SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2111.06283 · NeurIPS · 2021

DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks

Lukas Faber, Roger Wattenhofer, András Pál, Papp

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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; 1 failure 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/2111.06283.json · badge: /api/ran/2111.06283.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
karolismart/dropgnn canonical (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
FunctionStatusWhere it lives
S2V_to_PyG Ran
ran; our contract draft was wrong, not the code
karolismart/dropgnn/ptc_dataset.py
code served (permissive licence) · get_code("ca79c0c0249b5487")
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 Data. 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

torch.manual_seed(0)

class S2VData:
    def __init__(self):
        self.edge_mat = torch.tensor([[0, 1, 1, 2], [1, 0, 2, 1]], dtype=torch.long)
        self.node_features = torch.randn(3, 4)
        self.label = 1

data = S2VData()

ARGS = {
    'data': data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torch_geometric — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Data — a Data 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
load_data Ran
ran on a synthesized input
karolismart/dropgnn/ptc_dataset.py
code served (permissive licence) · get_code("22f66d8c36eceac7")
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 list. 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
import networkx as nx
import tempfile
import os

torch.manual_seed(0)

# Create a temporary directory and a minimal dataset file
temp_dir = tempfile.mkdtemp()
dataset_name = "test_dataset"

# Create a minimal .txt file in the format expected by load_data
# Format: first line is number of graphs
# Then for each graph: n (nodes) l (label)
# Then for each node: node_id degree neighbor1 neighbor2 ... [optional features]
dataset_content = """2
3 0
0 2 1 2
1 2 0 2
2 2 0 1
3 1
0 1 1
1 2 0 2
2 1 1
"""

dataset_path = os.path.join(temp_dir, f"{dataset_name}.txt")
with open(dataset_path, 'w') as f:
    f.write(dataset_content)

ARGS = {
    'dataset': dataset_name,
    'degree_as_tag': False,
    'folder': temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
networkx, numpy, torch, torch_geometric — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list 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
main Not yet run
unverified (harvested, no recorded run)
karolismart/dropgnn/gin-synthetic.py
code served (permissive licence) · get_code("0245c4edf22b808d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 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.

FunctionAlso present inEarliest-datedOthers named
S2V_to_PyG 2 other papers
1 dated earlier, 1 later
2110.02910 (2021-10)
Equivariant Subgraph Aggregation Networks
2206.11140 (2022-06)
Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries

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

This paper studies Dropout Graph Neural Networks (DropGNNs), a new approach that aims to overcome the limitations of standard GNN frameworks. In DropGNNs, we execute multiple runs of a GNN on the input graph, with some of the nodes randomly and independently dropped in each of these runs. Then, we combine the results of these runs to obtain the final result. We prove that DropGNNs can distinguish various graph neighborhoods that cannot be separated by message passing GNNs. We derive theoretical bounds for the number of runs required to ensure a reliable distribution of dropouts, and we prove several properties regarding the expressive capabilities and limits of DropGNNs. We experimentally validate our theoretical findings on expressiveness. Furthermore, we show that DropGNNs perform competitively on established GNN benchmarks.

For agents

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

get_harvested_code_for_paper("2111.06283")
get_code_for_paper("2111.06283")
have("2111.06283")

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

curl https://syntology.ai/api/ran/2111.06283.json

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

[![Syntology run record](https://syntology.ai/api/ran/2111.06283.svg)](https://syntology.ai/paper/2111.06283)

Connect an agent — have() is free.