SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.04301 · 2024

Tackling Noisy Clients in Federated Learning with End-to-end Label Correction

arXiv · PDF · Open in the Atlas

Code that ran

12 of 14 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 10 failures of our instrument; 2 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/2408.04301.json · badge: /api/ran/2408.04301.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
sprinter1999/fedelc canonical (classifier label)
classifier basis: census
12 ran · 2 no recorded run
FunctionStatusWhere it lives
DaAgg Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sprinter1999/fedelc/fl_models/fed.py
code served (permissive licence) · get_code("6953bfa11fc096e9")
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 dict. 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 numpy as np
import copy

torch.manual_seed(0)

# Create small model state dicts (weight dictionaries)
# Each state dict maps parameter names to tensors
def create_model_state_dict(seed):
    torch.manual_seed(seed)
    state_dict = {
        'layer1.weight': torch.randn(3, 4),
        'layer1.bias': torch.randn(3),
        'layer2.weight': torch.randn(2, 3),
    }
    return state_dict

# Create state dicts for 4 clients
w = [
    create_model_state_dict(0),
    create_model_state_dict(1),
    create_model_state_dict(2),
    create_model_state_dict(3),
]

# dict_len: list of sizes (data sizes for each client)
dict_len = [100, 150, 120, 110]

# client_tag: 1 for clean clients, 0 for noisy clients
# In this case: clients 0,1 are clean; clients 2,3 are noisy
client_tag = [1, 1, 0, 0]

ARGS = {
    'w': w,
    'dict_len': dict_len,
    'client_tag': client_tag,
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
FedAvg Ran
ran; our contract draft was wrong, not the code
sprinter1999/fedelc/fl_models/fed.py
code served (permissive licence) · get_code("ee28ff7729e298ee")
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 dict. 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 copy

torch.manual_seed(0)

# FedAvg expects:
# - w: a list of dicts, where each dict maps keys to tensors
# - average_weights: a list of numeric weights

# Create 3 clients' weight dicts
w_client_1 = {
    'layer1': torch.randn(4, 3),
    'layer2': torch.randn(2, 5)
}

w_client_2 = {
    'layer1': torch.randn(4, 3),
    'layer2': torch.randn(2, 5)
}

w_client_3 = {
    'layer1': torch.randn(4, 3),
    'layer2': torch.randn(2, 5)
}

w = [w_client_1, w_client_2, w_client_3]

# Weights for averaging (e.g., number of samples per client)
average_weights = [10, 20, 30]

ARGS = {
    'w': w,
    'average_weights': average_weights
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
ResNet18 Ran
ran; our contract draft was wrong, not the code
sprinter1999/fedelc/resnets/model_resnet.py
code served (permissive licence) · get_code("38dc12a408b60505")
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 ResNet. 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

torch.manual_seed(0)

ARGS = {
    "num_classes": 10
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
ResNet34 Ran
ran; our contract draft was wrong, not the code
sprinter1999/fedelc/resnets/model_resnet.py
code served (permissive licence) · get_code("3a03b2b229d94786")
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 ResNet. 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

torch.manual_seed(0)

ARGS = {
    "num_classes": 10
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
conv1x1 Ran
ran; our contract draft was wrong, not the code
sprinter1999/fedelc/model_resnet_official.py
pointer only (licence: MIT); the stored copy get_code serves, from medaitech/scrd4ad, is pointer only (licence: NONE) · get_code("2a80220dabcb742a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from medaitech/scrd4ad, and GitHub detected no licence in that repository 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
sprinter1999/fedelc/model_resnet_official.py
pointer only (licence: MIT); the stored copy get_code serves, from medaitech/scrd4ad, is pointer only (licence: NONE) · get_code("600ff2c45e0de056")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from medaitech/scrd4ad, and GitHub detected no licence in that repository 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
sprinter1999/fedelc/resnets/model_resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from amerch/CIFAR100-Training, is pointer only (licence: NONE) · get_code("583f9780bdd00a45")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from amerch/CIFAR100-Training, and GitHub detected no licence in that repository 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
sprinter1999/fedelc/fl_models/nets.py
code served (permissive licence) · get_code("70815f7b9640eb64")
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 Sequential. 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

torch.manual_seed(0)

# The function conv3x3 takes in_channels, out_channels, and **kwargs
# It creates a Sequential model with Conv2d, BatchNorm2d, ReLU, and MaxPool2d
# We need to provide valid integer arguments for in_channels and out_channels
# kwargs will be passed to Conv2d, so we can include optional Conv2d parameters

ARGS = {
    "in_channels": 3,
    "out_channels": 64,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
get_model Ran
ran; our contract draft was wrong, not the code
sprinter1999/fedelc/fl_models/nets.py
code served (permissive licence) · get_code("84f42caf8978cf88")
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 CNN4Conv. 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

torch.manual_seed(0)

class Args:
    def __init__(self, num_classes):
        self.num_classes = num_classes

