SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.14975 · NeurIPS · 2023

Eliminating Domain Bias for Federated Learning in Representation Space

Hao Wang, Jian Cao, Yang Hua, Jianqing Zhang, Tao Song, Zhengui Xue, Ruhui Ma, Haibing Guan

arXiv · PDF · Open in the Atlas

Code that ran

12 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 8 failures of our instrument; 4 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/2311.14975.json · badge: /api/ran/2311.14975.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
TsingZ0/DBE canonical (classifier label)
classifier basis: census
7 ran · 2 no recorded run
tsingz0/dbe community
Papers with Code archive
4 ran · 1 no recorded run
TsingZ0/PFLlib community
Papers with Code archive
1 ran · 1 no recorded run
FunctionStatusWhere it lives
Client Ran
ran on a synthesized input · constructed an object; no result was computed
tsingz0/dbe/system/flcore/clients/clientDBE.py
code served (permissive licence) · get_code("bcb93a525852f945")
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, Client: 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
import torch.nn as nn
import numpy as np
from torch.utils.data import DataLoader

torch.manual_seed(0)

# Create a minimal model
class SimpleModel(nn.Module):
    def __init__(self, num_classes=10):
        super(SimpleModel, self).__init__()
        self.fc1 = nn.Linear(4, 8)
        self.fc2 = nn.Linear(8, num_classes)
    
    def forward(self, x):
        x = torch.relu(self.fc1(x))
        x = self.fc2(x)
        return x

# Create a minimal args object
class Args:
    def __init__(self):
        self.model = SimpleModel(num_classes=10)
        self.algorithm = "FedAvg"
        self.dataset = "MNIST"
        self.device = torch.device("cpu")
        self.save_folder_name = "test_folder"
        self.num_classes = 10
        self.batch_size = 2
        self.local_learning_rate = 0.01
        self.local_epochs = 5
        self.privacy = False
        self.dp_sigma = 0.0
        self.learning_rate_decay_gamma = 0.99
        self.learning_rate_decay = False

args = Args()

# Create sample training data: list of (x, y) tuples
train_data = [
    (torch.randn(4, dtype=torch.float32), torch.tensor(0, dtype=torch.int64)),
    (torch.randn(4, dtype=torch.float32), torch.tensor(1, dtype=torch.int64)),
    (torch.randn(4, dtype=torch.float32), torch.tensor(2, dtype=torch.int64)),
    (torch.randn(4, dtype=torch.float32), torch.tensor(3, dtype=torch.int64)),
]

test_data = [
    (torch.randn(4, dtype=torch.float32), torch.tensor(4, dtype=torch.int64)),
    (torch.randn(4, dtype=torch.float32), torch.tensor(5, dtype=torch.int64)),
]

ARGS = {
    'args': args,
    'id': 0,
    'train_samples': len(train_data),
    'test_samples': len(test_data),
    'train_slow': False,
    'send_slow': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Client — 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 Client 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
Client Ran
ran on a synthesized input · constructed an object; no result was computed
TsingZ0/PFLlib/system/flcore/clients/clientdbe.py
code served (permissive licence) · get_code("b34107b395a46a1f")
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, Client: 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
import torch.nn as nn
import numpy as np
from collections import defaultdict

torch.manual_seed(0)

# Create a minimal model
class SimpleModel(nn.Module):
    def __init__(self, num_classes=10):
        super(SimpleModel, self).__init__()
        self.fc1 = nn.Linear(4, 8)
        self.fc2 = nn.Linear(8, num_classes)
    
    def forward(self, x):
        if isinstance(x, (list, tuple)):
            x = x[0]
        x = torch.relu(self.fc1(x))
        x = self.fc2(x)
        return x

# Create a simple args class
class Args:
    def __init__(self):
        self.model = SimpleModel(num_classes=10)
        self.algorithm = "FedAvg"
        self.dataset = "MNIST"
        self.device = "cpu"
        self.save_folder_name = "test_folder"
        self.num_classes = 10
        self.batch_size = 2
        self.local_learning_rate = 0.01
        self.local_epochs = 1
        self.few_shot = 0
        self.learning_rate_decay_gamma = 0.99
        self.learning_rate_decay = True

ARGS = {
    'args': Args(),
    'id': 0,
    'train_samples': 10,
    'test_samples': 5,
    'train_slow': False,
    'send_slow': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Client — 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 Client 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
DLG Ran
ran, honoured the contract we drafted
TsingZ0/DBE/system/utils/dlg.py
code served (permissive licence) · get_code("b215fd88c9a94b27")
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
import torch.nn as nn
import numpy as np
import math

torch.manual_seed(0)

