SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.15760 · CVPR · 2024

An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learning

Yang Liu, Jian Cao, Yang Hua, Jianqing Zhang

arXiv · PDF · Open in the Atlas

Code that ran

11 of 18 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; 2 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 6 failures of our instrument; 7 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/2403.15760.json · badge: /api/ran/2403.15760.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/fedktl canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
TsingZ0/FedKTL community
Papers with Code archive
8 ran · 7 no recorded run
FunctionStatusWhere it lives
Feature_Transformer Ran
ran on a synthesized input · constructed an object; no result was computed
TsingZ0/FedKTL/system/flcore/servers/serverktl_stylegan_3.py
code served (permissive licence) · get_code("fde61fb8121b8bc1")
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, Feature_Transformer: 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

torch.manual_seed(0)

ARGS = {
    "in_features": 4,
    "out_features": 3,
    "num_layers": 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 Feature_Transformer — 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 Feature_Transformer 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
MMD Ran
ran; our contract draft was wrong, not the code
tsingz0/fedktl/system/flcore/servers/serverktl_stable_diffusion.py
code served (permissive licence) · get_code("54f1b5ed38dafdfa")
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 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

torch.manual_seed(0)

# Create two sample tensors for distributions P and Q
# Shape: (batch_size, feature_dim) = (2, 4)
x = torch.randn(2, 4)
y = torch.randn(2, 4)

# Kernel type
kernel = "multiscale"

# Device
device = "cpu"

ARGS = {
    "x": x,
    "y": y,
    "kernel": kernel,
    "device": device,
}
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 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
agg_func Ran
ran; our contract draft was wrong, not the code
TsingZ0/FedKTL/system/flcore/servers/serverktl_stylegan_3.py
code served (permissive licence) · get_code("5d6dc231986a939a")
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 torch.nn.functional as F

torch.manual_seed(0)

# The function expects a dict where:
# - keys are labels
# - values are lists of tensors (proto_list)
# Each tensor should have a .data attribute and be normalizable with dim=0

protos = {
    0: [torch.randn(4), torch.randn(4)],  # Multiple prototypes for label 0
    1: [torch.randn(4)],  # Single prototype for label 1
    2: [torch.randn(4), torch.randn(4), torch.randn(4)],  # Multiple prototypes for label 2
}

ARGS = {
    "protos": protos
}
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
alexnet Ran
ran; our contract draft was wrong, not the code
tsingz0/fedktl/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
avg_func Ran
ran; our contract draft was wrong, not the code
TsingZ0/FedKTL/system/flcore/servers/serverktl_stylegan_3.py
code served (permissive licence) · get_code("df0caf0461bb89cb")
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 torch.nn as nn

torch.manual_seed(0)

# The function expects a dict where:
# - keys are labels
# - values are lists of objects with a .data attribute (like tensors)
# It computes the average of multiple prototypes or returns single prototype

proto1_label0 = torch.randn(4, 3)
proto2_label0 = torch.randn(4, 3)
proto1_label1 = torch.randn(4, 3)

protos = {
    0: [proto1_label0, proto2_label0],
    1: [proto1_label1]
}

ARGS = {
    "protos": protos
}
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
generate_random_orthogonal_matrix Ran
ran, honoured the contract we drafted
TsingZ0/FedKTL/system/flcore/servers/serverktl_stylegan_3.py
code served (permissive licence) · get_code("96aa3382752f5281")
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 Tensor, ndim 2, dtype family float, shape (5, 3) 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
import torch

torch.manual_seed(0)

# Analyze the function:
# - feat_in: integer, used as first dimension of random matrix
# - num_classes: integer, used as second dimension of random matrix
# The function creates a random matrix of shape (feat_in, num_classes),
# performs QR decomposition, and returns P which should be orthogonal.

