9e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, byyx666/ArchCraft 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.

DownsampleB Ran
ran on a synthesized input · constructed an object; no result was computed
byyx666/ArchCraft/task_il/networks/arch_craft.py
pointer only (licence: NONE) · get_code("8a7d5641e4d53e3b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, byyx666/ArchCraft 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.

Net Ran
ran on a synthesized input · constructed an object; no result was computed
byyx666/ArchCraft/task_il/networks/arch_craft.py
pointer only (licence: NONE) · get_code("54ceb19348d05def")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, byyx666/ArchCraft 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.

conv1x1 Ran
ran; our contract draft was wrong, not the code
byyx666/archcraft/class_il/convs/memo_resnet.py
pointer only (licence: NONE) · get_code("d9def42110729a85")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, byyx666/archcraft 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
byyx666/archcraft/class_il/convs/memo_resnet.py
pointer only (licence: NONE) · get_code("160bb14bd76201b4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, byyx666/archcraft 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
byyx666/archcraft/class_il/convs/modified_represnet.py
pointer only (licence: NONE) · get_code("1907f2ae25449f39")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, byyx666/archcraft 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.

conv_block Ran
ran; our contract draft was wrong, not the code
byyx666/archcraft/class_il/convs/conv_imagenet.py
pointer only (licence: NONE); the stored copy get_code serves, from tiangeluo/fsl-global, is pointer only (licence: GPL-2.0) · get_code("9d556d61294bb0a8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, byyx666/archcraft 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.

first_block Ran
ran; our contract draft was wrong, not the code
byyx666/archcraft/class_il/convs/conv_imagenet.py
pointer only (licence: NONE) · get_code("5af62c5da8dacdb2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, byyx666/archcraft 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.

mutate Ran
ran; our contract draft was wrong, not the code
byyx666/archcraft/class_il/model_code.py
pointer only (licence: NONE) · get_code("371888147f2affb4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, byyx666/archcraft 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.

params_clip Ran
ran; our contract draft was wrong, not the code
byyx666/archcraft/class_il/model_code.py
pointer only (licence: NONE) · get_code("febede461fb34d1b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, byyx666/archcraft 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.

params_count Ran
ran, honoured the contract we drafted
byyx666/archcraft/class_il/model_code.py
pointer only (licence: NONE) · get_code("d53cc8bbad3e59cc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, byyx666/archcraft 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.

params_count Ran
ran, honoured the contract we drafted
byyx666/archcraft/task_il/model_code.py
pointer only (licence: NONE) · get_code("84c526fa04bd55ba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, byyx666/archcraft 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_rep Ran
ran; our contract draft was wrong, not the code
byyx666/archcraft/class_il/convs/modified_represnet.py
pointer only (licence: NONE); the stored copy get_code serves, from jinglin-liang/OLAS, is pointer only (licence: NONE) · get_code("ecaa7ca05d715804")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, byyx666/archcraft 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.

mutate Not yet run
unverified (harvested, no recorded run)
byyx666/archcraft/task_il/model_code.py
pointer only (licence: NONE) · get_code("aa97e32681792f9f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, byyx666/archcraft 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.

resnet10 Not yet run
unverified (harvested, no recorded run)
byyx666/archcraft/class_il/convs/resnet.py
pointer only (licence: NONE) · get_code("b8e5c22b79010344")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, byyx666/archcraft 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.

resnet18 Not yet run
unverified (harvested, no recorded run)
byyx666/archcraft/class_il/convs/ucir_resnet.py
pointer only (licence: NONE); the stored copy get_code serves, from jinglin-liang/OLAS, is pointer only (licence: NONE) · get_code("4742faeabce1f66b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, byyx666/archcraft 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.

resnet18_cbam Not yet run
unverified (harvested, no recorded run)
byyx666/archcraft/class_il/convs/resnet_cbam.py
pointer only (licence: NONE); the stored copy get_code serves, from jinglin-liang/OLAS, is pointer only (licence: NONE) · get_code("9d7277889d69cf2d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, byyx666/archcraft 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_cbam Not yet run
unverified (harvested, no recorded run)
byyx666/archcraft/class_il/convs/resnet_cbam.py
pointer only (licence: NONE); the stored copy get_code serves, from jinglin-liang/OLAS, is pointer only (licence: NONE) · get_code("9eb3d43ee2e8ae7d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, byyx666/archcraft 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 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 distinct functions with an identity, 10 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 10 the same month, 7 later) and 9 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
conv1x1 431 other papers
344 dated earlier, 6 the same month, 70 later, 10 same year, order not determinable, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
conv3x3 312 other papers
238 dated earlier, 7 the same month, 56 later, 10 same year, order not determinable, 1 undated · 31 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 309 more not named here
resnet18 95 other papers
68 dated earlier, 2 the same month, 21 later, 3 same year, order not determinable, 1 undated
1805.00907 (2018-05)
Glow: Graph Lowering Compiler Techniques for Neural Networks
1902.08153 (2019-02)
Learned Step Size Quantization
1904.01355 (2019-04)
FCOS: Fully Convolutional One-Stage Object Detection
and 92 more not named here
conv3x3 74 other papers
58 dated earlier, 2 the same month, 13 later, 1 same year, order not determinable · 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
conv_block 11 other papers
10 dated earlier, 1 the same month
1703.05175 (2017-03)
Prototypical Networks for Few-shot Learning
1908.05257 (2019-08)
Few-Shot Learning with Global Class Representations
1911.06045 (2019-11)
Self-Supervised Learning For Few-Shot Image Classification
and 8 more not named here
resnet34_cbam 11 other papers
3 dated earlier, 1 the same month, 6 later, 1 same year, order not determinable
2309.14062 (2023-09)
FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
2310.15171 (2023-10)
RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions
aaai_29079 (2024 (year only))
Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning
and 8 more not named here
resnet18_cbam 10 other papers
4 dated earlier, 1 the same month, 4 later, 1 same year, order not determinable
2308.09297 (2023-08)
NAPA-VQ: Neighborhood Aware Prototype Augmentation with Vector Quantization for Continual Learning
2309.14062 (2023-09)
FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
2310.15171 (2023-10)
RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions
and 7 more not named here
resnet18_rep 6 other papers
2 dated earlier, 1 the same month, 2 later, 1 same year, order not determinable
2309.14062 (2023-09)
FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
aaai_29079 (2024 (year only))
Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning
2403.14101 (2024-03)
Text-Enhanced Data-free Approach for Federated Class-Incremental Learning
and 3 more not named here
resnet10 3 other papers
1 dated earlier, 1 the same month, 1 same year, order not determinable
2104.00466 (2021-04)
Improving Calibration for Long-Tailed Recognition
aaai_29262 (2024 (year only))
Feature Fusion from Head to Tail for Long-Tailed Visual Recognition
2404.00986 (2024-04)
Make Continual Learning Stronger via C-Flat
first_block 1 other paper
1 the same month
2404.00986 (2024-04)
Make Continual Learning Stronger via C-Flat

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

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 CLfriendly 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.

For agents

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

get_harvested_code_for_paper("2404.14829")
get_code_for_paper("2404.14829")
have("2404.14829")

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

curl https://syntology.ai/api/ran/2404.14829.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.14829.svg)](https://syntology.ai/paper/2404.14829)

Connect an agent — have() is free.