SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.08435 · 2021

Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning

arXiv · PDF · Open in the Atlas

Code that ran

9 of 10 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; 1 honoured the contract we drafted, 1 violated it and 6 have no contract verdict; 1 failure of our instrument; 1 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/2108.08435.json · badge: /api/ran/2108.08435.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
cuis15/FCFL canonical (classifier label)
classifier basis: census
9 ran · 1 no recorded run
FunctionStatusWhere it lives
concave_fun_eval Ran
ran on a synthesized input
cuis15/FCFL/FUEL/synthetic/utils.py
code served (permissive licence) · get_code("a03246af7c71643d")
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. 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 autograd.numpy as np
from autograd import grad

# Set seed for reproducibility
np.random.seed(0)

# Create a small test vector
x = np.array([0.1, 0.2, 0.3, 0.15], dtype=np.float64)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
autograd — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple 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
construct_log Ran
ran on a synthesized input
cuis15/FCFL/FUEL/utils.py
code served (permissive licence) · get_code("f9bb42bc79562af5")
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 Logger. 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 os
import logging
import tempfile

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

# Create a simple args object with the required attributes
class Args:
    def __init__(self):
        self.log_dir = temp_dir
        self.log_name = "test.log"

args = Args()

ARGS = {
    "args": args
}
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
f1 Ran
ran on a synthesized input
cuis15/FCFL/FUEL/synthetic/utils.py
code served (permissive licence) · get_code("63aab5e7619728e3")
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 float64, ndim 0, 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 autograd.numpy as np

def f1(x):
    n = len(x)
    dx = np.linalg.norm(x - 1.0 / np.sqrt(n))
    return 1 - np.exp(-dx ** 2)

# Create a small array for x
x = np.array([0.5, 0.3, 0.7, 0.2])

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
autograd — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
f2 Ran
ran on a synthesized input
cuis15/FCFL/FUEL/synthetic/utils.py
code served (permissive licence) · get_code("8bdf4363c98a9708")
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 float64, ndim 0, 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 autograd.numpy as np

def f2(x):
    n = len(x)
    dx = np.linalg.norm(x + 1.0 / np.sqrt(n))
    return 1 - np.exp(-dx ** 2)

# Create a small array argument for x
x = np.array([1.0, 2.0, 3.0, 4.0])

ARGS = {
    'x': x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
autograd — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
find_means_for_continuous_types Ran
ran, honoured the contract we drafted
cuis15/FCFL/FUEL/dataset_generate.py
code served (permissive licence) · get_code("d749254a20b52f05")
How it ran

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

# The function expects X to be a 2D array-like structure where:
# - X[0] gives the first row (to determine number of columns)
# - X[:, col] gives a column
# - values can be strings or numeric types
# This suggests a numpy array with dtype=object to hold mixed types

X = np.array([
    ['1.5', '2.3', 'not_a_number', '4.1'],
    ['3.2', 'invalid', '5.5', '6.0'],
    ['7.8', '8.9', '9.1', 'text']
], dtype=object)

ARGS = {'X': X}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list 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
format_axes Ran
ran on a synthesized input
cuis15/FCFL/FUEL/synthetic/latex_utils.py
code served (permissive licence) · get_code("19c3adf4dc402137")
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 Axes. 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 matplotlib.pyplot as plt
import matplotlib.patches as mpatches

# Create a minimal matplotlib axes object
fig, ax = plt.subplots()

# Add a simple line to the plot so legend can work
ax.plot([1, 2, 3], [1, 2, 3], label='test line')

ARGS = {
    'ax': ax,
    'title': 'Test Title',
    'xlabel': 'X Axis Label',
    'ylabel': 'Y Axis Label',
    'leg_loc': 'upper left',
    'grid': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Axes — a Axes output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Axes 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
isFloat Ran
ran, violated the contract we drafted
cuis15/FCFL/FUEL/dataset_generate.py
code served (permissive licence) · get_code("dd69c2e2e8f79e3a")
How it ran

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

ARGS = {
    "string": "3.14159"
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 bool, 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
prepare_data Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
cuis15/FCFL/FUEL/dataset_generate.py
code served (permissive licence) · get_code("6509d4b83913ec5b")
How it ran

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

# Create sample raw_data that matches the expected format
# raw_data should have shape (n_samples, n_features + 1) where last column is the target
# Based on the inputs structure, there are 14 features + 1 target

# Sample data with 3 people
raw_data = np.array([
    # age, workclass, fnlwgt, education, education-num, marital-status, occupation, relationship, race, sex, capital-gain, capital-loss, hours-per-week, native-country, target
    [25, 'Private', 100000, 'Bachelors', 13, 'Never-married', 'Tech-support', 'Own-child', 'White', 'Male', 0, 0, 40, 'United-States', '<=50K'],
    [45, 'Self-emp-inc', 200000, 'Masters', 14, 'Married-civ-spouse', 'Exec-managerial', 'Husband', 'White', 'Male', 5000, 0, 50, 'United-States', '>50K'],
    [35, 'Private', 150000, 'HS-grad', 9, 'Divorced', 'Sales', 'Not-in-family', 'Black', 'Female', 0, 0, 35, 'Canada', '<=50K']
], dtype=object)