ARGS = {
    "feat_in": 5,
    "num_classes": 3,
}
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 Tensor, ndim 2, dtype family float, shape (5, 3) — shape (5, 3) 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
load_item Ran
ran, honoured the contract we drafted
TsingZ0/FedKTL/system/flcore/servers/serverktl_stylegan_3.py
code served (permissive licence) · get_code("132dfc2af9ff530c")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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 os
import tempfile

torch.manual_seed(0)

# Create a temporary directory for testing
temp_dir = tempfile.mkdtemp()

# Create a sample tensor to save
sample_tensor = torch.randn(2, 4)
torch.save(sample_tensor, os.path.join(temp_dir, 'test_role_test_item.pt'))

ARGS = {
    'role': 'test_role',
    'item_name': 'test_item',
    'item_path': temp_dir
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
mobilenet_v2 Ran
ran; our contract draft was wrong, not the code
tsingz0/fedktl/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
read_client_data Ran
ran on a synthesized input
TsingZ0/FedKTL/system/flcore/servers/serverktl_stylegan_3.py
code served (permissive licence) · get_code("c8273104f9d91d46")
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_dir = os.path.join(temp_dir, 'dataset', 'test_dataset')
train_dir = os.path.join(dataset_dir, 'train')
test_dir = os.path.join(dataset_dir, 'test')
os.makedirs(train_dir, exist_ok=True)
os.makedirs(test_dir, exist_ok=True)

# Create mock training data file
train_data = {
    'x': np.random.rand(2, 4).tolist(),
    'y': [0, 1]
}
train_file = os.path.join(train_dir, '0.npz')
np.savez(train_file, data=train_data)

# Create mock test data file
test_data = {
    'x': np.random.rand(2, 4).tolist(),
    'y': [1, 0]
}
test_file = os.path.join(test_dir, '0.npz')
np.savez(test_file, data=test_data)

# Change to temp directory so relative paths work
original_cwd = os.getcwd()
os.chdir(temp_dir)

ARGS = {
    'dataset': 'test_dataset',
    '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_Shakespeare Ran
ran on a synthesized input
TsingZ0/FedKTL/system/flcore/servers/serverktl_stylegan_3.py
code served (permissive licence) · get_code("a741dc4e721c56c6")
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
from unittest.mock import patch, MagicMock

torch.manual_seed(0)

# Create temporary directory structure and mock files
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 sample train data
train_data = {
    'x': [[1, 2, 3, 4], [5, 6, 7, 8]],
    'y': [0, 1]
}
train_file = os.path.join(train_dir, '0.npz')
np.savez(train_file, data=train_data)

# Create sample test data
test_data = {
    'x': [[9, 10, 11, 12], [13, 14, 15, 16]],
    '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 args and args[0] == '../dataset':
        return original_join(temp_dir, 'dataset', *args[1:])
    return original_join(*args)

# Apply the patch globally for the function execution
import builtins
_original_open = builtins.open

def mock_open_wrapper(file, *args, **kwargs):
    return _original_open(file, *args, **kwargs)

with patch('os.path.join', side_effect=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/FedKTL/system/flcore/servers/serverktl_stylegan_3.py
code served (permissive licence) · get_code("fd69af949887cea7")
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 numpy as np
import torch
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
BaseHeadSplit Not yet run
unverified (harvested, no recorded run)
TsingZ0/FedKTL/system/flcore/servers/serverktl_stylegan_3.py
code served (permissive licence) · get_code("c93d596514b9ca52")
How it ran

no invocation recorded.

Client Not yet run
unverified (harvested, no recorded run)
TsingZ0/FedKTL/system/flcore/servers/serverktl_stylegan_3.py
code served (permissive licence) · get_code("f2e3ea1cfc9c8a5d")
How it ran

no invocation recorded.

FedKTL Not yet run
unverified (harvested, no recorded run)
TsingZ0/FedKTL/system/flcore/servers/serverktl_stylegan_3.py
code served (permissive licence) · get_code("9ba786e9c49315cc")
How it ran

no invocation recorded.

