SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.01068 · 2023

FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations

arXiv · PDF · Open in the Atlas

Code that ran

14 of 21 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; 0 honoured the contract we drafted, 0 violated it and 10 have no contract verdict; 4 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/2302.01068.json · badge: /api/ran/2302.01068.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
a514514772/fedlap-dp community (classifier label)
classifier basis not recorded on the link
14 ran · 7 no recorded run
FunctionStatusWhere it lives
VGG11 Ran
ran; our contract draft was wrong, not the code
a514514772/fedlap-dp/utils/networks.py
pointer only (licence: MIT); the stored copy get_code serves, from ndhg1213/CMIDD, is pointer only (licence: NONE) · get_code("8e1b179ef1f0fe03")
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 ndhg1213/CMIDD, 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.

VGG11BN Ran
ran; our contract draft was wrong, not the code
a514514772/fedlap-dp/utils/networks.py
pointer only (licence: MIT); the stored copy get_code serves, from ndhg1213/CMIDD, is pointer only (licence: NONE) · get_code("cfab0fafbf988aa4")
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 ndhg1213/CMIDD, 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.

VGG13 Ran
ran; our contract draft was wrong, not the code
a514514772/fedlap-dp/utils/networks.py
pointer only (licence: MIT); the stored copy get_code serves, from ndhg1213/CMIDD, is pointer only (licence: NONE) · get_code("07962bf28fe347a0")
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 ndhg1213/CMIDD, 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.

accumulate_grads Ran
ran on a synthesized input
a514514772/fedlap-dp/utils/analysis.py
code served (permissive licence) · get_code("5a7f510dabadb84b")
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 ndarray, ndim 1, dtype family float, shape (23,) 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

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

# Create a simple forward pass and compute gradients
x = torch.randn(2, 4)
y = torch.randn(2, 2)
loss_fn = nn.MSELoss()

output = model(x)
loss = loss_fn(output, y)
loss.backward()

ARGS = {
    "model": model
}
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 ndarray, ndim 1, dtype family float, shape (23,) — shape (23,) 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
augment Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
a514514772/fedlap-dp/utils/augmentation.py
code served (permissive licence) · get_code("4ac684d789a25255")
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 4, dtype family float, shape (2, 3, 4, 5) 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 numpy as np

torch.manual_seed(0)
np.random.seed(0)

# Create a small batch of images: batch_size=2, channels=3, height=4, width=5
images = torch.randn(2, 3, 4, 5, dtype=torch.float)

# Create augmentation parameters dict with all required keys
dc_aug_param = {
    'strategy': 'crop_scale_rotate_noise',
    'scale': 0.1,
    'crop': 2,
    'rotate': 15,
    'noise': 0.01
}

device = 'cpu'

ARGS = {
    'images': images,
    'dc_aug_param': dc_aug_param,
    'device': device
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 3, 4, 5) — shape (2, 3, 4, 5) 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
compute_model_diff Ran
ran on a synthesized input
a514514772/fedlap-dp/utils/utils.py
code served (permissive licence) · get_code("06b378b3395f19b6")
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 ndarray, 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)

# Create a small neural network model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

# Create two model instances
m_new = SimpleModel()
m_old = SimpleModel()

# Modify m_new slightly so they have different weights
with torch.no_grad():
    for param in m_new.parameters():
        param.add_(0.1)

ARGS = {
    "m_new": m_new,
    "m_old": m_old,
}
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 ndarray, 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
compute_model_distance Ran
ran on a synthesized input
a514514772/fedlap-dp/utils/fl_utils.py
code served (permissive licence) · get_code("464e8a98f11cf468")
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

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self, input_size=4, hidden_size=3, output_size=2):
        super().__init__()
        self.linear1 = nn.Linear(input_size, hidden_size)
        self.linear2 = nn.Linear(hidden_size, output_size)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

m1 = SimpleModel(input_size=4, hidden_size=3, output_size=2)
m2 = SimpleModel(input_size=4, hidden_size=3, output_size=2)

