SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2111.04263 · ICLR · 2021

Federated Learning Based on Dynamic Regularization

Matthew Mattina, Yue Zhao, Durmus Alp, Emre Acar, Ramon Navarro, Paul Whatmough

arXiv · PDF · Open in the Atlas

Code that ran

6 of 15 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 1 failure of our instrument; 9 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/2111.04263.json · badge: /api/ran/2111.04263.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
thejungwon/gc-fed community
Papers with Code archive
4 ran · 5 no recorded run
TsingZ0/PFL-Non-IID community
Papers with Code archive
1 ran · 3 no recorded run
NAVER-INTEL-Co-Lab/gaudi-byzantine community
Papers with Code archive
1 ran · 0 no recorded run
alpemreacar/FedDyn marked official in Papers with Code
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
CNN Ran
ran on a synthesized input · constructed an object; no result was computed
thejungwon/gc-fed/algorithms/gcfed.py
pointer only (licence: NONE) · get_code("cff80b8ecb8c8c99")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thejungwon/gc-fed 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.

MLP Ran
ran on a synthesized input · constructed an object; no result was computed
thejungwon/gc-fed/algorithms/gcfed.py
pointer only (licence: NONE) · get_code("acd09ebeda2c9bc6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thejungwon/gc-fed 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.

ResNet18 Ran
ran on a synthesized input · constructed an object; no result was computed
thejungwon/gc-fed/algorithms/gcfed.py
pointer only (licence: NONE) · get_code("ce17439507a51476")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thejungwon/gc-fed 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.

VGG11 Ran
ran on a synthesized input · constructed an object; no result was computed
thejungwon/gc-fed/algorithms/gcfed.py
pointer only (licence: NONE) · get_code("f0aeb868a782b3d7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thejungwon/gc-fed 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.

model_parameter_vector Ran
ran, honoured the contract we drafted
TsingZ0/PFL-Non-IID/system/flcore/servers/serverdyn.py
code served (permissive licence) · get_code("1f7693bbd3b8865f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 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

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()

ARGS = {
    "model": model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 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
server_dyn Ran
ran; our contract draft was wrong, not the code
NAVER-INTEL-Co-Lab/gaudi-byzantine/src/aggregation.py
code served (permissive licence) · get_code("a0b65033d450bccb")
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 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 copy

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

class Args:
    def __init__(self):
        self.device = 'cpu'
        self.mu = 0.01

# Create global model
global_model = SimpleModel()

# Create local model weights (state dicts)
w_locals = []
for _ in range(2):
    w_locals.append(copy.deepcopy(global_model.state_dict()))
    # Slightly perturb the weights
    for k in w_locals[-1].keys():
        w_locals[-1][k] = w_locals[-1][k] + torch.randn_like(w_locals[-1][k]) * 0.01

# Create index users
idx_users = [0, 1]

# Create controls dict (initially empty, will be populated by function)
controls = {}

# Create sorted_idxs (can be empty or contain user indices)
sorted_idxs = [0, 1]

ARGS = {
    'args': Args(),
    'global_model': global_model,
    'w_locals': w_locals,
    'idx_users': idx_users,
    'controls': controls,
    'sorted_idxs': sorted_idxs
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type 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
FedDyn Not yet run
unverified (harvested, no recorded run)
TsingZ0/PFL-Non-IID/system/flcore/servers/serverdyn.py
code served (permissive licence) · get_code("a327f364bcb74163")
How it ran

no invocation recorded.

GCFedClient Not yet run
unverified (harvested, no recorded run)
thejungwon/gc-fed/algorithms/gcfed.py
pointer only (licence: NONE) · get_code("70803d2f07b42d4a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thejungwon/gc-fed 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. No invocation recorded.

Server Not yet run
unverified (harvested, no recorded run)
TsingZ0/PFL-Non-IID/system/flcore/servers/serverdyn.py
code served (permissive licence) · get_code("0a6af52fc93a95a1")
How it ran

no invocation recorded.

clientDyn Not yet run
unverified (harvested, no recorded run)
TsingZ0/PFL-Non-IID/system/flcore/servers/serverdyn.py
code served (permissive licence) · get_code("16480f2cf0b819dd")
How it ran

no invocation recorded.

get_model Not yet run
unverified (harvested, no recorded run)
thejungwon/gc-fed/algorithms/gcfed.py
pointer only (licence: NONE) · get_code("021173b9b0b6da38")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thejungwon/gc-fed 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. No invocation recorded.

init_weights Not yet run
unverified (harvested, no recorded run)
thejungwon/gc-fed/algorithms/gcfed.py
pointer only (licence: NONE) · get_code("39c6548f5ca70964")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thejungwon/gc-fed 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. No invocation recorded.

log_info Not yet run
unverified (harvested, no recorded run)
thejungwon/gc-fed/algorithms/gcfed.py
pointer only (licence: NONE) · get_code("a2a34e406dfeba02")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thejungwon/gc-fed 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. No invocation recorded.