Server Not yet run
unverified (harvested, no recorded run)
TsingZ0/FedKTL/system/flcore/servers/serverktl_stylegan_3.py
code served (permissive licence) · get_code("995784bb2619aade")
How it ran

no invocation recorded.

clientKTL Not yet run
unverified (harvested, no recorded run)
TsingZ0/FedKTL/system/flcore/servers/serverktl_stylegan_3.py
code served (permissive licence) · get_code("1afe923e67a729c7")
How it ran

no invocation recorded.

read_data Not yet run
unverified (harvested, no recorded run)
TsingZ0/FedKTL/system/flcore/servers/serverktl_stylegan_3.py
code served (permissive licence) · get_code("2e468f03b54c3418")
How it ran

no invocation recorded.

save_item Not yet run
unverified (harvested, no recorded run)
TsingZ0/FedKTL/system/flcore/servers/serverktl_stylegan_3.py
code served (permissive licence) · get_code("7da90aab3cbb2186")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 12 are also present in other papers whose code we hold (12 with at least one paper dated earlier, 0 the same month, 5 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
read_client_data_text
brick of this paper's assembly: helper
8 other papers
6 dated earlier, 2 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
4 dated earlier, 1 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
2311.14975 (2023-11)
Eliminating Domain Bias for Federated Learning in Representation Space
and 2 more not named here
read_data
brick of this paper's assembly: helper
5 other papers
4 dated earlier, 1 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
2311.14975 (2023-11)
Eliminating Domain Bias for Federated Learning in Representation Space
and 2 more not named here
read_client_data_Shakespeare
brick of this paper's assembly: helper
4 other papers
3 dated earlier, 1 later · 2 only as an assembly brick
2308.10279 (2023-08)
GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning
2311.14975 (2023-11)
Eliminating Domain Bias for Federated Learning in Representation Space
2401.03230 (2024-01)
FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning
and 1 more not named here
load_item
brick of this paper's assembly: helper
3 other papers
3 dated earlier · 1 only as an assembly brick
2209.10083 (2022-09)
Federated Learning from Pre-Trained Models: A Contrastive Learning Approach
2312.04992 (2023-12)
PFLlib: A Beginner-Friendly and Comprehensive Personalized Federated Learning Library and Benchmark
2401.03230 (2024-01)
FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning
agg_func
brick of this paper's assembly: helper
2 other papers
2 dated earlier
2209.10083 (2022-09)
Federated Learning from Pre-Trained Models: A Contrastive Learning Approach
2312.04992 (2023-12)
PFLlib: A Beginner-Friendly and Comprehensive Personalized Federated Learning Library and Benchmark
save_item
brick of this paper's assembly: helper
2 other papers
1 dated earlier, 1 later · 2 only as an assembly brick
2401.03230 (2024-01)
FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning
2607.26801 (2026-07)
FedTopo: Relation-Level Topology Sharing for Model-Heterogeneous Federated Learning
Client
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2401.03230 (2024-01)
FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning
MMD
brick of this paper's assembly: loss
1 other paper
1 dated earlier
2307.01217 (2023-07)
FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy
Server
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2401.03230 (2024-01)
FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning
alexnet 1 other paper
1 dated earlier
2311.14975 (2023-11)
Eliminating Domain Bias for Federated Learning in Representation Space
mobilenet_v2 1 other paper
1 dated earlier
2311.14975 (2023-11)
Eliminating Domain Bias for Federated Learning in Representation Space

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

Heterogeneous Federated Learning (HtFL) enables collaborative learning on multiple clients with different model architectures while preserving privacy. Despite recent research progress, knowledge sharing in HtFL is still difficult due to data and model heterogeneity. To tackle this issue, we leverage the knowledge stored in public pre-trained generators and propose a new upload-efficient knowledge transfer scheme called Federated Knowledge-Transfer Loop (Fed-KTL). Our FedKTL can produce client-task-related prototypical image-vector pairs via the generator's inference on the server. With these pairs, each client can transfer preexisting knowledge from the generator to its local model through an additional supervised local task. We conduct extensive experiments on four datasets under two types of data heterogeneity with 14 kinds of models including CNNs and ViTs. Results show that our upload-efficient FedKTL surpasses seven state-of-the-art methods by up to 7.31% in accuracy. Moreover, our knowledge transfer scheme is applicable in scenarios with only one edge client. Code: https://github.com/TsingZ0/FedKTL

For agents

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

get_harvested_code_for_paper("2403.15760")
get_code_for_paper("2403.15760")
have("2403.15760")

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

curl https://syntology.ai/api/ran/2403.15760.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.15760.svg)](https://syntology.ai/paper/2403.15760)

Connect an agent — have() is free.