SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.01289 · ICLR · 2023

Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning

Yisen Wang, Yifei Wang, Rundong Luo

arXiv · PDF · Open in the Atlas

Code that ran

None of the 10 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (10 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/2303.01289.json · badge: /api/ran/2303.01289.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
pku-ml/dynacl canonical (classifier label)
classifier basis: classifier_2025
0 ran · 10 no recorded run
FunctionStatusWhere it lives
PGD_contrastive Not yet run
unverified (harvested, no recorded run)
pku-ml/dynacl/train_DynACL.py
pointer only (licence: NONE) · get_code("eab4871a4e41ef63")
How it ran

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

PGD_contrastive Not yet run
unverified (harvested, no recorded run)
pku-ml/dynacl/train_DynACL.py
pointer only (licence: NONE) · get_code("f9aee0a7d5571cc8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pku-ml/dynacl 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)
pku-ml/dynacl/train_DynACL.py
pointer only (licence: NONE) · get_code("71d7a5fe7208bd5b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pku-ml/dynacl 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)
pku-ml/dynacl/LPAFT.py
pointer only (licence: NONE) · get_code("21ded214fa0c58f4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pku-ml/dynacl 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)
pku-ml/dynacl/LPAFT_AFF.py
pointer only (licence: NONE) · get_code("adfc6498df48c365")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pku-ml/dynacl 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)
pku-ml/dynacl/train_DynACL.py
pointer only (licence: NONE) · get_code("86a8813c1ea89045")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pku-ml/dynacl 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_head Not yet run
unverified (harvested, no recorded run)
pku-ml/dynacl/LPAFT.py
pointer only (licence: NONE) · get_code("ce621e27660c3383")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pku-ml/dynacl 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_head Not yet run
unverified (harvested, no recorded run)
pku-ml/dynacl/LPAFT_AFF.py
pointer only (licence: NONE) · get_code("f7e78f7868dd48c7")
How it ran

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

validate Not yet run
unverified (harvested, no recorded run)
pku-ml/dynacl/train_DynACL.py
pointer only (licence: NONE) · get_code("9040321f6a02a4c0")
How it ran

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

validate Not yet run
unverified (harvested, no recorded run)
pku-ml/dynacl/LPAFT_AFF.py
pointer only (licence: NONE) · get_code("8c927972c0406923")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pku-ml/dynacl 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 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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.

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

Recent works have shown that self-supervised learning can achieve remarkable robustness when integrated with adversarial training (AT). However, the robustness gap between supervised AT (sup-AT) and self-supervised AT (self-AT) remains significant. Motivated by this observation, we revisit existing self-AT methods and discover an inherent dilemma that affects self-AT robustness: either strong or weak data augmentations are harmful to self-AT, and a medium strength is insufficient to bridge the gap. To resolve this dilemma, we propose a simple remedy named DYNACL (Dynamic Adversarial Contrastive Learning). In particular, we propose an augmentation schedule that gradually anneals from a strong augmentation to a weak one to benefit from both extreme cases. Besides, we adopt a fast post-processing stage for adapting it to downstream tasks. Through extensive experiments, we show that DYNACL can improve state-of-the-art self-AT robustness by 8.84% under Auto-Attack on the CIFAR-10 dataset, and can even outperform vanilla supervised adversarial training for the first time. Our code is available at https://github.com/PKU-ML/DYNACL.

For agents

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

get_harvested_code_for_paper("2303.01289")
get_code_for_paper("2303.01289")
have("2303.01289")

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

curl https://syntology.ai/api/ran/2303.01289.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.01289.svg)](https://syntology.ai/paper/2303.01289)

Connect an agent — have() is free.