SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.02636 · NeurIPS · 2022

Geodesic Graph Neural Network for Efficient Graph Representation Learning

Yixin Chen, Muhan Zhang, Lecheng Kong

arXiv · PDF · Open in the Atlas

Code that ran

1 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 1 has no contract verdict; 0 failures of our instrument; 4 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/2210.02636.json · badge: /api/ran/2210.02636.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
woodcutter1998/gdgnn canonical (classifier label)
classifier basis not recorded on the link
1 ran · 4 no recorded run
FunctionStatusWhere it lives
single_source_neg_sample Ran
ran on a synthesized input
woodcutter1998/gdgnn/graph_utils.py
code served (permissive licence) · get_code("7f1fbd4c990cc92e")
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 ndarray, ndim 1, dtype family int, shape (2,) 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 numpy as np
from scipy import sparse

# Create a small sparse adjacency matrix
# Using a 5x5 matrix for testing
# We'll make it sparse with some edges
rows = np.array([0, 0, 1, 2, 2, 3])
cols = np.array([1, 2, 3, 0, 4, 1])
data = np.array([1, 1, 1, 1, 1, 1])
adj = sparse.csr_matrix((data, (rows, cols)), shape=(5, 5))

source = 0

ARGS = {
    "adj": adj,
    "source": source
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family int, shape (2,) — shape (2,) 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
collate_hor_link Not yet run
unverified (harvested, no recorded run)
woodcutter1998/gdgnn/collate.py
code served (permissive licence) · get_code("4d609628bde15b6b")
How it ran

no invocation recorded.

collate_hor_link_kg Not yet run
unverified (harvested, no recorded run)
woodcutter1998/gdgnn/collate.py
code served (permissive licence) · get_code("cb56933ffd4cf224")
How it ran

no invocation recorded.

collate_ver_link Not yet run
unverified (harvested, no recorded run)
woodcutter1998/gdgnn/collate.py
code served (permissive licence) · get_code("524521c3ac4d7975")
How it ran

no invocation recorded.

get_single_source_shortest_path_from_pred Not yet run
unverified (harvested, no recorded run)
woodcutter1998/gdgnn/graph_utils.py
code served (permissive licence) · get_code("0e9b54853cfc3ccd")
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, 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 5 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

Graph Neural Networks (GNNs) have recently been applied to graph learning tasks and achieved state-of-the-art (SOTA) results. However, many competitive methods run GNNs multiple times with subgraph extraction and customized labeling to capture information that is hard for normal GNNs to learn. Such operations are timeconsuming and do not scale to large graphs. In this paper, we propose an efficient GNN framework called Geodesic GNN (GDGNN) that requires only one GNN run and injects conditional relationships between nodes into the model without labeling. This strategy effectively reduces the runtime of subgraph methods. Specifically, we view the shortest paths between two nodes as the spatial graph context of the neighborhood around them. The GNN embeddings of nodes on the shortest paths are used to generate geodesic representations. Conditioned on the geodesic representations, GDGNN can generate node, link, and graph representations that carry much richer structural information than plain GNNs. We theoretically prove that GDGNN is more powerful than plain GNNs. We present experimental results to show that GDGNN achieves highly competitive performance with SOTA GNN models on various graph learning tasks while taking significantly less time.

For agents

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

get_harvested_code_for_paper("2210.02636")
get_code_for_paper("2210.02636")
have("2210.02636")

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

curl https://syntology.ai/api/ran/2210.02636.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.02636.svg)](https://syntology.ai/paper/2210.02636)

Connect an agent — have() is free.