SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.01942 · ICML · 2024

Mitigating Label Noise on Graphs via Topological Sample Selection

Bo Han, Jun Yu, Tongliang Liu, Jiangchao Yao, Xiaobo Xia, Yuhao Wu, Ruxin Wang

arXiv · PDF · Open in the Atlas

Code that ran

6 of 9 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures 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/2403.01942.json · badge: /api/ran/2403.01942.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
tmllab/2024_ICML_TSS canonical (classifier label)
classifier basis: census
5 ran · 3 no recorded run
wu-yu-hao/2024_icml_tss marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
class_conditional_betweenness_centrality Ran
ran; our contract draft was wrong, not the code
wu-yu-hao/2024_icml_tss/utils.py
code served (permissive licence) · get_code("296ecf63857163ee")
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 1, dtype family float, shape (5,) 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

torch.manual_seed(0)

# Create a minimal data object with required attributes
class MinimalData:
    def __init__(self):
        # y: class labels for all nodes (shape: [num_nodes])
        self.y = torch.tensor([0, 1, 0, 1, 0], dtype=torch.long)
        
        # Pi: pairwise matrix (shape: [num_nodes, num_nodes])
        # This represents some kind of path or probability matrix
        self.Pi = torch.rand(5, 5, dtype=torch.float32)

data = MinimalData()

# rely_idx: indices to consider (subset of nodes)
rely_idx = torch.tensor([0, 1, 2, 3, 4], dtype=torch.long)

ARGS = {
    "data": data,
    "rely_idx": rely_idx,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (5,) — shape (5,) 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
difficulty_measurer Ran
ran; our contract draft was wrong, not the code
tmllab/2024_ICML_TSS/utils.py
pointer only (licence: NONE) · get_code("6cd020e3121e6563")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tmllab/2024_ICML_TSS 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.

evaluate Ran
ran; our contract draft was wrong, not the code
tmllab/2024_ICML_TSS/train_eval.py
pointer only (licence: NONE) · get_code("22af6af53b4c250b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tmllab/2024_ICML_TSS 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.

predict Ran
ran; our contract draft was wrong, not the code
tmllab/2024_ICML_TSS/train_eval.py
pointer only (licence: NONE) · get_code("b662bcd70e07850c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tmllab/2024_ICML_TSS 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.

train Ran
ran; our contract draft was wrong, not the code
tmllab/2024_ICML_TSS/train_eval.py
pointer only (licence: NONE) · get_code("106b95ab43885bd3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tmllab/2024_ICML_TSS 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.

training_scheduler Ran
ran, honoured the contract we drafted
tmllab/2024_ICML_TSS/utils.py
pointer only (licence: NONE) · get_code("291679e8720c2aa2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tmllab/2024_ICML_TSS 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.

multiclass_noisify Not yet run
unverified (harvested, no recorded run)
tmllab/2024_ICML_TSS/make_noise.py
pointer only (licence: NONE) · get_code("e6909ca443b75a70")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tmllab/2024_ICML_TSS 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.

noisify_multiclass_symmetric Not yet run
unverified (harvested, no recorded run)
tmllab/2024_ICML_TSS/make_noise.py
pointer only (licence: NONE) · get_code("92243e64bc561890")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tmllab/2024_ICML_TSS 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.

noisify_pairflip Not yet run
unverified (harvested, no recorded run)
tmllab/2024_ICML_TSS/make_noise.py
pointer only (licence: NONE) · get_code("aebcd3a541c14ea0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tmllab/2024_ICML_TSS 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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

Despite the success of the carefully-annotated benchmarks, the effectiveness of existing graph neural networks (GNNs) can be considerably impaired in practice when the real-world graph data is noisily labeled. Previous explorations in sample selection have been demonstrated as an effective way for robust learning with noisy labels, however, the conventional studies focus on i.i.d data, and when moving to non-iid graph data and GNNs, two notable challenges remain: (1) nodes located near topological class boundaries are very informative for classification but cannot be successfully distinguished by the heuristic sample selection. (2) there is no available measure that considers the graph topological information to promote sample selection in a graph. To address this dilemma, we propose a Topological Sample Selection (TSS) method that boosts the informative sample selection process in a graph by utilising topological information. We theoretically prove that our procedure minimizes an upper bound of the expected risk under target clean distribution, and experimentally show the superiority of our method compared with state-ofthe-art baselines. Our implementation is available at https://github.com/tmllab/2024_ICML_TSS.

For agents

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

get_harvested_code_for_paper("2403.01942")
get_code_for_paper("2403.01942")
have("2403.01942")

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

curl https://syntology.ai/api/ran/2403.01942.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.01942.svg)](https://syntology.ai/paper/2403.01942)

Connect an agent — have() is free.