ARGS = {
    "m1": m1,
    "m2": m2,
}
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
create_server_opt Ran
ran on a synthesized input
a514514772/fedlap-dp/main_baseline.py
code served (permissive licence) · get_code("3dd0838c983f6de8")
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
import torch.optim as optim

torch.manual_seed(0)

class SimpleNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

class ArgsConfig:
    def __init__(self, optimization, lr_net):
        self.optimization = optimization
        self.lr_net = lr_net

subnet_server = SimpleNet()
args = ArgsConfig(optimization='fedadam', lr_net=0.001)

ARGS = {
    'subnet_server': subnet_server,
    'args': args
}
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
distance_wb Ran
ran on a synthesized input
a514514772/fedlap-dp/utils/ops.py
code served (permissive licence) · get_code("05e4679ed899a619")
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)

# The function takes two gradient tensors and computes a weighted distance metric
# It handles tensors of shapes: 4D, 3D, 2D, or 1D
# Let's create valid arguments for each dimension case

# Create a 4D tensor (batch_size=2, channels=3, height=4, width=5)
gwr_4d = torch.randn(2, 3, 4, 5)
gws_4d = torch.randn(2, 3, 4, 5)

# Create a 3D tensor (batch_size=2, seq_len=4, features=5)
gwr_3d = torch.randn(2, 4, 5)
gws_3d = torch.randn(2, 4, 5)

# Create a 2D tensor (batch_size=2, features=5)
gwr_2d = torch.randn(2, 5)
gws_2d = torch.randn(2, 5)

# Create a 1D tensor (features=5)
gwr_1d = torch.randn(5)
gws_1d = torch.randn(5)

# Use 4D tensors as the main test case
ARGS = {
    "gwr": gwr_4d,
    "gws": gws_4d,
}
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
epoch Ran
ran on a synthesized input
a514514772/fedlap-dp/utils/ops.py
code served (permissive licence) · get_code("68185a4f54101d97")
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, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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)

# Define a minimal network that works with the function
class MinimalNet(nn.Module):
    def __init__(self, num_classes=3):
        super().__init__()
        self.linear = nn.Linear(4, num_classes)
    
    def forward(self, x):
        # x shape: (batch_size, 4)
        return self.linear(x)

# Define minimal augmentation function stubs
def DiffAugment(img, strategy, param=None):
    return img

def augment(img, dc_aug_param, device):
    return img

# Define minimal args object
class Args:
    def __init__(self):
        self.device = 'cpu'
        self.dsa = False
        self.dsa_strategy = None
        self.dsa_param = None
        self.dc_aug_param = None

# Create dataloader: list of (image, label) tuples
# Batch size 2, image dim 4, 3 classes
dataloader = [
    (torch.randn(2, 4), torch.tensor([0, 1])),
    (torch.randn(2, 4), torch.tensor([2, 0])),
]

# Create network
net = MinimalNet(num_classes=3)

# Create optimizer
optimizer = torch.optim.SGD(net.parameters(), lr=0.01)

# Create criterion
criterion = nn.CrossEntropyLoss()

# Create args
args = Args()

# Build ARGS dict
ARGS = {
    'mode': 'train',
    'dataloader': dataloader,
    'net': net,
    'optimizer': optimizer,
    'criterion': criterion,
    'args': args,
    'aug': False,
}
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, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
get_global_opt Ran
ran on a synthesized input
a514514772/fedlap-dp/utils/analysis.py
code served (permissive licence) · get_code("7840c088ad8dbbbb")
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 Adam. 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 torch.optim as optim

torch.manual_seed(0)

class SimpleNet(nn.Module):
    def __init__(self):
        super(SimpleNet, self).__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

class Args:
    def __init__(self, optimization, lr_net):
        self.optimization = optimization
        self.lr_net = lr_net

net = SimpleNet()

ARGS = {
    'args': Args(optimization='fedadam', lr_net=0.001),
    'net': net
}
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 Adam — a Adam output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Adam 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
get_privacy_spent Ran
ran on a synthesized input
a514514772/fedlap-dp/RDP_record_level.py
code served (permissive licence) · get_code("2a4aad919ee70e6f")
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, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

