SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.10319 · NeurIPS · 2020

Self-Adaptive Training: beyond Empirical Risk Minimization

Lang Huang, Chao Zhang, Hongyang Zhang

arXiv · PDF · Open in the Atlas

Code that ran

2 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 2 have no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-21; 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/2002.10319.json · badge: /api/ran/2002.10319.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
LayneH/self-adaptive-training canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
BorealisAI/towards-better-sel-cls community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
SelfAdaptiveTrainingCE Ran
ran on a synthesized input · constructed an object; no result was computed
LayneH/self-adaptive-training/losses/loss.py
code served (permissive licence) · get_code("cb4ce68cc060e246")
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, SelfAdaptiveTrainingCE: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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.nn import functional as F

torch.manual_seed(0)

# Create small test data
batch_size = 2
num_classes = 4
num_samples = 6

# Create labels tensor - shape (num_samples,)
labels = torch.randint(0, num_classes, (num_samples,))

# Create logits tensor - shape (batch_size, num_classes)
logits = torch.randn(batch_size, num_classes)

# Create targets tensor - shape (batch_size,)
targets = torch.randint(0, num_classes, (batch_size,))

# Create index tensor - indices into the full dataset
index = torch.tensor([0, 3])

# Epoch number
epoch = 50

ARGS = {
    "labels": labels,
    "num_classes": num_classes,
    "momentum": 0.9,
    "es": 40
}
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 SelfAdaptiveTrainingCE — 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 SelfAdaptiveTrainingCE 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
SelfAdativeTraining Ran
ran on a synthesized input
BorealisAI/towards-better-sel-cls/loss.py
pointer only (licence: NOASSERTION) · get_code("b47c02d80eb5a7e7")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, BorealisAI/towards-better-sel-cls (NOASSERTION). 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.

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose self-adaptive training-a new training algorithm that dynamically calibrates training process by model predictions without incurring extra computational cost-to improve generalization of deep learning for potentially corrupted training data. This problem is important to robustly learning from data that are corrupted by, e.g., random noises and adversarial examples. The standard empirical risk minimization (ERM) for such data, however, may easily overfit noises and thus suffers from sub-optimal performance. In this paper, we observe that model predictions can substantially benefit the training process: self-adaptive training significantly mitigates the overfitting issue and improves generalization over ERM under both random and adversarial noises. Besides, in sharp contrast to the recently-discovered double-descent phenomenon in ERM, self-adaptive training exhibits a single-descent error-capacity curve, indicating that such a phenomenon might be a result of overfitting of noises. Experiments on the CIFAR and ImageNet datasets verify the effectiveness of our approach in two applications: classification with label noise and selective classification. The code is available at https://github.com/LayneH/self-adaptive-training.

For agents

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

get_harvested_code_for_paper("2002.10319")
get_code_for_paper("2002.10319")
have("2002.10319")

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

curl https://syntology.ai/api/ran/2002.10319.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.10319.svg)](https://syntology.ai/paper/2002.10319)

Connect an agent — have() is free.