SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.14403 · IJCAI · 2022

Rethinking the Setting of Semi-supervised Learning on Graphs

Jie Tang, Ming Ding, Yukuo Cen, Zihan Wang, Weikai Li, Ziang Li, Ziyu Zeng

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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 0 have no contract verdict; 2 failures of our instrument; 0 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/2205.14403.json · badge: /api/ran/2205.14403.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
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
THUDM/IGB community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
index_to_mask Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from divelab/Non-Local-GNN
pointer only; the stored copy get_code serves, from divelab/Non-Local-GNN, is pointer only (licence: GPL-3.0) · get_code("da80a2b9fd449bd2")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

random_planetoid_splits Ran
ran; our contract draft was wrong, not the code
THUDM/IGB/validutil/train_eval.py
code served (permissive licence) · get_code("b017e6b34b8cbf42")
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 MockData. 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
from tqdm import tqdm

torch.manual_seed(0)

class MockData:
    def __init__(self, num_nodes, num_classes):
        self.num_nodes = num_nodes
        # Create labels for each class with enough samples
        # We need at least 1500 samples total (20 per class for train + 500 val + 1000 test)
        # With num_classes=3, we need ~500 per class
        self.y = torch.zeros(num_nodes, dtype=torch.long)
        samples_per_class = num_nodes // num_classes
        for i in range(num_classes):
            start_idx = i * samples_per_class
            end_idx = start_idx + samples_per_class if i < num_classes - 1 else num_nodes
            self.y[start_idx:end_idx] = i
        
        self.train_mask = None
        self.val_mask = None
        self.test_mask = None

# Create mock data with enough nodes and classes
# Need at least 1500 nodes (20*num_classes for train + 500 for val + 1000 for test)
num_nodes = 1600
num_classes = 3

data = MockData(num_nodes=num_nodes, num_classes=num_classes)

ARGS = {
    "data": data,
    "num_classes": num_classes,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MockData — a MockData output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MockData 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 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
index_to_mask
brick of this paper's assembly: helper
12 other papers
4 dated earlier, 8 later
2005.14612 (2020-05)
Non-Local Graph Neural Networks
2007.09296 (2020-07)
Towards Deeper Graph Neural Networks
2111.07337 (2021-11)
p-Laplacian Based Graph Neural Networks
and 9 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

We argue that the present setting of semisupervised learning on graphs may result in unfair comparisons, due to its potential risk of overtuning hyper-parameters for models. In this paper, we highlight the significant influence of tuning hyper-parameters, which leverages the label information in the validation set to improve the performance. To explore the limit of over-tuning hyperparameters, we propose ValidUtil, an approach to fully utilize the label information in the validation set through an extra group of hyper-parameters. With ValidUtil, even GCN can easily get high accuracy of 85.8% on Cora. To avoid over-tuning, we merge the training set and the validation set and construct an i.i.d. graph benchmark (IGB) consisting of 4 datasets. Each dataset contains 100 i.i.d. graphs sampled from a large graph to reduce the evaluation variance. Our experiments suggest that IGB is a more stable benchmark than previous datasets for semisupervised learning on graphs. Our code and data are released at https://github.com/THUDM/IGB/. * indicates equal contribution. 1 The experiments can be reproduced using the CogDL package [Cen et al., 2021].

For agents

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

get_harvested_code_for_paper("2205.14403")
get_code_for_paper("2205.14403")
have("2205.14403")

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

curl https://syntology.ai/api/ran/2205.14403.json

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

[![Syntology run record](https://syntology.ai/api/ran/2205.14403.svg)](https://syntology.ai/paper/2205.14403)

Connect an agent — have() is free.