# Build a simple neural network
class SimpleNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 8)
        self.linear2 = nn.Linear(8, 3)
    
    def forward(self, x):
        x = torch.relu(self.linear1(x))
        x = self.linear2(x)
        return x

net = SimpleNet()

# Create origin gradients (dummy gradients for the network parameters)
origin_grad = []
for param in net.parameters():
    origin_grad.append(torch.randn_like(param))

# Create target_inputs as a list of (gt_data, gt_out) tuples
# gt_data should be batch_size x input_dim, gt_out should be batch_size x output_dim
target_inputs = [
    (torch.randn(2, 4), torch.randn(2, 3)),
    (torch.randn(2, 4), torch.randn(2, 3))
]

ARGS = {
    "net": net,
    "origin_grad": origin_grad,
    "target_inputs": target_inputs
}
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 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
alexnet Ran
ran; our contract draft was wrong, not the code
TsingZ0/DBE/system/flcore/trainmodel/alexnet.py
code served (permissive licence) · get_code("4839e6f3a569f1b9")
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 AlexNet. 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 = {
    'pretrained': False,
    'progress': True,
}
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 AlexNet — a AlexNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a AlexNet 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
TsingZ0/DBE/system/flcore/trainmodel/resnet.py
pointer only (licence: Apache-2.0); 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 (Apache-2.0), 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
TsingZ0/DBE/system/flcore/trainmodel/resnet.py
pointer only (licence: Apache-2.0); 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 (Apache-2.0), 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.

mobilenet_v2 Ran
ran; our contract draft was wrong, not the code
TsingZ0/DBE/system/flcore/trainmodel/mobilenet_v2.py
code served (permissive licence) · get_code("22b172e83bc1a35c")
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 MobileNetV2. 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,
    'width_mult': 1.0,
    'inverted_residual_setting': None,
    'round_nearest': 8,
    'block': None,
    'norm_layer': None,
}
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 MobileNetV2 — a MobileNetV2 output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MobileNetV2 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
psnr Ran
ran, honoured the contract we drafted
TsingZ0/DBE/system/utils/dlg.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from phamdinhdat-ai/Fed_2024, is pointer only (licence: NONE) · get_code("4946a7bb15ea5717")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from phamdinhdat-ai/Fed_2024, 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.

read_client_data Ran
ran; our contract draft was wrong, not the code
tsingz0/dbe/system/flcore/clients/clientDBE.py
code served (permissive licence) · get_code("595b80d1ed9df88b")
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 list. 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 os
import tempfile
import shutil

torch.manual_seed(0)

# Create a temporary directory structure for the dataset
temp_dir = tempfile.mkdtemp()
dataset_dir = os.path.join(temp_dir, 'dataset')
os.makedirs(dataset_dir, exist_ok=True)

# Create a sample dataset directory
sample_dataset = 'sample_dataset'
sample_path = os.path.join(dataset_dir, sample_dataset)
train_dir = os.path.join(sample_path, 'train')
test_dir = os.path.join(sample_path, 'test')
os.makedirs(train_dir, exist_ok=True)
os.makedirs(test_dir, exist_ok=True)

# Create sample train data file
train_data = {
    'x': np.random.randint(0, 10, size=(2, 4)),
    'y': np.random.randint(0, 3, size=2)
}
train_file = os.path.join(train_dir, '0.npz')
np.savez(train_file, data=train_data)

# Create sample test data file
test_data = {
    'x': np.random.randint(0, 10, size=(2, 4)),
    'y': np.random.randint(0, 3, size=2)
}
test_file = os.path.join(test_dir, '0.npz')
np.savez(test_file, data=test_data)

# Patch os.path.join to redirect to our temp directory
original_join = os.path.join
def patched_join(*args):
    if args and args[0] == '../dataset':
        return original_join(dataset_dir, *args[1:])
    return original_join(*args)
os.path.join = patched_join

ARGS = {
    'dataset': 'sample_dataset',
    'idx': 0,
    'is_train': True
}
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 list — a list 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
read_client_data Ran
ran; our contract draft was wrong, not the code
TsingZ0/DBE/system/utils/data_utils.py
code served (permissive licence) · get_code("10541ee086fd6a62")
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 list. 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 os
import tempfile
import shutil

torch.manual_seed(0)

# Create a temporary directory structure to mock the dataset
temp_dir = tempfile.mkdtemp()
dataset_name = 'TestDataset'
dataset_path = os.path.join(temp_dir, 'dataset', dataset_name)
train_dir = os.path.join(dataset_path, 'train')
test_dir = os.path.join(dataset_path, 'test')
os.makedirs(train_dir, exist_ok=True)
os.makedirs(test_dir, exist_ok=True)

