SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.06492 · ICCV · 2021

Collaborative Unsupervised Visual Representation Learning from Decentralized Data

Shuai Yi, Shuai Zhang, Weiming Zhuang, Yonggang Wen, Xin Gan

arXiv · PDF · Open in the Atlas

Code that ran

2 of 5 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; 3 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/2108.06492.json · badge: /api/ran/2108.06492.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
EasyFL-AI/EasyFL marked official in Papers with Code
Papers with Code archive
2 ran · 3 no recorded run
FunctionStatusWhere it lives
MLP Ran
ran on a synthesized input
EasyFL-AI/EasyFL/applications/fedssl/model.py
code served (permissive licence) · get_code("43b65445bde2bf33")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 2, dtype family float, shape (2, 3) 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 torch
from torch import nn

OneLayer = '1_layer'
TwoLayer = '2_layer'

class MLP(nn.Module):

    def __init__(self, dim, projection_size, hidden_size=4096, num_layer=TwoLayer):
        super().__init__()
        self.in_features = dim
        if num_layer == OneLayer:
            self.net = nn.Sequential(nn.Linear(dim, projection_size))
        elif num_layer == TwoLayer:
            self.net = nn.Sequential(nn.Linear(dim, hidden_size), nn.BatchNorm1d(hidden_size), nn.ReLU(inplace=True), nn.Linear(hidden_size, projection_size))
        else:
            raise NotImplementedError(f'Not defined MLP: {num_layer}')

    def forward(self, x):
        return self.net(x)


INIT_ARGS = {
    'dim': 4,
    'projection_size': 3,
    'hidden_size': 768,
    'num_layer': TwoLayer
}

ARGS = {
    'x': torch.randn(2, 4)
}

mlp = MLP(**INIT_ARGS)
output = mlp(**ARGS)
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 3) — shape (2, 3) 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
ResNet18 Ran
ran on a synthesized input
EasyFL-AI/EasyFL/applications/fedssl/model.py
code served (permissive licence) · get_code("75992b6b253f9430")
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 ResNet. 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 = {
    "num_classes": 10
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
BaseModel Not yet run
unverified (harvested, no recorded run)
EasyFL-AI/EasyFL/applications/fedssl/model.py
code served (permissive licence) · get_code("4a08683ecb8da2f1")
How it ran

no invocation recorded.

MoCoModel Not yet run
unverified (harvested, no recorded run)
EasyFL-AI/EasyFL/applications/fedssl/model.py
code served (permissive licence) · get_code("279410413f7add8f")
How it ran

no invocation recorded.

ResNet Not yet run
unverified (harvested, no recorded run)
EasyFL-AI/EasyFL/applications/fedssl/model.py
code served (permissive licence) · get_code("73958f1ff0c64689")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 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.

FunctionAlso present inEarliest-datedOthers named
ResNet18
brick of this paper's assembly: model
27 other papers
6 dated earlier, 21 later
1605.07146 (2016-05)
Wide Residual Networks
1901.09847 (2019-01)
Error Feedback Fixes SignSGD and other Gradient Compression Schemes
1910.09652 (2019-10)
Kernelized Wasserstein Natural Gradient
and 24 more not named here

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

Unsupervised representation learning has achieved outstanding performances using centralized data available on the Internet. However, the increasing awareness of privacy protection limits sharing of decentralized unlabeled image data that grows explosively in multiple parties (e.g., mobile phones and cameras). As such, a natural problem is how to leverage these data to learn visual representations for downstream tasks while preserving data privacy. To address this problem, we propose a novel federated unsupervised learning framework, FedU. In this framework, each party trains models from unlabeled data independently using contrastive learning with an online network and a target network. Then, a central server aggregates trained models and updates clients' models with the aggregated model. It preserves data privacy as each party only has access to its raw data. Decentralized data among multiple parties are normally non-independent and identically distributed (non-IID), leading to performance degradation. To tackle this challenge, we propose two simple but effective methods: 1) We design the communication protocol to upload only the encoders of online networks for server aggregation and update them with the aggregated encoder; 2) We introduce a new module to dynamically decide how to update predictors based on the divergence caused by non-IID. The predictor is the other component of the online network. Extensive experiments and ablations demonstrate the effectiveness and significance of FedU. It outperforms training with only one party by over 5% and other methods by over 14% in linear and semi-supervised evaluation on non-IID data.

For agents

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

get_harvested_code_for_paper("2108.06492")
get_code_for_paper("2108.06492")
have("2108.06492")

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

curl https://syntology.ai/api/ran/2108.06492.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.06492.svg)](https://syntology.ai/paper/2108.06492)

Connect an agent — have() is free.