# Construct valid arguments for get_privacy_spent
ARGS = {
    "orders": [1.5, 2.0, 3.0, 5.0],
    "rdp": [0.5, 0.8, 1.2, 1.8],
    "delta": 1e-5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
match_loss Ran
ran on a synthesized input
a514514772/fedlap-dp/utils/ops.py
code served (permissive licence) · get_code("b6b7ca954109fa0e")
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
import torch.nn as nn

torch.manual_seed(0)

# Create small gradient weight tensors for synthetic and real models
# Using distinct sizes: 4x3, 3x2, 5 to make shapes unambiguous
gw_syn = [
    torch.randn(4, 3),           # 2D tensor
    torch.randn(3, 2, 2),        # 3D tensor
    torch.randn(2, 2, 2, 2),     # 4D tensor
]

gw_real = [
    torch.randn(4, 3),           # 2D tensor
    torch.randn(3, 2, 2),        # 3D tensor
    torch.randn(2, 2, 2, 2),     # 4D tensor
]

# Build a minimal logger class with add_value method
class MinimalLogger:
    def add_value(self, key, value):
        pass

# Build args object with required attributes and dict functionality
class ArgsObject(dict):
    def __init__(self, *args, **kwargs):
        super().__init__(*args, **kwargs)
        self.device = torch.device('cpu')
        self.dis_metric = 'gm'
        self.logger = MinimalLogger()
    
    def __getattr__(self, name):
        try:
            return self[name]
        except KeyError:
            raise AttributeError(name)
    
    def __setattr__(self, name, value):
        if name in ('device', 'dis_metric', 'logger'):
            super().__setattr__(name, value)
        else:
            self[name] = value

args = ArgsObject()
args['tmp_buffer'] = {'id_client': 0}

ARGS = {
    'gw_syn': gw_syn,
    'gw_real': gw_real,
    'args': args,
    'dis_metric': 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 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
rand_scale Ran
ran on a synthesized input
a514514772/fedlap-dp/utils/augmentation.py
code served (permissive licence) · get_code("a7a3291ababdea1f")
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 4, dtype family float, shape (2, 3, 4, 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 torch.nn.functional as F

torch.manual_seed(0)

class ParamConfig:
    def __init__(self):
        self.latestseed = 0
        self.ratio_scale = 1.5
        self.batchmode = False

# Create a small batch tensor: batch_size=2, channels=3, height=4, width=4
x = torch.randn(2, 3, 4, 4)

# Create param object with required attributes
param = ParamConfig()

ARGS = {
    'x': x,
    'param': param
}
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 4, dtype family float, shape (2, 3, 4, 4) — shape (2, 3, 4, 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
DiffAugment Not yet run
unverified (harvested, no recorded run)
a514514772/fedlap-dp/utils/augmentation.py
code served (permissive licence) · get_code("6e636dbbdcaa0f16")
How it ran

no invocation recorded.

compute_epsilon Not yet run
unverified (harvested, no recorded run)
a514514772/fedlap-dp/RDP_record_level.py
code served (permissive licence) · get_code("dc4735db69f56c6c")
How it ran

no invocation recorded.

compute_epsilon Not yet run
unverified (harvested, no recorded run)
a514514772/fedlap-dp/rdp_accountant.py
code served (permissive licence) · get_code("9e86773fdea3d6c0")
How it ran

no invocation recorded.

compute_rdp Not yet run
unverified (harvested, no recorded run)
a514514772/fedlap-dp/RDP_record_level.py
code served (permissive licence) · get_code("9bc608b2340472d0")
How it ran

no invocation recorded.

get_dataset Not yet run
unverified (harvested, no recorded run)
a514514772/fedlap-dp/utils/misc.py
code served (permissive licence) · get_code("5211c024ed09fb69")
How it ran

no invocation recorded.

get_network Not yet run
unverified (harvested, no recorded run)
a514514772/fedlap-dp/utils/misc.py
code served (permissive licence) · get_code("9559a2ae8eb12814")
How it ran

no invocation recorded.

prepare_data Not yet run
unverified (harvested, no recorded run)
a514514772/fedlap-dp/utils/misc.py
code served (permissive licence) · get_code("247505620d52f110")
How it ran

no invocation recorded.

