SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2501.10466 · ICML · 2025

Efficient Semi-Supervised Adversarial Training via Latent Clustering-Based Data Reduction

Xiao Zhang, Somrita Ghosh, Yuelin Xu

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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; 4 failures of our instrument; 0 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/2501.10466.json · badge: /api/ran/2501.10466.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
trustmlrg/efficientssat canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
TrustMLRG/EfficientSSAT community
Papers with Code archive
1 ran · 0 no recorded run
somrita99/SSATwithLCS marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
_lcs_km_order Ran
ran; our contract draft was wrong, not the code
TrustMLRG/EfficientSSAT/datasets.py
code served (permissive licence) · get_code("906802529bac67d1")
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 ndarray, ndim 1, dtype family int, shape (10,) 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 numpy as np
from numpy.random import Generator, PCG64

# Set up random number generator
rng = np.random.Generator(PCG64(seed=42))

# Create sample feature data: 10 samples, 5 features
feats = np.random.randn(10, 5).astype(np.float64)

# Define parameters
kmeans_k = 3
selection_seed = 0

ARGS = {
    "feats": feats,
    "kmeans_k": kmeans_k,
    "selection_seed": selection_seed,
    "rng": rng,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family int, shape (10,) — shape (10,) 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
build_embeddings_and_pseudolabels Ran
ran; our contract draft was wrong, not the code
somrita99/SSATwithLCS/diffusionmgmm.py
pointer only (licence: NONE) · get_code("3e625fc5f22175b7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, somrita99/SSATwithLCS 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.

confidence_minimization_loss Ran
ran; our contract draft was wrong, not the code
trustmlrg/efficientssat/diffusionm.py
code served (permissive licence) · get_code("c1621b9c5bab6107")
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) 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.functional as F

torch.manual_seed(0)

# The function takes logits as input and computes confidence minimization loss
# logits should be a 2D tensor of shape (batch_size, num_classes)
# The function applies softmax, gets max confidence per sample, and returns negative mean

logits = torch.randn(2, 4)  # batch_size=2, num_classes=4

ARGS = {
    "logits": logits,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
eval_loader Ran
ran, honoured the contract we drafted
trustmlrg/efficientssat/trainnew.py
code served (permissive licence) · get_code("996b377efc034323")
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) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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.utils.data import DataLoader

torch.manual_seed(0)

# Define a minimal model that takes input and produces classification output
class MinimalModel(nn.Module):
    def __init__(self, input_dim=4, num_classes=3):
        super().__init__()
        self.linear = nn.Linear(input_dim, num_classes)
    
    def forward(self, x):
        return self.linear(x)

# Create model instance
model = MinimalModel(input_dim=4, num_classes=3)

# Create device
device = torch.device('cpu')

# Create a minimal DataLoader with tiny tensors
# Each batch: (data, target) where data is [batch_size, 4] and target is [batch_size]
data_list = [
    (torch.randn(2, 4), torch.tensor([0, 1])),
    (torch.randn(2, 4), torch.tensor([2, 0])),
]
loader = DataLoader(data_list, batch_size=2)

# Define ARGS dictionary with all parameters
ARGS = {
    'model': model,
    'device': device,
    'loader': loader,
    'max_batches': None,
    'name': 'Eval'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
pgd_linf Ran
ran; our contract draft was wrong, not the code
trustmlrg/efficientssat/pgd_attack.py
code served (permissive licence) · get_code("a13f74ed9b3d0b95")
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) and returned Tensor, ndim 2, dtype family float, shape (2, 4) 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 a simple model that takes input and outputs logits for classification
class SimpleModel(nn.Module):
    def __init__(self, input_dim=4, num_classes=3):
        super().__init__()
        self.linear = nn.Linear(input_dim, num_classes)
    
    def forward(self, x):
        return self.linear(x)

# Create model instance
model = SimpleModel(input_dim=4, num_classes=3)

# Create input tensor: batch_size=2, input_dim=4
x = torch.randn(2, 4)
x = torch.clamp(x, 0.0, 1.0)  # Clamp to valid range [0, 1]

# Create target labels: batch_size=2, with class indices in range [0, 2]
y = torch.tensor([0, 2])

# Define arguments dictionary
ARGS = {
    "model_for_grad": model,
    "x": x,
    "y": y,
    "epsilon": 0.3,
    "num_steps": 2,
    "step_size": 0.1,
    "random_start": True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 2, dtype family float, shape (2, 4) — shape (2, 4) 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

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 5 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

Learning robust models under adversarial settings is widely recognized as requiring a considerably large number of training samples. Recent work proposes semi-supervised adversarial training (SSAT), which utilizes external unlabeled or synthetically generated data and is currently the state of the art. However, SSAT requires substantial extra data to attain high robustness, resulting in prolonged training time and increased memory usage. In this paper, we propose data reduction strategies to improve the efficiency of SSAT by optimizing the amount of additional data incorporated. Specifically, we design novel latent clustering-based techniques to select or generate a small, critical subset of data samples near the model's decision boundary. While focusing on boundary-adjacent points, our methods maintain a balanced ratio between boundary and non-boundary data points, thereby avoiding overfitting. Comprehensive experiments across image benchmarks demonstrate that our methods can effectively reduce SSAT's data requirements and computational costs while preserving its strong robustness advantages. In particular, our latent-space selection scheme based on k-means clustering and our guided diffusion-based approach with LCG-KM are the most effective, achieving nearly identical robust accuracies with 5× to 10× less unlabeled data. When compared to full SSAT trained to convergence, our methods reduce total runtime by approximately 3× to 4× due to strategic prioritization of unlabeled data.

For agents

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

get_harvested_code_for_paper("2501.10466")
get_code_for_paper("2501.10466")
have("2501.10466")

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

curl https://syntology.ai/api/ran/2501.10466.json

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

[![Syntology run record](https://syntology.ai/api/ran/2501.10466.svg)](https://syntology.ai/paper/2501.10466)

Connect an agent — have() is free.