SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.02142 · NeurIPS · 2022

Deep invariant networks with differentiable augmentation layers

Alexandre Gramfort, Thomas Moreau, Cédric Rommel

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 1 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/2202.02142.json · badge: /api/ran/2202.02142.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
cedricrommel/augnet canonical (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
FunctionStatusWhere it lives
AugmentationLayer Ran
ran on a synthesized input · constructed an object; no result was computed
cedricrommel/augnet/augnet/models/augnet.py
code served (permissive licence) · get_code("f8b2da3bb8ce9bf4")
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 an instance of its own class, AugmentationLayer: the run constructed the object and did not call it, so no result was computed. 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
from torch import nn, Tensor

torch.manual_seed(0)

# Create minimal augmentation modules that satisfy the interface
class MinimalAugmentation(nn.Module):
    def __init__(self, has_magnitude=True):
        super().__init__()
        if has_magnitude:
            self._magnitude = nn.Parameter(torch.tensor(0.5))
            self.magnitude = self._magnitude
        else:
            self._magnitude = None
            self.magnitude = None
        
        self._probability = nn.Parameter(torch.tensor(0.7))
        self.probability = self._probability
    
    def forward(self, x):
        # Simple identity augmentation
        return x

# Create a list of augmentation modules
aug1 = MinimalAugmentation(has_magnitude=True)
aug2 = MinimalAugmentation(has_magnitude=False)
augmentations = [aug1, aug2]

# Define ARGS dictionary with all parameters
ARGS = {
    'augmentations': augmentations,
    'temperature': 1.0,
    'initial_weights': torch.tensor([0.6, 0.4]),
    'data_dim': 3,
    'fixed_probability': 1.0
}
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 AugmentationLayer — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a AugmentationLayer output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
aggreg_and_print_metric Not yet run
unverified (harvested, no recorded run)
cedricrommel/augnet/experiments/cifar10/train_augerino_new.py
code served (permissive licence) · get_code("3c17a5604b076c0f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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

Designing learning systems which are invariant to certain data transformations is critical in machine learning. Practitioners can typically enforce a desired invariance on the trained model through the choice of a network architecture, e.g. using convolutions for translations, or using data augmentation. Yet, enforcing true invariance in the network can be difficult, and data invariances are not always known a piori. State-of-the-art methods for learning data augmentation policies require held-out data and are based on bilevel optimization problems, which are complex to solve and often computationally demanding. In this work we investigate new ways of learning invariances only from the training data. Using learnable augmentation layers built directly in the network, we demonstrate that our method is very versatile. It can incorporate any type of differentiable augmentation and be applied to a broad class of learning problems beyond computer vision. We provide empirical evidence showing that our approach is easier and faster to train than modern automatic data augmentation techniques based on bilevel optimization, while achieving comparable results. Experiments show that while the invariances transferred to a model through automatic data augmentation are limited by the model expressivity, the invariance yielded by our approach is insensitive to it by design. 36th Conference on Neural Information Processing Systems (NeurIPS 2022).

For agents

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

get_harvested_code_for_paper("2202.02142")
get_code_for_paper("2202.02142")
have("2202.02142")

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

curl https://syntology.ai/api/ran/2202.02142.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.02142.svg)](https://syntology.ai/paper/2202.02142)

Connect an agent — have() is free.