# Create mock training data
train_data = {
    'x': np.array([[1, 2, 3, 4], [5, 6, 7, 8]], dtype=np.int64),
    'y': np.array([0, 1], dtype=np.int64)
}
train_file = os.path.join(train_dir, '0.npz')
np.savez(train_file, data=train_data)

# Create mock test data
test_data = {
    'x': np.array([[9, 10, 11, 12], [13, 14, 15, 16]], dtype=np.int64),
    'y': np.array([1, 0], dtype=np.int64)
}
test_file = os.path.join(test_dir, '0.npz')
np.savez(test_file, data=test_data)

# Patch os.path.join to redirect to our temp directory
original_join = os.path.join
def patched_join(a, *p):
    if a == '../dataset':
        return os.path.join(temp_dir, 'dataset', *p)
    return original_join(a, *p)

os.path.join = patched_join

ARGS = {
    'dataset': dataset_name,
    'idx': 0,
    'is_train': True
}
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 list — a list 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
read_client_data_Shakespeare Ran
ran; our contract draft was wrong, not the code
tsingz0/dbe/system/flcore/clients/clientDBE.py
code served (permissive licence) · get_code("63f5fae02e590aa7")
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 list. 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 os
import tempfile
import shutil

torch.manual_seed(0)

# Create a temporary directory structure to mock the dataset
temp_dir = tempfile.mkdtemp()
dataset_name = 'test_dataset'
dataset_path = os.path.join(temp_dir, 'dataset', dataset_name)
train_dir = os.path.join(dataset_path, 'train')
test_dir = os.path.join(dataset_path, 'test')

os.makedirs(train_dir, exist_ok=True)
os.makedirs(test_dir, exist_ok=True)

# Create mock training data
train_data = {
    'x': np.array([[1, 2, 3, 4], [5, 6, 7, 8]], dtype=np.int64),
    'y': np.array([0, 1], dtype=np.int64)
}
train_file = os.path.join(train_dir, '0.npz')
np.savez(train_file, data=train_data)

# Create mock test data
test_data = {
    'x': np.array([[9, 10, 11, 12], [13, 14, 15, 16]], dtype=np.int64),
    'y': np.array([1, 0], dtype=np.int64)
}
test_file = os.path.join(test_dir, '0.npz')
np.savez(test_file, data=test_data)

# Patch os.path.join to use our temp directory
original_join = os.path.join
def patched_join(*args):
    if args and args[0] == '../dataset':
        return original_join(temp_dir, 'dataset', *args[1:])
    return original_join(*args)

os.path.join = patched_join

ARGS = {
    'dataset': dataset_name,
    'idx': 0,
    'is_train': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list 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
read_client_data_text Ran
ran; our contract draft was wrong, not the code
tsingz0/dbe/system/flcore/clients/clientDBE.py
code served (permissive licence) · get_code("62bd3835aba88265")
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 list. 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 os
import tempfile
import shutil

torch.manual_seed(0)

# Create a temporary directory structure to mock the dataset
temp_dir = tempfile.mkdtemp()
dataset_name = "test_dataset"
dataset_path = os.path.join(temp_dir, dataset_name)
train_dir = os.path.join(dataset_path, 'train')
test_dir = os.path.join(dataset_path, 'test')

os.makedirs(train_dir, exist_ok=True)
os.makedirs(test_dir, exist_ok=True)

# Create mock training data
train_data = {
    'x': [(np.array([1, 2, 3, 4]), 4), (np.array([5, 6, 7, 8]), 4)],
    'y': [0, 1]
}
train_file = os.path.join(train_dir, '0.npz')
np.savez(train_file, data=train_data)

# Create mock test data
test_data = {
    'x': [(np.array([9, 10, 11, 12]), 4), (np.array([13, 14, 15, 16]), 4)],
    'y': [1, 0]
}
test_file = os.path.join(test_dir, '0.npz')
np.savez(test_file, data=test_data)

# Patch os.path.join to use our temp directory
original_join = os.path.join
def patched_join(*args):
    if len(args) > 0 and args[0] == '../dataset':
        return original_join(temp_dir, *args[1:])
    return original_join(*args)

os.path.join = patched_join

ARGS = {
    'dataset': dataset_name,
    'idx': 0,
    'is_train': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list 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
clientDBE Not yet run
unverified (harvested, no recorded run)
tsingz0/dbe/system/flcore/clients/clientDBE.py
code served (permissive licence) · get_code("cbbf4025770d2739")
How it ran

no invocation recorded.

