SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1905.05178 · 2019

Graph U-Nets

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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 0 have 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/1905.05178.json · badge: /api/ran/1905.05178.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
hujilin1229/gUNet reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
HongyangGao/Graph-U-Nets reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
FunctionStatusWhere it lives
normalize_adj Ran
ran, honoured the contract we drafted
hujilin1229/gUNet/ops.py
code served (permissive licence) · get_code("597b9f2e337f0d63")
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 Tensor, ndim 2, dtype family float, shape (4, 4) 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
import numpy as np
import scipy.sparse as sp

torch.manual_seed(0)

# Create a small adjacency matrix as a sparse tensor
# The function expects a tensor that has .to_dense() and .cpu() methods
# We'll create a 4x4 adjacency matrix (small, symmetric)
adj_dense = torch.tensor([
    [0.0, 1.0, 1.0, 0.0],
    [1.0, 0.0, 1.0, 1.0],
    [1.0, 1.0, 0.0, 1.0],
    [0.0, 1.0, 1.0, 0.0]
], dtype=torch.float32)

# Convert to sparse tensor format
adj_sparse = adj_dense.to_sparse()

ARGS = {
    "adj": adj_sparse
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, scipy, 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 (4, 4) — shape (4, 4) 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
normalize_adj_torch Ran
ran, honoured the contract we drafted
hujilin1229/gUNet/ops.py
code served (permissive licence) · get_code("88e5b6e8be02c080")
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 Tensor, ndim 2, dtype family float, shape (4, 4) 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

torch.manual_seed(0)

# Create a small sparse adjacency matrix
# The function expects a sparse tensor that can be converted to dense
# Create a 4x4 sparse adjacency matrix
indices = torch.tensor([[0, 1, 2, 3], [1, 2, 3, 0]], dtype=torch.long)
values = torch.ones(4, dtype=torch.float32)
mx = torch.sparse_coo_tensor(indices, values, (4, 4), dtype=torch.float32)

ARGS = {
    "mx": mx
}
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 Tensor, ndim 2, dtype family float, shape (4, 4) — shape (4, 4) 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
top_k_graph Ran
ran; our contract draft was wrong, not the code
HongyangGao/Graph-U-Nets/src/utils/ops.py
pointer only (licence: GPL-3.0) · get_code("094df4d2b0f19a49")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, HongyangGao/Graph-U-Nets, 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.

norm_g Not yet run
unverified (harvested, no recorded run)
HongyangGao/Graph-U-Nets/src/utils/ops.py
pointer only (licence: GPL-3.0) · get_code("3ff2604f52241f1b")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, HongyangGao/Graph-U-Nets, 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. No invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 1 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
norm_g 1 other paper
1 later
2606.12494 (2026-06)
Net-Ev <sup>2</sup> : A Generative Simulator for Network Event Evolution
normalize_adj_torch 1 other paper
1 later
2010.01804 (2020-10)
Graph Cross Networks with Vertex Infomax Pooling
top_k_graph 1 other paper
1 later
2410.03396 (2024-10)
GraphCroc: Cross-Correlation Autoencoder for Graph Structural Reconstruction

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

We consider the problem of representation learning for graph data. Convolutional neural networks can naturally operate on images, but have significant challenges in dealing with graph data. Given images are special cases of graphs with nodes lie on 2D lattices, graph embedding tasks have a natural correspondence with image pixel-wise prediction tasks such as segmentation. While encoder-decoder architectures like U-Nets have been successfully applied on many image pixel-wise prediction tasks, similar methods are lacking for graph data. This is due to the fact that pooling and up-sampling operations are not natural on graph data. To address these challenges, we propose novel graph pooling (gPool) and unpooling (gUnpool) operations in this work. The gPool layer adaptively selects some nodes to form a smaller graph based on their scalar projection values on a trainable projection vector. We further propose the gUnpool layer as the inverse operation of the gPool layer. The gUnpool layer restores the graph into its original structure using the position information of nodes selected in the corresponding gPool layer. Based on our proposed gPool and gUnpool layers, we develop an encoder-decoder model on graph, known as the graph U-Nets. Our experimental results on node classification and graph classification tasks demonstrate that our methods achieve consistently better performance than previous models.

For agents

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

get_harvested_code_for_paper("1905.05178")
get_code_for_paper("1905.05178")
have("1905.05178")

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

curl https://syntology.ai/api/ran/1905.05178.json

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

[![Syntology run record](https://syntology.ai/api/ran/1905.05178.svg)](https://syntology.ai/paper/1905.05178)

Connect an agent — have() is free.