SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.13024 · 2026

FedHENet: A Frugal Federated Learning Framework for Heterogeneous Environments

Alejandro Dopico-Castro, Bertha Guijarro-Berdiñas, Oscar Fontenla-Romero, Amparo Alonso-Betanzos, Iván Digón

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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 1 has no contract verdict; 2 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2602.13024.json · badge: /api/ran/2602.13024.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
AlejandroDopico2/FedHENet canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
get_algorithm_parameters Ran
ran; our contract draft was wrong, not the code
AlejandroDopico2/FedHENet/fedhenet/algorithms/factory.py
code served (permissive licence) · get_code("67e4ad9ab4402058")
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 get_algorithm_parameters takes a single parameter: algorithm_name (str)
# It returns a dictionary of default parameters for the specified algorithm
# The function body simply looks up the algorithm_name in a defaults dict and returns it

ARGS = {
    'algorithm_name': 'fedavg'
}
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
split_iid Ran
ran; our contract draft was wrong, not the code
AlejandroDopico2/FedHENet/fedhenet/datasets.py
code served (permissive licence) · get_code("49075fe4ce313fe4")
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
import random
from torch.utils.data import Subset
from torchvision.datasets import MNIST
from torchvision.transforms import ToTensor
import tempfile
import os

# Create a minimal in-memory dataset to avoid file I/O
class FakeVisionDataset:
    def __init__(self, size=10):
        self.size = size
        self.data = [torch.randn(1, 28, 28) for _ in range(size)]
        self.targets = [i % 10 for i in range(size)]
    
    def __len__(self):
        return self.size
    
    def __getitem__(self, idx):
        return self.data[idx], self.targets[idx]

# Instantiate the fake dataset
fake_dataset = FakeVisionDataset(size=10)

# Define ARGS
ARGS = {
    'dataset': fake_dataset,
    'num_clients': 3,
    'seed': 42
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — 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
subsample_dataset Ran
ran on a synthesized input
AlejandroDopico2/FedHENet/fedhenet/datasets.py
code served (permissive licence) · get_code("6eb9a83c86aba72c")
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 Subset. 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 math
import random
import torch
from torch.utils.data import Subset
from torchvision.datasets import VisionDataset

torch.manual_seed(0)

class MinimalVisionDataset(VisionDataset):
    """Minimal VisionDataset for testing."""
    def __init__(self, size=10):
        super().__init__(root=None)
        self.size = size
    
    def __len__(self):
        return self.size
    
    def __getitem__(self, idx):
        return torch.randn(3, 32, 32), idx % 10

dataset = MinimalVisionDataset(size=20)

ARGS = {
    'dataset': dataset,
    'fraction': 0.5,
    'seed': 42
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Subset — a Subset 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
load_config Not yet run
unverified (harvested, no recorded run)
AlejandroDopico2/FedHENet/fedhenet/config.py
code served (permissive licence) · get_code("48a2e692102f9265")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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

Federated Learning (FL) enables collaborative training without centralizing data, essential for privacy compliance in real-world scenarios involving sensitive visual information. Most FL approaches rely on expensive, iterative deep network optimization, which still risks privacy via shared gradients. In this work, we propose FedHENet, extending the FedHEONN framework to image classification. By using a fixed, pretrained feature extractor and learning only a single output layer, we avoid costly local fine-tuning. This layer is learned by analytically aggregating client knowledge in a single round of communication using homomorphic encryption (HE). Experiments show that FedHENet achieves competitive accuracy compared to iterative FL baselines while demonstrating superior stability performance and up to 70% better energy efficiency. Crucially, our method is hyperparameter-free, removing the carbon footprint associated with hyperparameter tuning in standard FL. Code available in https://github.com/AlejandroDopico2/FedHENet/

For agents

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

get_harvested_code_for_paper("2602.13024")
get_code_for_paper("2602.13024")
have("2602.13024")

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

curl https://syntology.ai/api/ran/2602.13024.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.13024.svg)](https://syntology.ai/paper/2602.13024)

Connect an agent — have() is free.