SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.06514 · ICLR · 2022

Large-Scale Representation Learning on Graphs via Bootstrapping

Rémi Munos, Michal Valko, Petar Veličković, Shantanu Thakoor, Deepmind Corentin, Tallec Deepmind, Mohammad Gheshlaghi, Azar Deepmind, Mehdi Azabou, Eva Dyer

arXiv · PDF · Open in the Atlas

Code that ran

5 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 1 failure 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/2102.06514.json · badge: /api/ran/2102.06514.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
Namkyeong/BGRL_Pytorch reimplementation (classifier label)
classifier basis: classifier_2025
4 ran · 3 no recorded run
nyushcs/gaugllm community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
BGRL Ran
ran on a synthesized input · constructed an object; no result was computed
Namkyeong/BGRL_Pytorch/models.py
pointer only (licence: NONE) · get_code("440ee572d2844192")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Namkyeong/BGRL_Pytorch 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.

BGRL Ran
ran on a synthesized input · constructed an object; no result was computed
nyushcs/gaugllm/BGRL/bgrl/bgrl.py
code served (permissive licence) · get_code("b051eaf09045db0f")
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 an instance of its own class, BGRL: the run constructed the object and did not call it, so no result was computed. 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
import copy

torch.manual_seed(0)

class SimpleEncoder(nn.Module):
    """Minimal encoder with reset_parameters method."""
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def reset_parameters(self):
        self.linear.reset_parameters()
    
    def forward(self, x):
        return self.linear(x)

class SimplePredictor(nn.Module):
    """Minimal predictor network."""
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(3, 2)
    
    def forward(self, x):
        return self.linear(x)

encoder = SimpleEncoder()
predictor = SimplePredictor()

ARGS = {
    "encoder": encoder,
    "predictor": predictor,
}
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 BGRL — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a BGRL 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
EMA Ran
ran on a synthesized input · constructed an object; no result was computed
Namkyeong/BGRL_Pytorch/models.py
pointer only (licence: NONE) · get_code("9b7e3a0ad9dda817")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Namkyeong/BGRL_Pytorch 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.

Encoder Ran
ran on a synthesized input · constructed an object; no result was computed
Namkyeong/BGRL_Pytorch/models.py
pointer only (licence: NONE) · get_code("5b5e12c730d06d3c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Namkyeong/BGRL_Pytorch 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.

loss_fn Ran
ran; our contract draft was wrong, not the code
Namkyeong/BGRL_Pytorch/models.py
pointer only (licence: NONE) · get_code("00cae89471470576")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Namkyeong/BGRL_Pytorch 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.

init_weights Not yet run
unverified (harvested, no recorded run)
Namkyeong/BGRL_Pytorch/models.py
pointer only (licence: NONE) · get_code("17aa6a8dd8ecb13a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Namkyeong/BGRL_Pytorch 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. No invocation recorded.

set_requires_grad Not yet run
unverified (harvested, no recorded run)
Namkyeong/BGRL_Pytorch/models.py
pointer only (licence: NONE) · get_code("47295fd3ab15aafb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Namkyeong/BGRL_Pytorch 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. No invocation recorded.

update_moving_average Not yet run
unverified (harvested, no recorded run)
Namkyeong/BGRL_Pytorch/models.py
pointer only (licence: NONE) · get_code("a099858928c8811a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Namkyeong/BGRL_Pytorch 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. No invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 5 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 5 later) and 3 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
loss_fn
brick of this paper's assembly: loss
7 other papers
1 dated earlier, 5 later, 1 same year, order not determinable · 3 only as an assembly brick
2006.07733 (2020-06)
Bootstrap your own latent: A new approach to self-supervised Learning
2021.acl-long.402 (2021 (year only))
Bootstrapped Unsupervised Sentence Representation Learning
2110.04935 (2021-10)
Learning Temporally-Consistent Representations for Data-Efficient Reinforcement Learning
and 4 more not named here
set_requires_grad
brick of this paper's assembly: helper
4 other papers
1 dated earlier, 3 later · 4 only as an assembly brick
2006.07733 (2020-06)
Bootstrap your own latent: A new approach to self-supervised Learning
2105.05682 (2021-05)
Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning
2206.12038 (2022-06)
BYOL-S: Learning Self-supervised Speech Representations by Bootstrapping
and 1 more not named here
update_moving_average
brick of this paper's assembly: update_rule
4 other papers
1 dated earlier, 3 later · 4 only as an assembly brick
2006.07733 (2020-06)
Bootstrap your own latent: A new approach to self-supervised Learning
2105.05682 (2021-05)
Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning
2206.12038 (2022-06)
BYOL-S: Learning Self-supervised Speech Representations by Bootstrapping
and 1 more not named here
EMA
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2606.10284 (2026-06)
Revisiting Positive Samples in Graph Contrastive Learning: From the Perspective of Message Passing
init_weights
brick of this paper's assembly: helper
1 other paper
1 later
2606.10284 (2026-06)
Revisiting Positive Samples in Graph Contrastive Learning: From the Perspective of Message Passing

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

Self-supervised learning provides a promising path towards eliminating the need for costly label information in representation learning on graphs. However, to achieve state-of-the-art performance, methods often need large numbers of negative examples and rely on complex augmentations. This can be prohibitively expensive, especially for large graphs. To address these challenges, we introduce Bootstrapped Graph Latents (BGRL) -a graph representation learning method that learns by predicting alternative augmentations of the input. BGRL uses only simple augmentations and alleviates the need for contrasting with negative examples, and is thus scalable by design. BGRL outperforms or matches prior methods on several established benchmarks, while achieving a 2-10x reduction in memory costs. Furthermore, we show that BGRL can be scaled up to extremely large graphs with hundreds of millions of nodes in the semi-supervised regime -achieving state-ofthe-art performance and improving over supervised baselines where representations are shaped only through label information. In particular, our solution centered on BGRL constituted one of the winning entries to the Open Graph Benchmark -Large Scale Challenge at KDD Cup 2021, on a graph orders of magnitudes larger than all previously available benchmarks, thus demonstrating the scalability and effectiveness of our approach.

For agents

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

get_harvested_code_for_paper("2102.06514")
get_code_for_paper("2102.06514")
have("2102.06514")

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

curl https://syntology.ai/api/ran/2102.06514.json

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

[![Syntology run record](https://syntology.ai/api/ran/2102.06514.svg)](https://syntology.ai/paper/2102.06514)

Connect an agent — have() is free.