clientDBE Not yet run
unverified (harvested, no recorded run)
TsingZ0/PFLlib/system/flcore/clients/clientdbe.py
code served (permissive licence) · get_code("65f41de191a63731")
How it ran

no invocation recorded.

read_client_data_text Not yet run
unverified (harvested, no recorded run)
TsingZ0/DBE/system/utils/data_utils.py
code served (permissive licence) · get_code("736b76e55626f3c9")
How it ran

no invocation recorded.

read_data Not yet run
unverified (harvested, no recorded run)
TsingZ0/DBE/system/utils/data_utils.py
code served (permissive licence) · get_code("2e468f03b54c3418")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 11 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 2 the same month, 10 later) and 3 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
conv1x1 112 other papers
58 dated earlier, 2 the same month, 50 later, 2 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
60 dated earlier, 1 the same month, 48 later, 2 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
Client
brick of this paper's assembly: helper
9 other papers
9 dated earlier · 2 only as an assembly brick
1602.05629 (2016-02)
Communication-Efficient Learning of Deep Networks from Decentralized Data
2001.01523 (2020-01)
Think Locally, Act Globally: Federated Learning with Local and Global Representations
2012.04221 (2020-12)
Ditto: Fair and Robust Federated Learning Through Personalization
and 6 more not named here
DLG 8 other papers
6 dated earlier, 2 later · 4 only as an assembly brick
1602.05629 (2016-02)
Communication-Efficient Learning of Deep Networks from Decentralized Data
2102.07623 (2021-02)
FedBN: Federated Learning on Non-IID Features via Local Batch Normalization
2106.06042 (2021-06)
FEDBABU: TOWARD ENHANCED REPRESENTATION FOR FEDERATED IMAGE CLASSIFICATION
and 5 more not named here
read_client_data_text
brick of this paper's assembly: helper
8 other papers
4 dated earlier, 4 later · 2 only as an assembly brick
1602.05629 (2016-02)
Communication-Efficient Learning of Deep Networks from Decentralized Data
2212.01197 (2022-12)
FedALA: Adaptive Local Aggregation for Personalized Federated Learning
2307.10507 (2023-07)
FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model Interpolation
and 5 more not named here
read_client_data
brick of this paper's assembly: helper
5 other papers
2 dated earlier, 3 later · 2 only as an assembly brick
2212.01197 (2022-12)
FedALA: Adaptive Local Aggregation for Personalized Federated Learning
2308.10279 (2023-08)
GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning
2401.03230 (2024-01)
FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning
and 2 more not named here
read_data
brick of this paper's assembly: helper
5 other papers
2 dated earlier, 3 later · 2 only as an assembly brick
2212.01197 (2022-12)
FedALA: Adaptive Local Aggregation for Personalized Federated Learning
2308.10279 (2023-08)
GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning
2401.03230 (2024-01)
FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning
and 2 more not named here
read_client_data_Shakespeare
brick of this paper's assembly: helper
4 other papers
1 dated earlier, 3 later · 2 only as an assembly brick
2308.10279 (2023-08)
GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning
2401.03230 (2024-01)
FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning
2403.15760 (2024-03)
An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learning
and 1 more not named here
alexnet 1 other paper
1 later
2403.15760 (2024-03)
An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learning
mobilenet_v2 1 other paper
1 later
2403.15760 (2024-03)
An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learning
psnr 1 other paper
1 later
2601.04587 (2026-01)
FedKDX: Federated Learning with Negative Knowledge Distillation for Enhanced Healthcare AI Systems

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) is popular for its privacy-preserving and collaborative learning abilities. However, under statistically heterogeneous scenarios, we observe that biased data domains on clients cause a representation bias phenomenon and further degenerate generic representations during local training, i.e., the representation degeneration phenomenon. To address these issues, we propose a general framework Domain Bias Eliminator (DBE) for FL. Our theoretical analysis reveals that DBE can promote bi-directional knowledge transfer between server and client, as it reduces the domain discrepancy between server and client in representation space. Besides, extensive experiments on four datasets show that DBE can greatly improve existing FL methods in both generalization and personalization abilities. The DBE-equipped FL method can outperform ten state-of-the-art personalized FL methods by a large margin. Our code is public at https://github.com/TsingZ0/DBE.

For agents

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

get_harvested_code_for_paper("2311.14975")
get_code_for_paper("2311.14975")
have("2311.14975")

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

curl https://syntology.ai/api/ran/2311.14975.json

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

[![Syntology run record](https://syntology.ai/api/ran/2311.14975.svg)](https://syntology.ai/paper/2311.14975)

Connect an agent — have() is free.