SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1804.05271 · 2018

Adaptive Federated Learning in Resource Constrained Edge Computing Systems

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; 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/1804.05271.json · badge: /api/ran/1804.05271.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
IBM/adaptive-federated-learning canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
bias_variable Ran
ran; our contract draft was wrong, not the code
IBM/adaptive-federated-learning/models/cnn_cifar10.py
pointer only (licence: MIT); the stored copy get_code serves, from jerichooconnell/tf_unet, is pointer only (licence: GPL-3.0) · get_code("5d78e1f7a1afb766")
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 jerichooconnell/tf_unet, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

conv2d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
IBM/adaptive-federated-learning/models/cnn_cifar10.py
code served (permissive licence) · get_code("3cd17758f440bd57")
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 EagerTensor, ndim 4, dtype family float, shape (2, 4, 3, 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 tensorflow as tf
import numpy as np

# Create input tensor x with shape [batch, height, width, channels]
# Following NHWC format (standard for tf.nn.conv2d)
# batch=2, height=4, width=3, channels=2
x = tf.constant(np.random.randn(2, 4, 3, 2).astype(np.float32))

# Create filter tensor W with shape [filter_height, filter_width, in_channels, out_channels]
# filter_height=3, filter_width=3, in_channels=2, out_channels=4
W = tf.constant(np.random.randn(3, 3, 2, 4).astype(np.float32))

ARGS = {
    'x': x,
    'W': W
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 4, dtype family float, shape (2, 4, 3, 4) — shape (2, 4, 3, 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
get_model Ran
ran on a synthesized input
IBM/adaptive-federated-learning/models/get_model.py
code served (permissive licence) · get_code("6f4c3bfaab6066d4")
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 ModelCNNMnist. 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 only takes model_class_name as a required parameter
# and optionally rand_seed and step_size, but doesn't actually use them
# It just imports and instantiates one of three model classes based on the name

# Since the imports will fail (models don't exist), we'll use a valid model class name
# and mock the imports by creating stand-in classes

class ModelCNNMnist(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 8, 3)
        self.fc = nn.Linear(8 * 26 * 26, 10)
    
    def forward(self, x):
        x = self.conv1(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)
        return x

class ModelCNNCifar10(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(3, 16, 3)
        self.fc = nn.Linear(16 * 30 * 30, 10)
    
    def forward(self, x):
        x = self.conv1(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)
        return x

class ModelSVMSmooth(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(5, 1)
    
    def forward(self, x):
        return self.linear(x)

# Patch the imports
import sys
from types import ModuleType

models_cnn_mnist = ModuleType('models.cnn_mnist')
models_cnn_mnist.ModelCNNMnist = ModelCNNMnist
sys.modules['models.cnn_mnist'] = models_cnn_mnist

models_cnn_cifar10 = ModuleType('models.cnn_cifar10')
models_cnn_cifar10.ModelCNNCifar10 = ModelCNNCifar10
sys.modules['models.cnn_cifar10'] = models_cnn_cifar10

models_svm_smooth = ModuleType('models.svm_smooth')
models_svm_smooth.ModelSVMSmooth = ModelSVMSmooth
sys.modules['models.svm_smooth'] = models_svm_smooth

models = ModuleType('models')
sys.modules['models'] = models

ARGS = {
    'model_class_name': 'ModelCNNMnist',
    'rand_seed': 42,
    'step_size': 0.01
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
models, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ModelCNNMnist — a ModelCNNMnist output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ModelCNNMnist 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
weight_variable Not yet run
unverified (harvested, no recorded run)
IBM/adaptive-federated-learning/models/cnn_cifar10.py
code served (permissive licence) · get_code("cb07eb141f5648be")
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, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 3 later) and 1 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
bias_variable 5 other papers
3 dated earlier, 2 later
1505.04597 (2015-05)
U-Net: Convolutional Networks for Biomedical Image Segmentation
1604.07316 (2016-04)
End to End Learning for Self-Driving Cars
1604.07379 (2016-04)
Context Encoders: Feature Learning by Inpainting
and 2 more not named here
weight_variable 3 other papers
2 dated earlier, 1 later
1604.07316 (2016-04)
End to End Learning for Self-Driving Cars
1604.07379 (2016-04)
Context Encoders: Feature Learning by Inpainting
1912.09091 (2019-12)
Overcoming Long-term Catastrophic Forgetting through Adversarial Neural Pruning and Synaptic Consolidation
conv2d 2 other papers
2 later
1805.04980 (2018-05)
Unifying and Merging Well-trained Deep Neural Networks for Inference Stage
2502.16782 (2025-02)
CipherPrune: Efficient and Scalable Private Transformer Inference

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

Emerging technologies and applications including Internet of Things (IoT), social networking, and crowd-sourcing generate large amounts of data at the network edge. Machine learning models are often built from the collected data, to enable the detection, classification, and prediction of future events. Due to bandwidth, storage, and privacy concerns, it is often impractical to send all the data to a centralized location. In this paper, we consider the problem of learning model parameters from data distributed across multiple edge nodes, without sending raw data to a centralized place. Our focus is on a generic class of machine learning models that are trained using gradient-descent based approaches. We analyze the convergence bound of distributed gradient descent from a theoretical point of view, based on which we propose a control algorithm that determines the best trade-off between local update and global parameter aggregation to minimize the loss function under a given resource budget. The performance of the proposed algorithm is evaluated via extensive experiments with real datasets, both on a networked prototype system and in a larger-scale simulated environment. The experimentation results show that our proposed approach performs near to the optimum with various machine learning models and different data distributions.

For agents

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

get_harvested_code_for_paper("1804.05271")
get_code_for_paper("1804.05271")
have("1804.05271")

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

curl https://syntology.ai/api/ran/1804.05271.json

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

[![Syntology run record](https://syntology.ai/api/ran/1804.05271.svg)](https://syntology.ai/paper/1804.05271)

Connect an agent — have() is free.