SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.12529 · IJCAI · 2020

Towards Accurate and Robust Domain Adaptation under Noisy Environments

Yilong Yin, Zhongyi Han, Chaoran Cui, Xian-Jin Gui

arXiv · PDF · Open in the Atlas

Code that ran

3 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; 2 failures of our instrument; 3 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/2004.12529.json · badge: /api/ran/2004.12529.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
zhyhan/RDA marked official in Papers with Code
Papers with Code archive
3 ran · 3 no recorded run
FunctionStatusWhere it lives
class_rank_criterion Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhyhan/RDA/model/RDA.py
code served (permissive licence) · get_code("24b2248bc71483a6")
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. 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
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

batch_size = 2
num_classes = 4

outputs_source = torch.randn(batch_size, num_classes)
labels_source = torch.randint(0, num_classes, (batch_size,))
lr = 0.3
del_rate = 0.5

ARGS = {
    "outputs_source": outputs_source,
    "labels_source": labels_source,
    "lr": lr,
    "del_rate": del_rate,
}
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
entropy Ran
ran; our contract draft was wrong, not the code
zhyhan/RDA/model/RDA.py
code served (permissive licence) · get_code("8ae1cfe379f57196")
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 as nn

torch.manual_seed(0)

# The function expects output_target to be a tensor that:
# 1. Can be passed to nn.Softmax(dim=1)
# 2. Has shape compatible with softmax on dim=1
# 3. Will be used in element-wise operations with log

# Create a small tensor with batch size 2 and 4 output classes
output_target = torch.randn(2, 4)

ARGS = {
    "output_target": output_target
}
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
linear_rampup Ran
ran, honoured the contract we drafted
zhyhan/RDA/model/RDA.py
code served (permissive licence) · get_code("b62a22ec4dd59e09")
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 float, 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 numpy as np

ARGS = {
    "now_iter": 5000,
    "total_iter": 20000,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, 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
PMD Not yet run
unverified (harvested, no recorded run)
zhyhan/RDA/model/RDA.py
code served (permissive licence) · get_code("9102a9aeb2b04ff6")
How it ran

no invocation recorded.

RDANet Not yet run
unverified (harvested, no recorded run)
zhyhan/RDA/model/RDA.py
code served (permissive licence) · get_code("87def0b5f1f9171c")
How it ran

no invocation recorded.

WarmStartGradientReverseLayer Not yet run
unverified (harvested, no recorded run)
zhyhan/RDA/model/RDA.py
code served (permissive licence) · get_code("fa11465b14446e34")
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 (1 with at least one paper dated earlier, 0 the same month, 2 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
WarmStartGradientReverseLayer
brick of this paper's assembly: helper
3 other papers
1 dated earlier, 2 later
1409.7495 (2014-09)
Unsupervised Domain Adaptation by Backpropagation
2204.03838 (2022-04)
Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation
2204.07683 (2022-04)
Safe Self-Refinement for Transformer-based Domain Adaptation
entropy
brick of this paper's assembly: loss
1 other paper
1 later
2108.06129 (2021-08)
Learning Transferable Parameters for Unsupervised Domain Adaptation

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

In non-stationary environments, learning machines usually confront the domain adaptation scenario where the data distribution does change over time. Previous domain adaptation works have achieved great success in theory and practice. However, they always lose robustness in noisy environments where the labels and features of examples from the source domain become corrupted. In this paper, we report our attempt towards achieving accurate noise-robust domain adaptation. We first give a theoretical analysis that reveals how harmful noises influence unsupervised domain adaptation. To eliminate the effect of label noise, we propose an offline curriculum learning for minimizing a newly-defined empirical source risk. To reduce the impact of feature noise, we propose a proxy distribution based margin discrepancy. We seamlessly transform our methods into an adversarial network that performs efficient joint optimization for them, successfully mitigating the negative influence from both data corruption and distribution shift. A series of empirical studies show that our algorithm remarkably outperforms state of the art, over 10% accuracy improvements in some domain adaptation tasks under noisy environments.

For agents

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

get_harvested_code_for_paper("2004.12529")
get_code_for_paper("2004.12529")
have("2004.12529")

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

curl https://syntology.ai/api/ran/2004.12529.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.12529.svg)](https://syntology.ai/paper/2004.12529)

Connect an agent — have() is free.