ARGS = {
    'args': Args(num_classes=10)
}
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 CNN4Conv — a CNN4Conv output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CNN4Conv 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
linear_rampup Ran
ran, honoured the contract we drafted
sprinter1999/fedelc/fl_models/update.py
code served (permissive licence) · get_code("6944acdaa94d65ef")
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 = {
    "current": 10,
    "warm_up": 5,
    "lambda_u": 0.5,
    "rampup_length": 16
}
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
mixup Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sprinter1999/fedelc/fl_models/update.py
code served (permissive licence) · get_code("4cdd625c4b850e8c")
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 numpy as np
import torch

torch.manual_seed(0)

# Create small input tensors for batch of 2 samples with 4 features each
inputs = torch.randn(2, 4)

# Create small target tensors for batch of 2 samples with 3 classes (one-hot or soft targets)
targets = torch.randn(2, 3)

# Define alpha parameter for beta distribution
alpha = 1.0

ARGS = {
    "inputs": inputs,
    "targets": targets,
    "alpha": alpha,
}
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
model_dist Ran
ran, honoured the contract we drafted
sprinter1999/fedelc/fl_models/fed.py
code served (permissive licence) · get_code("975bec9c5526b66a")
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 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 torch

torch.manual_seed(0)

# Create two dictionaries of tensors with the same keys
# The function expects dicts with tensor values, some of which may be integers (skipped)
# and some floats (which are used to compute distance)

w_1 = {
    'layer1': torch.randn(4, 3).float(),
    'layer2': torch.randn(2, 5).float(),
    'int_param': torch.tensor([1, 2, 3], dtype=torch.int32),
}

w_2 = {
    'layer1': torch.randn(4, 3).float(),
    'layer2': torch.randn(2, 5).float(),
    'int_param': torch.tensor([4, 5, 6], dtype=torch.int32),
}

ARGS = {
    'w_1': w_1,
    'w_2': w_2,
}
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 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
ResNet50 Not yet run
unverified (harvested, no recorded run)
sprinter1999/fedelc/model_resnet_official.py
code served (permissive licence) · get_code("b658a92985b03a37")
How it ran

no invocation recorded.

load_dataset Not yet run
unverified (harvested, no recorded run)
sprinter1999/fedelc/utils/dataset.py
code served (permissive licence) · get_code("8540a2512762d9a0")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 3 the same month, 4 later) and 6 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
conv3x3 686 other papers
618 dated earlier, 3 the same month, 48 later, 17 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
conv1x1 112 other papers
87 dated earlier, 1 the same month, 20 later, 4 same year, order not determinable · 6 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1806.01531 (2018-06)
Deep Mixture of Experts via Shallow Embedding
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
and 109 more not named here
conv3x3 111 other papers
87 dated earlier, 1 the same month, 19 later, 4 same year, order not determinable · 6 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
1806.01531 (2018-06)
Deep Mixture of Experts via Shallow Embedding
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
and 108 more not named here
ResNet18 27 other papers
19 dated earlier, 8 later
1605.07146 (2016-05)
Wide Residual Networks
1901.09847 (2019-01)
Error Feedback Fixes SignSGD and other Gradient Compression Schemes
1910.09652 (2019-10)
Kernelized Wasserstein Natural Gradient
and 24 more not named here
conv3x3 2 other papers
2 dated earlier
2106.06042 (2021-06)
FEDBABU: TOWARD ENHANCED REPRESENTATION FOR FEDERATED IMAGE CLASSIFICATION
2311.13267 (2023-11)
FedFN: Feature Normalization for Alleviating Data Heterogeneity Problem in Federated Learning
ResNet34 1 other paper
1 dated earlier
2310.07587 (2023-10)
Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer
ResNet50 1 other paper
1 dated earlier
2310.07587 (2023-10)
Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer
linear_rampup 1 other paper
1 dated earlier
2103.13646 (2021-03)
Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels

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

Recently, federated learning (FL) has achieved wide successes for diverse privacy-sensitive applications without sacrificing the sensitive private information of clients. However, the data quality of client datasets can not be guaranteed since corresponding annotations of different clients often contain complex label noise of varying degrees, which inevitably causes the performance degradation. Intuitively, the performance degradation is dominated by clients with higher noise rates since their trained models contain more misinformation from data, thus it is necessary to devise an effective optimization scheme to mitigate the negative impacts of these noisy clients. In this work, we propose a two-stage framework FedELC to tackle this complicated label noise issue. The first stage aims to guide the detection of noisy clients with higher label noise, while the second stage aims to correct the labels of noisy clients' data via an end-to-end label correction framework which is achieved by learning possible ground-truth labels of noisy clients' datasets via back propagation. We implement sixteen related methods and evaluate five datasets with three types of complicated label noise scenarios for a comprehensive comparison. Extensive experimental results demonstrate our proposed framework achieves superior performance than its counterparts for different scenarios. Additionally, we effectively improve the data quality of detected noisy clients' local datasets with our label correction framework. The code is available at https://github.com/Sprinter1999/FedELC.

For agents

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

get_harvested_code_for_paper("2408.04301")
get_code_for_paper("2408.04301")
have("2408.04301")

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

curl https://syntology.ai/api/ran/2408.04301.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.04301.svg)](https://syntology.ai/paper/2408.04301)

Connect an agent — have() is free.