# Create means array - one mean value for each continuous feature
# Based on input_shape = [1, 8, 1, 16, 1, 7, 14, 6, 5, 2, 1, 1, 1, 41]
# Continuous features are at indices: 0 (age), 2 (fnlwgt), 4 (education-num), 10 (capital-gain), 11 (capital-loss), 12 (hours-per-week)
# We need 14 values (one for each feature type)
means = [38.0, 0, 189000.0, 0, 10.0, 0, 0, 0, 0, 0, 1000.0, 100.0, 40.0, 0]

ARGS = {
    'raw_data': raw_data,
    'means': means
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple 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_data Ran
ran on a synthesized input
cuis15/FCFL/FUEL/utils.py
code served (permissive licence) · get_code("79c283c686e75fbe")
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. 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 os
import json
import tempfile
import shutil

# Create temporary directories for train and test data
train_temp_dir = tempfile.mkdtemp(prefix='train_adult_')
test_temp_dir = tempfile.mkdtemp(prefix='test_adult_')

# Create sample training data file
train_data_content = {
    'user_data': {
        'client_1': {'x': [1, 2, 3], 'y': [0]},
        'client_2': {'x': [4, 5, 6], 'y': [1]}
    },
    'hierarchies': [['group_a', 'subgroup_1'], ['group_b', 'subgroup_2']]
}

train_file_path = os.path.join(train_temp_dir, 'data_0.json')
with open(train_file_path, 'w') as f:
    json.dump(train_data_content, f)

# Create sample test data file
test_data_content = {
    'user_data': {
        'client_1': {'x': [7, 8, 9], 'y': [0]},
        'client_2': {'x': [10, 11, 12], 'y': [1]}
    }
}

test_file_path = os.path.join(test_temp_dir, 'data_0.json')
with open(test_file_path, 'w') as f:
    json.dump(test_data_content, f)

ARGS = {
    'train_data_dir': train_temp_dir,
    'test_data_dir': test_temp_dir
}
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 — a tuple 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
concave_fun Not yet run
unverified (harvested, no recorded run)
cuis15/FCFL/FUEL/utils.py
code served (permissive licence) · get_code("85629ba2ef2046f9")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 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, 1 later) and 0 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
isFloat 2 other papers
1 dated earlier, 1 later
1902.00146 (2019-02)
Agnostic Federated Learning
2401.18070 (2024-01)
Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?
concave_fun 1 other paper
1 dated earlier
1902.00146 (2019-02)
Agnostic Federated Learning
concave_fun_eval 1 other paper
1 dated earlier
1902.00146 (2019-02)
Agnostic Federated Learning
construct_log 1 other paper
1 dated earlier
1902.00146 (2019-02)
Agnostic Federated Learning
f1 1 other paper
1 dated earlier
1902.00146 (2019-02)
Agnostic Federated Learning
f2 1 other paper
1 dated earlier
1902.00146 (2019-02)
Agnostic Federated Learning
find_means_for_continuous_types 1 other paper
1 dated earlier
1902.00146 (2019-02)
Agnostic Federated Learning
format_axes 1 other paper
1 dated earlier
1902.00146 (2019-02)
Agnostic Federated Learning
prepare_data 1 other paper
1 dated earlier
1902.00146 (2019-02)
Agnostic Federated Learning
read_data 1 other paper
1 dated earlier
1902.00146 (2019-02)
Agnostic Federated Learning

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

Federated learning (FL) has gain growing interests for its capability of learning from distributed data sources collectively without the need of accessing the raw data samples across different sources. So far FL research has mostly focused on improving the performance, how the algorithmic disparity will be impacted for the model learned from FL and the impact of algorithmic disparity on the utility inconsistency are largely unexplored. In this paper, we propose an FL framework to jointly consider performance consistency and algorithmic fairness across different local clients (data sources). We derive our framework from a constrained multi-objective optimization perspective, in which we learn a model satisfying fairness constraints on all clients with consistent performance. Specifically, we treat the algorithm prediction loss at each local client as an objective and maximize the worst-performing client with fairness constraints through optimizing a surrogate maximum function with all objectives involved. A gradient-based procedure is employed to achieve the Pareto optimality of this optimization problem. Theoretical analysis is provided to prove that our method can converge to a Pareto solution that achieves the min-max performance with fairness constraints on all clients. Comprehensive experiments on synthetic and real-world datasets demonstrate the superiority that our approach over baselines and its effectiveness in achieving both fairness and consistency across all local clients.

For agents

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

get_harvested_code_for_paper("2108.08435")
get_code_for_paper("2108.08435")
have("2108.08435")

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

curl https://syntology.ai/api/ran/2108.08435.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.08435.svg)](https://syntology.ai/paper/2108.08435)

Connect an agent — have() is free.