set_random_seed Not yet run
unverified (harvested, no recorded run)
thejungwon/gc-fed/algorithms/gcfed.py
pointer only (licence: NONE) · get_code("c08e488e6cf86c88")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thejungwon/gc-fed 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. No invocation recorded.

train_FedDyn Not yet run
unverified (harvested, no recorded run)
alpemreacar/FedDyn/utils_methods.py
code served (permissive licence) · get_code("d8e5236ae622abdc")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 0 the same month, 9 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
Server
brick of this paper's assembly: helper
4 other papers
3 dated earlier, 1 later
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 1 more not named here
CNN
brick of this paper's assembly: helper
3 other papers
2 dated earlier, 1 later · 3 only as an assembly brick
1602.05629 (2016-02)
Communication-Efficient Learning of Deep Networks from Decentralized Data
2106.03097 (2021-06)
Preservation of the Global Knowledge by Not-True Distillation in Federated Learning
2209.00189 (2022-09)
Federated Learning with Label Distribution Skew via Logits Calibration
MLP
brick of this paper's assembly: helper
3 other papers
2 dated earlier, 1 later · 3 only as an assembly brick
1602.05629 (2016-02)
Communication-Efficient Learning of Deep Networks from Decentralized Data
2106.03097 (2021-06)
Preservation of the Global Knowledge by Not-True Distillation in Federated Learning
2209.00189 (2022-09)
Federated Learning with Label Distribution Skew via Logits Calibration
ResNet18
brick of this paper's assembly: helper
3 other papers
2 dated earlier, 1 later · 3 only as an assembly brick
1602.05629 (2016-02)
Communication-Efficient Learning of Deep Networks from Decentralized Data
2106.03097 (2021-06)
Preservation of the Global Knowledge by Not-True Distillation in Federated Learning
2209.00189 (2022-09)
Federated Learning with Label Distribution Skew via Logits Calibration
VGG11
brick of this paper's assembly: helper
3 other papers
2 dated earlier, 1 later · 3 only as an assembly brick
1602.05629 (2016-02)
Communication-Efficient Learning of Deep Networks from Decentralized Data
2106.03097 (2021-06)
Preservation of the Global Knowledge by Not-True Distillation in Federated Learning
2209.00189 (2022-09)
Federated Learning with Label Distribution Skew via Logits Calibration
get_model
brick of this paper's assembly: model
3 other papers
2 dated earlier, 1 later · 3 only as an assembly brick
1602.05629 (2016-02)
Communication-Efficient Learning of Deep Networks from Decentralized Data
2106.03097 (2021-06)
Preservation of the Global Knowledge by Not-True Distillation in Federated Learning
2209.00189 (2022-09)
Federated Learning with Label Distribution Skew via Logits Calibration
init_weights
brick of this paper's assembly: helper
3 other papers
2 dated earlier, 1 later · 3 only as an assembly brick
1602.05629 (2016-02)
Communication-Efficient Learning of Deep Networks from Decentralized Data
2106.03097 (2021-06)
Preservation of the Global Knowledge by Not-True Distillation in Federated Learning
2209.00189 (2022-09)
Federated Learning with Label Distribution Skew via Logits Calibration
log_info
brick of this paper's assembly: helper
3 other papers
2 dated earlier, 1 later · 3 only as an assembly brick
1602.05629 (2016-02)
Communication-Efficient Learning of Deep Networks from Decentralized Data
2106.03097 (2021-06)
Preservation of the Global Knowledge by Not-True Distillation in Federated Learning
2209.00189 (2022-09)
Federated Learning with Label Distribution Skew via Logits Calibration
set_random_seed
brick of this paper's assembly: helper
3 other papers
2 dated earlier, 1 later · 2 only as an assembly brick
1602.05629 (2016-02)
Communication-Efficient Learning of Deep Networks from Decentralized Data
2106.03097 (2021-06)
Preservation of the Global Knowledge by Not-True Distillation in Federated Learning
2209.00189 (2022-09)
Federated Learning with Label Distribution Skew via Logits Calibration

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

We propose a novel federated learning method for distributively training neural network models, where the server orchestrates cooperation between a subset of randomly chosen devices in each round. We view Federated Learning problem primarily from a communication perspective and allow more device level computations to save transmission costs. We point out a fundamental dilemma, in that the minima of the local-device level empirical loss are inconsistent with those of the global empirical loss. Different from recent prior works, that either attempt inexact minimization or utilize devices for parallelizing gradient computation, we propose a dynamic regularizer for each device at each round, so that in the limit the global and device solutions are aligned. We demonstrate both through empirical results on real and synthetic data as well as analytical results that our scheme leads to efficient training, in both convex and non-convex settings, while being fully agnostic to device heterogeneity and robust to large number of devices, partial participation and unbalanced data.

For agents

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

get_harvested_code_for_paper("2111.04263")
get_code_for_paper("2111.04263")
have("2111.04263")

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

curl https://syntology.ai/api/ran/2111.04263.json

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

[![Syntology run record](https://syntology.ai/api/ran/2111.04263.svg)](https://syntology.ai/paper/2111.04263)

Connect an agent — have() is free.