Also present in other papers' code

Of 21 samples lifted from this paper's linked repositories, 21 carry a function identity and 0 do not. Of the 21 distinct functions with an identity, 10 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 0 the same month, 3 later) and 11 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
VGG11BN 28 other papers
5 dated earlier, 23 later
2203.01531 (2022-03)
CAFE: Learning to Condense Dataset by Aligning Features
2204.07513 (2022-04)
Synthesizing Informative Training Samples with GAN
2210.16774 (2022-10)
Dataset Distillation via Factorization
and 25 more not named here
VGG11 27 other papers
5 dated earlier, 22 later
2203.01531 (2022-03)
CAFE: Learning to Condense Dataset by Aligning Features
2204.07513 (2022-04)
Synthesizing Informative Training Samples with GAN
2210.16774 (2022-10)
Dataset Distillation via Factorization
and 24 more not named here
VGG13 19 other papers
4 dated earlier, 15 later
2204.07513 (2022-04)
Synthesizing Informative Training Samples with GAN
2210.16774 (2022-10)
Dataset Distillation via Factorization
2211.04446 (2022-11)
Private Set Generation with Discriminative Information
and 16 more not named here
augment 2 other papers
2 dated earlier
2203.01531 (2022-03)
CAFE: Learning to Condense Dataset by Aligning Features
2211.04446 (2022-11)
Private Set Generation with Discriminative Information
compute_epsilon 1 other paper
1 dated earlier
2211.04446 (2022-11)
Private Set Generation with Discriminative Information
compute_rdp 1 other paper
1 dated earlier
2211.04446 (2022-11)
Private Set Generation with Discriminative Information
epoch 1 other paper
1 dated earlier
2211.04446 (2022-11)
Private Set Generation with Discriminative Information
get_dataset 1 other paper
1 dated earlier
2211.04446 (2022-11)
Private Set Generation with Discriminative Information
get_network 1 other paper
1 dated earlier
2211.04446 (2022-11)
Private Set Generation with Discriminative Information
get_privacy_spent 1 other paper
1 dated earlier
2211.04446 (2022-11)
Private Set Generation with Discriminative Information

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

Conventional gradient-sharing approaches for federated learning (FL), such as FedAvg, rely on aggregation of local models and often face performance degradation under differential privacy (DP) mechanisms or data heterogeneity, which can be attributed to the inconsistency between the local and global objectives. To address this issue, we propose FedLAP-DP, a novel privacy-preserving approach for FL. Our formulation involves clients synthesizing a small set of samples that approximate local loss landscapes by simulating the gradients of real images within a local region. Acting as loss surrogates, these synthetic samples are aggregated on the server side to uncover the global loss landscape and enable global optimization. Building upon these insights, we offer a new perspective to enforce record-level differential privacy in FL. A formal privacy analysis demonstrates that FedLAP-DP incurs the same privacy costs as typical gradient-sharing schemes while achieving an improved trade-off between privacy and utility. Extensive experiments validate the superiority of our approach across various datasets with highly skewed distributions in both DP and non-DP settings. Beyond the promising performance, our approach presents a faster convergence speed compared to typical gradient-sharing methods and opens up the possibility of trading communication costs for better performance by sending a larger set of synthetic images. The source is available at \url{https://github.com/hui-po-wang/FedLAP-DP}.

For agents

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

get_harvested_code_for_paper("2302.01068")
get_code_for_paper("2302.01068")
have("2302.01068")

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

curl https://syntology.ai/api/ran/2302.01068.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.01068.svg)](https://syntology.ai/paper/2302.01068)

Connect an agent — have() is free.