SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.04099 · NeurIPS · 2021

Topology-Imbalance Learning for Semi-Supervised Node Classification

Peng Li, Jie Zhou, Xu Sun, Deli Chen, Yankai Lin, Guangxiang Zhao, Xuancheng Ren

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 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; 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/2110.04099.json · badge: /api/ran/2110.04099.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
victorchen96/renode canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
IMB_LOSS Ran
ran on a synthesized input · constructed an object; no result was computed
victorchen96/renode/transductive/imb_loss.py
code served (permissive licence) · get_code("bf31c456b229af92")
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 an instance of its own class, IMB_LOSS: the run constructed the object and did not call it, so no result was computed. 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

torch.manual_seed(0)

# Create a minimal opt object with required attributes
class Opt:
    def __init__(self):
        self.device = 'cpu'
        self.factor_focal = 2.0
        self.factor_cb = 0.9999

opt = Opt()

# Create a minimal data object with required attributes
class Data:
    def __init__(self):
        self.num_classes = 4
        # train_node should be a list of lists, each representing samples per class
        self.train_node = [
            [1, 2, 3, 4, 5],           # class 0: 5 samples
            [1, 2],                    # class 1: 2 samples
            [1, 2, 3, 4],              # class 2: 4 samples
            [1, 2, 3]                  # class 3: 3 samples
        ]

data = Data()

ARGS = {
    'loss_name': 'focal',
    'opt': opt,
    'data': data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type IMB_LOSS — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a IMB_LOSS 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
focal_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
victorchen96/renode/transductive/imb_loss.py
code served (permissive licence) · get_code("6ccd040c4ef8720b")
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 Tensor, ndim 1, dtype family float, 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 torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create small tensors for the function
batch_size = 2
num_features = 4

# labels: binary labels, shape (batch_size, num_features)
labels = torch.randint(0, 2, (batch_size, num_features)).float()

# logits: raw model outputs, shape (batch_size, num_features)
logits = torch.randn(batch_size, num_features)

# alpha: weighting factor for the loss
alpha = 0.25

# gamma: focusing parameter
gamma = 2.0

ARGS = {
    "labels": labels,
    "logits": logits,
    "alpha": alpha,
    "gamma": gamma,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 1, dtype family float, 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
test Ran
ran; our contract draft was wrong, not the code
victorchen96/renode/transductive/transductive_run.py
code served (permissive licence) · get_code("884a6792e888cfc4")
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 float, ndim 0, dtype family float, shape () 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 torch.nn as nn
from sklearn.metrics import f1_score

torch.manual_seed(0)

# Create a minimal options object with device attribute
class OptConfig:
    def __init__(self):
        self.device = torch.device('cpu')

opt = OptConfig()

# Create a minimal model that takes x and adj as input
class MinimalModel(nn.Module):
    def __init__(self, input_dim, num_classes):
        super().__init__()
        self.linear = nn.Linear(input_dim, num_classes)
    
    def forward(self, x, adj):
        # Simple forward pass ignoring adj for this minimal example
        return self.linear(x)

model = MinimalModel(input_dim=4, num_classes=3)

# Create a minimal data object with x and y attributes
class Data:
    def __init__(self):
        self.x = torch.randn(5, 4)  # 5 nodes, 4 features
        self.y = torch.tensor([0, 1, 2, 1, 0])  # 5 labels

data = Data()

# Create adjacency matrix (5x5 for 5 nodes)
adj = torch.eye(5)

# Create target mask (select indices 2, 3, 4 for testing)
target_mask = torch.tensor([False, False, True, True, True])

ARGS = {
    'opt': opt,
    'model': model,
    'data': data,
    'adj': adj,
    'target_mask': target_mask,
    'test_type': ''
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
sklearn, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () 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

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 (0 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
focal_loss
brick of this paper's assembly: loss
1 other paper
1 later
2308.14181 (2023-08)
Class-Imbalanced Graph Learning without Class Rebalancing

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

The class imbalance problem, as an important issue in learning node representations, has drawn increasing attention from the community. Although the imbalance considered by existing studies roots from the unequal quantity of labeled examples in different classes (quantity imbalance), we argue that graph data expose a unique source of imbalance from the asymmetric topological properties of the labeled nodes, i.e., labeled nodes are not equal in terms of their structural role in the graph (topology imbalance). In this work, we first probe the previously unknown topology-imbalance issue, including its characteristics, causes, and threats to semisupervised node classification learning. We then provide a unified view to jointly analyzing the quantity-and topology-imbalance issues by considering the node influence shift phenomenon with the Label Propagation algorithm. In light of our analysis, we devise an influence conflict detection-based metric Totoro to measure the degree of graph topology imbalance and propose a model-agnostic method ReNode to address the topology-imbalance issue by re-weighting the influence of labeled nodes adaptively based on their relative positions to class boundaries. Systematic experiments demonstrate the effectiveness and generalizability of our method in relieving topology-imbalance issue and promoting semi-supervised node classification. The further analysis unveils varied sensitivity of different graph neural networks (GNNs) to topology imbalance, which may serve as a new perspective in evaluating GNN architectures. 1

For agents

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

get_harvested_code_for_paper("2110.04099")
get_code_for_paper("2110.04099")
have("2110.04099")

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

curl https://syntology.ai/api/ran/2110.04099.json

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

[![Syntology run record](https://syntology.ai/api/ran/2110.04099.svg)](https://syntology.ai/paper/2110.04099)

Connect an agent — have() is free.