SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.12097 · 2020

Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learning

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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 2 have no contract verdict; 0 failures of our instrument; 0 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/2006.12097.json · badge: /api/ran/2006.12097.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
wyjeong/FedMatch canonical (classifier label)
classifier basis: census
2 ran · 0 no recorded run
FunctionStatusWhere it lives
np_load Ran
ran on a synthesized input
wyjeong/FedMatch/misc/utils.py
code served (permissive licence) · get_code("517ed82786c497ef")
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 os
import numpy as np
import tempfile

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

# Create a sample numpy file with pickled object
sample_data = {
    'key1': 'value1',
    'key2': [1, 2, 3],
    'key3': np.array([4, 5, 6])
}
filename = 'test_data.npy'
filepath = os.path.join(temp_dir, filename)
np.save(filepath, sample_data, allow_pickle=True)

ARGS = {
    'base_dir': temp_dir,
    'filename': filename
}
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 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
set_config Ran
ran on a synthesized input
wyjeong/FedMatch/config.py
code served (permissive licence) · get_code("9247d6b871c27fbe")
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 Namespace. 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 numpy as np
from argparse import Namespace

torch.manual_seed(0)

# Create a minimal args object with all required attributes
args = Namespace()

# Basic attributes that will be set by set_config
args.gpu_mem = None
args.dataset_path = None
args.output_path = None
args.archi = 'resnet9'
args.dataset_id_to_name = None

# Task-related attributes - this determines which branch of set_config is taken
args.task = 'biid_lc_c10'  # Contains 'lc', 'biid', and 'c10' to trigger multiple branches

# Model-related attributes
args.model = 'fedmatch'

# Scenario will be set by set_config based on task
args.scenario = None

# All other attributes that may be set
args.num_labels_per_class = None
args.num_epochs_client = None
args.batch_size_client = None
args.num_epochs_server = None
args.batch_size_server = None
args.num_epochs_server_pretrain = None
args.lr_factor = None
args.lr_patience = None
args.lr_min = None
args.sync = None
args.num_tasks = None
args.num_clients = None
args.num_rounds = None
args.dataset_id = None
args.num_classes = None
args.num_test = None
args.num_valid = None
args.batch_size_test = None
args.lr = None
args.wd = None
args.num_helpers = None
args.confidence = None
args.psi_factor = None
args.h_interval = None
args.lambda_s = None
args.lambda_i = None
args.lambda_a = None
args.lambda_l2 = None
args.lambda_l1 = None
args.l1_thres = None
args.delta_thres = None

ARGS = {'args': args}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Namespace — a Namespace output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Namespace 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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

While existing federated learning approaches mostly require that clients have fully-labeled data to train on, in realistic settings, data obtained at the client-side often comes without any accompanying labels. Such deficiency of labels may result from either high labeling cost, or difficulty of annotation due to the requirement of expert knowledge. Thus the private data at each client may be either partly labeled, or completely unlabeled with labeled data being available only at the server, which leads us to a new practical federated learning problem, namely Federated Semi-Supervised Learning (FSSL). In this work, we study two essential scenarios of FSSL based on the location of the labeled data. The first scenario considers a conventional case where clients have both labeled and unlabeled data (labels-at-client), and the second scenario considers a more challenging case, where the labeled data is only available at the server (labels-at-server). We then propose a novel method to tackle the problems, which we refer to as Federated Matching (FedMatch). FedMatch improves upon naive combinations of federated learning and semi-supervised learning approaches with a new inter-client consistency loss and decomposition of the parameters for disjoint learning on labeled and unlabeled data. Through extensive experimental validation of our method in the two different scenarios, we show that our method outperforms both local semi-supervised learning and baselines which naively combine federated learning with semi-supervised learning. The code is available at https://github.com/wyjeong/FedMatch.

For agents

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

get_harvested_code_for_paper("2006.12097")
get_code_for_paper("2006.12097")
have("2006.12097")

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

curl https://syntology.ai/api/ran/2006.12097.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.12097.svg)](https://syntology.ai/paper/2006.12097)

Connect an agent — have() is free.