SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.13170 · 2022

AdaBest: Minimizing Client Drift in Federated Learning via Adaptive Bias Estimation

arXiv · PDF · Open in the Atlas

Code that ran

4 of 8 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 4 have no contract verdict; 0 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/2204.13170.json · badge: /api/ran/2204.13170.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
fedsim-dev/fedsim community (classifier label)
classifier basis not recorded on the link
4 ran · 4 no recorded run
FunctionStatusWhere it lives
decode_margs Ran
ran on a synthesized input
fedsim-dev/fedsim/fedsim_cli/utils.py
code served (permissive licence) · get_code("58c0bf63e2ddbd44")
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 numpy as np
from typing import OrderedDict, Tuple
import yaml

torch.manual_seed(0)

# Test case 1: Simple single-element tuple (concatenates to form obj name)
obj_and_args_1 = (["MyObject"],)

# Test case 2: Multi-element tuple with object name and arguments with YAML values
obj_and_args_2 = ("ObjectName", "param1:42", "param2:hello", "param3:[1, 2, 3]")

# Test case 3: Multi-element tuple with arguments containing colon with type constructors
obj_and_args_3 = ("MyClass", "size:range:5", "values:list:1-2-3")

# Test case 4: None value
obj_and_args_4 = None

# Test case 5: Single-char elements that get concatenated
obj_and_args_5 = (["A"], ["B"], ["C"])

# Test case 6: Complex mix with dict and list arguments
obj_and_args_6 = ("TestObj", "config:{a: 1, b: 2}", "threshold:0.5")

ARGS = {
    "obj_and_args": obj_and_args_2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, yaml — 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_from_module Ran
ran on a synthesized input
fedsim-dev/fedsim/fedsim/utils/import_utils.py
code served (permissive licence) · get_code("54264fda6cbab53b")
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 builtin_function_or_method. 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 importlib

ARGS = {
    "module_name": "math",
    "entry_name": "sqrt"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type builtin_function_or_method — a builtin_function_or_method output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a builtin_function_or_method 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
parse_class_from_file Ran
ran on a synthesized input
fedsim-dev/fedsim/fedsim_cli/utils.py
code served (permissive licence) · get_code("1bf7169a354cb416")
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 type. 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 importlib.util
import os
import tempfile

# Create a temporary module file for testing
temp_dir = tempfile.mkdtemp()
test_module_path = os.path.join(temp_dir, 'test_module.py')

# Write a simple test module with a class
with open(test_module_path, 'w') as f:
    f.write("""
class TestClass:
    def __init__(self):
        self.value = 42
""")

# Prepare the argument: format is "module_file:ClassName"
# The function expects "f:c" where f is the file path (without .py) and c is the class name
module_file = test_module_path[:-3]  # Remove .py extension
class_name = "TestClass"
s = f"{module_file}:{class_name}"

ARGS = {
    "s": s
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type type — a type output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a type 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
vector_to_parameters_like Ran
ran on a synthesized input
fedsim-dev/fedsim/fedsim/utils/convert_parameters.py
code served (permissive licence) · get_code("14e4f93102251ddc")
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

torch.manual_seed(0)

# Create a vector that represents flattened parameters
vec = torch.randn(10)

# Create some parameter-like tensors with different shapes
# to use as a template for reshaping
param1 = torch.randn(2, 3)
param2 = torch.randn(4)

parameters_like = [param1, param2]

ARGS = {
    "vec": vec,
    "parameters_like": parameters_like,
}
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 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
apply_on_dict Not yet run
unverified (harvested, no recorded run)
fedsim-dev/fedsim/fedsim/utils/dict_ops.py
code served (permissive licence) · get_code("80be16d191c0ad4e")
How it ran

no invocation recorded.

get_output_size Not yet run
unverified (harvested, no recorded run)
fedsim-dev/fedsim/fedsim/models/utils.py
code served (permissive licence) · get_code("d04382d1c4b70279")
How it ran

no invocation recorded.

vector_to_named_parameters_like Not yet run
unverified (harvested, no recorded run)
fedsim-dev/fedsim/fedsim/utils/convert_parameters.py
code served (permissive licence) · get_code("74963996d8900867")
How it ran

no invocation recorded.

vectorize_module Not yet run
unverified (harvested, no recorded run)
fedsim-dev/fedsim/fedsim/utils/convert_parameters.py
code served (permissive licence) · get_code("81fde0e6751c67a5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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.

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

In Federated Learning (FL), a number of clients or devices collaborate to train a model without sharing their data. Models are optimized locally at each client and further communicated to a central hub for aggregation. While FL is an appealing decentralized training paradigm, heterogeneity among data from different clients can cause the local optimization to drift away from the global objective. In order to estimate and therefore remove this drift, variance reduction techniques have been incorporated into FL optimization recently. However, these approaches inaccurately estimate the clients' drift and ultimately fail to remove it properly. In this work, we propose an adaptive algorithm that accurately estimates drift across clients. In comparison to previous works, our approach necessitates less storage and communication bandwidth, as well as lower compute costs. Additionally, our proposed methodology induces stability by constraining the norm of estimates for client drift, making it more practical for large scale FL. Experimental findings demonstrate that the proposed algorithm converges significantly faster and achieves higher accuracy than the baselines across various FL benchmarks.

For agents

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

get_harvested_code_for_paper("2204.13170")
get_code_for_paper("2204.13170")
have("2204.13170")

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

curl https://syntology.ai/api/ran/2204.13170.json

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

[![Syntology run record](https://syntology.ai/api/ran/2204.13170.svg)](https://syntology.ai/paper/2204.13170)

Connect an agent — have() is free.