SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.08533 · NeurIPS · 2025

Adv-SSL: Adversarial Self-Supervised Representation Learning with Theoretical Guarantees

Yuling Jiao, Jerry Yang, Chenguang Duan, Huazhen Lin, Wensen Ma

arXiv · PDF · Open in the Atlas

Code that ran

2 of 6 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 4 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/2408.08533.json · badge: /api/ran/2408.08533.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
vincen-github/Adv-SSL community
Papers with Code archive
2 ran · 4 no recorded run
FunctionStatusWhere it lives
adv Ran
ran; our contract draft was wrong, not the code
vincen-github/Adv-SSL/methods/adv.py
code served (permissive licence) · get_code("2b71d3ec215ebece")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from torch.nn.functional import normalize
from numpy import sqrt
from torch import eye, norm, cat, trace

torch.manual_seed(0)

# Create small tensors with distinct batch and feature dimensions
batch_size = 2
feature_dim = 4

# x0: shape (2, 4) - batch of 2, features of dimension 4
x0 = torch.randn(batch_size, feature_dim)

# x1: shape (2, 4) - batch of 2, features of dimension 4
x1 = torch.randn(batch_size, feature_dim)

# G: shape (4, 4) - gram/correlation matrix for feature_dim x feature_dim
# Initialize as a small positive semi-definite matrix
G = torch.randn(feature_dim, feature_dim)
G = G @ G.T  # Make it positive semi-definite

# lambda_param: regularization parameter
lambda_param = 0.05

ARGS = {
    "x0": x0,
    "x1": x1,
    "G": G,
    "lambda_param": lambda_param
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
frobenius_inner_product Ran
ran, honoured the contract we drafted
vincen-github/Adv-SSL/methods/adv.py
code served (permissive licence) · get_code("c1e1c6febf11e188")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create two small tensors for the frobenius_inner_product function
# The function computes trace(A.T @ B), so A and B should be 2D tensors
# Using distinct dimensions (4x3 and 4x3) for clarity

A = torch.randn(4, 3)
B = torch.randn(4, 3)

ARGS = {
    "A": A,
    "B": B
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
Adv Not yet run
unverified (harvested, no recorded run)
vincen-github/Adv-SSL/methods/adv.py
code served (permissive licence) · get_code("d3c0d7a0f832baec")
How it ran

no invocation recorded.

BaseMethod Not yet run
unverified (harvested, no recorded run)
vincen-github/Adv-SSL/methods/adv.py
code served (permissive licence) · get_code("674dea343e3a353d")
How it ran

no invocation recorded.

eval_sgd Not yet run
unverified (harvested, no recorded run)
vincen-github/Adv-SSL/methods/adv.py
code served (permissive licence) · get_code("f1cd990820d62bd1")
How it ran

no invocation recorded.

get_model Not yet run
unverified (harvested, no recorded run)
vincen-github/Adv-SSL/methods/adv.py
code served (permissive licence) · get_code("06ebbacf39d65124")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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, 0 later) and 4 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
eval_sgd
brick of this paper's assembly: helper
2 other papers
2 dated earlier · 1 only as an assembly brick
2002.05709 (2020-02)
A Simple Framework for Contrastive Learning of Visual Representations
2006.07733 (2020-06)
Bootstrap your own latent: A new approach to self-supervised Learning
get_model
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2303.09079 (2023-03)
SSL-Cleanse: Trojan Detection and Mitigation in Self-Supervised Learning

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

Learning transferable data representations from abundant unlabeled data remains a central challenge in machine learning. Although numerous self-supervised learning methods have been proposed to address this challenge, a significant class of these approaches aligns the covariance or correlation matrix with the identity matrix. Despite impressive performance across various downstream tasks, these methods often suffer from biased sample risk, leading to substantial optimization shifts in mini-batch settings and complicating theoretical analysis. In this paper, we introduce a novel Adversarial Self-Supervised Representation Learning (Adv-SSL) for unbiased transfer learning with no additional cost compared to its biased counterparts. Our approach not only outperforms the existing methods across multiple benchmark datasets but is also supported by comprehensive end-to-end theoretical guarantees. Our analysis reveals that the minimax optimization in Adv-SSL encourages representations to form well-separated clusters in the embedding space, provided there is sufficient upstream unlabeled data. As a result, our method achieves strong classification performance even with limited downstream labels, shedding new light on few-shot learning.

For agents

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

get_harvested_code_for_paper("2408.08533")
get_code_for_paper("2408.08533")
have("2408.08533")

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

curl https://syntology.ai/api/ran/2408.08533.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.08533.svg)](https://syntology.ai/paper/2408.08533)

Connect an agent — have() is free.