SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.11364 · 2020

Improving Semi-supervised Federated Learning by Reducing the Gradient Diversity of Models

arXiv · PDF · Open in the Atlas

Code that ran

6 of 11 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; 2 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 2 failures of our instrument; 5 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/2008.11364.json · badge: /api/ran/2008.11364.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
jhcknzzm/SSFL-Benchmarking-Semi-supervised-Federated-Learning canonical (classifier label)
classifier basis: census
6 ran · 5 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; our contract draft was wrong, not the code
jhcknzzm/SSFL-Benchmarking-Semi-supervised-Federated-Learning/models/base.py
pointer only (licence: MIT); the stored copy get_code serves, from nadav-out/padam, is pointer only (licence: NONE) · get_code("c7442eb6f91cb5bd")
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 nadav-out/padam, and GitHub detected no licence in that repository 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.

compute_conv_output_size Ran
ran, honoured the contract we drafted
jhcknzzm/SSFL-Benchmarking-Semi-supervised-Federated-Learning/models/Semi_net.py
code served (permissive licence) · get_code("e71c2a2bc2fc8909")
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 int, ndim 0, dtype family int, 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.

import numpy as np

# This function computes the output size of a convolutional layer
# given input size and convolution parameters.
# All parameters are simple numeric values.

ARGS = {
    "Lin": 28,           # Input length (e.g., 28x28 image)
    "kernel_size": 3,    # Kernel/filter size
    "stride": 1,         # Stride of convolution
    "padding": 1,        # Padding added to input
    "dilation": 1        # Dilation factor
}
Setup block drafted by
a language model, Claude Haiku 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 int, ndim 0, dtype family int, 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
conv_bn_relu_pool Ran
ran on a synthesized input
jhcknzzm/SSFL-Benchmarking-Semi-supervised-Federated-Learning/models/resnet9.py
code served (permissive licence) · get_code("b83c8090ce555da4")
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 Sequential. 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)

ARGS = {
    "in_channels": 3,
    "out_channels": 64,
    "pool": True
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
flatten_tensors Ran
ran, honoured the contract we drafted
jhcknzzm/SSFL-Benchmarking-Semi-supervised-Federated-Learning/comm_helpers.py
pointer only (licence: MIT); the stored copy get_code serves, from shuangtongli/scool, is pointer only (licence: GPL-3.0) · get_code("de96e9b005b53e0f")
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 shuangtongli/scool, 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.

get_groups Ran
ran on a synthesized input
jhcknzzm/SSFL-Benchmarking-Semi-supervised-Federated-Learning/Grad_Diff.py
code served (permissive licence) · get_code("068a61460ff86dc6")
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 argparse

class Args:
    def __init__(self, experiment_name):
        self.experiment_name = experiment_name

# Test with EMNIST comUE10
ARGS = {
    'args': Args('EMNIST_comUE10')
}
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
unflatten_tensors Ran
ran; our contract draft was wrong, not the code
jhcknzzm/SSFL-Benchmarking-Semi-supervised-Federated-Learning/comm_helpers.py
pointer only (licence: MIT); the stored copy get_code serves, from shuangtongli/scool, is pointer only (licence: GPL-3.0) · get_code("349c36e737eadfe1")
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 shuangtongli/scool, 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.

Load_Avgmodel_weights Not yet run
unverified (harvested, no recorded run)
jhcknzzm/SSFL-Benchmarking-Semi-supervised-Federated-Learning/Grad_Diff.py
code served (permissive licence) · get_code("f901f7345452fe78")
How it ran

no invocation recorded.

Load_model_grad_checkpoint Not yet run
unverified (harvested, no recorded run)
jhcknzzm/SSFL-Benchmarking-Semi-supervised-Federated-Learning/Grad_Diff.py
code served (permissive licence) · get_code("8c55f4031b35b37a")
How it ran

no invocation recorded.

accuracy Not yet run
unverified (harvested, no recorded run)
jhcknzzm/SSFL-Benchmarking-Semi-supervised-Federated-Learning/models/resnet9.py
code served (permissive licence) · get_code("3c7852aeade0ad78")
How it ran

no invocation recorded.

communicate Not yet run
unverified (harvested, no recorded run)
jhcknzzm/SSFL-Benchmarking-Semi-supervised-Federated-Learning/comm_helpers.py
code served (permissive licence) · get_code("7dbc4e9dd1b3e1a1")
How it ran

no invocation recorded.

get Not yet run
unverified (harvested, no recorded run)
jhcknzzm/SSFL-Benchmarking-Semi-supervised-Federated-Learning/models/cifar.py
code served (permissive licence) · get_code("f8be03d81632009c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 5 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 5 later) and 5 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
compute_conv_output_size 7 other papers
2 dated earlier, 5 later
1905.11614 (2019-05)
Uncertainty-based Continual Learning with Adaptive Regularization
2003.09553 (2020-03)
Adversarial Continual Learning
2103.09762 (2021-03)
Gradient Projection Memory for Continual Learning
and 4 more not named here
accuracy 3 other papers
3 later
2201.05629 (2022-01)
Zero-Shot Machine Unlearning
2210.13043 (2022-10)
Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data
2404.10824 (2024-04)
Decoupled Weight Decay for Any $p$ Norm
flatten_tensors 2 other papers
2 later
2210.14026 (2022-10)
SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication
2306.09595 (2023-06)
Structured Cooperative Learning with Graphical Model Priors
unflatten_tensors 2 other papers
2 later
2210.14026 (2022-10)
SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication
2306.09595 (2023-06)
Structured Cooperative Learning with Graphical Model Priors
conv_bn_relu_pool 1 other paper
1 later
2208.09754 (2022-08)
FLIS: Clustered Federated Learning via Inference Similarity for Non-IID Data Distribution

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) is a promising way to use the computing power of mobile devices while maintaining the privacy of users. Current work in FL, however, makes the unrealistic assumption that the users have ground-truth labels on their devices, while also assuming that the server has neither data nor labels. In this work, we consider the more realistic scenario where the users have only unlabeled data, while the server has some labeled data, and where the amount of labeled data is smaller than the amount of unlabeled data. We call this learning problem semi-supervised federated learning (SSFL). For SSFL, we demonstrate that a critical issue that affects the test accuracy is the large gradient diversity of the models from different users. Based on this, we investigate several design choices. First, we find that the so-called consistency regularization loss (CRL), which is widely used in semi-supervised learning, performs reasonably well but has large gradient diversity. Second, we find that Batch Normalization (BN) increases gradient diversity. Replacing BN with the recently-proposed Group Normalization (GN) can reduce gradient diversity and improve test accuracy. Third, we show that CRL combined with GN still has a large gradient diversity when the number of users is large. Based on these results, we propose a novel grouping-based model averaging method to replace the FedAvg averaging method. Overall, our grouping-based averaging, combined with GN and CRL, achieves better test accuracy than not just a contemporary paper on SSFL in the same settings (>10\%), but also four supervised FL algorithms.

For agents

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

get_harvested_code_for_paper("2008.11364")
get_code_for_paper("2008.11364")
have("2008.11364")

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

curl https://syntology.ai/api/ran/2008.11364.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.11364.svg)](https://syntology.ai/paper/2008.11364)

Connect an agent — have() is free.