SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.05563 · 2020

Graph Information Bottleneck for Subgraph Recognition

arXiv · PDF · Open in the Atlas

Code that ran

4 of 7 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 2 have no contract verdict; 1 failure 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/2010.05563.json · badge: /api/ran/2010.05563.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
Samyu0304/graph-information-bottleneck-for-Subgraph-Recognition canonical (classifier label)
classifier basis: census
4 ran · 3 no recorded run
FunctionStatusWhere it lives
graph_level_reader Ran
ran on a synthesized input
Samyu0304/graph-information-bottleneck-for-Subgraph-Recognition/graph-interpretation/model/utils.py
code served (permissive licence) · get_code("678727c26290b1bb")
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 dict. 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 json
import tempfile
import os

# Create a temporary JSON file with sample graph-level data
temp_dir = tempfile.mkdtemp()
temp_path = os.path.join(temp_dir, "graph_data.json")

# Write sample graph-level data to the JSON file
sample_data = {
    "graphs": [
        {
            "nodes": [0, 1, 2],
            "edges": [[0, 1], [1, 2]],
            "label": 0
        },
        {
            "nodes": [0, 1],
            "edges": [[0, 1]],
            "label": 1
        }
    ],
    "metadata": {
        "num_graphs": 2,
        "num_classes": 2
    }
}

with open(temp_path, 'w') as f:
    json.dump(sample_data, f)

ARGS = {
    "path": temp_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
hierarchical_graph_reader Ran
ran on a synthesized input
Samyu0304/graph-information-bottleneck-for-Subgraph-Recognition/graph-interpretation/model/utils.py
code served (permissive licence) · get_code("e7df7995c8536ad7")
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 Graph. 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 pandas as pd
import networkx as nx
import tempfile
import os

# Create a temporary CSV file with edge data
temp_dir = tempfile.gettempdir()
temp_file = os.path.join(temp_dir, "test_edges.csv")

# Write sample edge data to CSV
edge_data = pd.DataFrame([
    [0, 1],
    [1, 2],
    [2, 3],
    [0, 3]
], columns=['source', 'target'])
edge_data.to_csv(temp_file, index=False)

ARGS = {
    'path': temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
networkx, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Graph — a Graph output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Graph output the recorded ndim 1 and dtype family int 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
k_fold Ran
ran; our contract draft was wrong, not the code
Samyu0304/graph-information-bottleneck-for-Subgraph-Recognition/graph-classfication/ours_train_eval.py
code served (permissive licence) · get_code("8a60d7e1fd8f0dbe")
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 tuple. 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 torch.utils.data import Dataset

torch.manual_seed(0)

class MockDataset(Dataset):
    def __init__(self, num_samples=10, num_classes=2):
        self.num_samples = num_samples
        self.num_classes = num_classes
        # Create mock data with y labels for stratification
        self.data = type('obj', (object,), {
            'y': torch.randint(0, num_classes, (num_samples,))
        })()
    
    def __len__(self):
        return self.num_samples
    
    def __getitem__(self, idx):
        return torch.randn(4), self.data.y[idx]

dataset = MockDataset(num_samples=10, num_classes=2)
folds = 2

ARGS = {
    'dataset': dataset,
    'folds': folds
}
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 tuple — a tuple output has no array shape of its own; none is 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
num_graphs Ran
ran, honoured the contract we drafted
Samyu0304/graph-information-bottleneck-for-Subgraph-Recognition/graph-classfication/ours_train_eval.py
pointer only (licence: MIT); the stored copy get_code serves, from RingBDStack/VIB-GSL, is pointer only (licence: NONE) · get_code("9da87b0b1605a660")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from RingBDStack/VIB-GSL, and GitHub detected no licence in that repository 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.

cross_validation_with_val_set Not yet run
unverified (harvested, no recorded run)
Samyu0304/graph-information-bottleneck-for-Subgraph-Recognition/graph-classfication/ours_train_eval.py
code served (permissive licence) · get_code("003c863eba48841e")
How it ran

no invocation recorded.

get_dataset Not yet run
unverified (harvested, no recorded run)
Samyu0304/graph-information-bottleneck-for-Subgraph-Recognition/graph-classfication/datasets.py
code served (permissive licence) · get_code("447832767a387876")
How it ran

no invocation recorded.

preprocess Not yet run
unverified (harvested, no recorded run)
Samyu0304/graph-information-bottleneck-for-Subgraph-Recognition/graph-interpretation/preprocess.py
code served (permissive licence) · get_code("39bce85e40cd2642")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 2 the same month, 2 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.

FunctionAlso present inEarliest-datedOthers named
num_graphs 9 other papers
2 dated earlier, 1 the same month, 6 later
1904.12058 (2019-04)
Inductive Matrix Completion Based on Graph Neural Networks
2002.06757 (2020-02)
Relational Message Passing for Knowledge Graph Completion
2010.12811 (2020-10)
Graph Information Bottleneck
and 6 more not named here
k_fold 2 other papers
1 the same month, 1 later
2010.12811 (2020-10)
Graph Information Bottleneck
2310.19906 (2023-10)
Interpretable Prototype-based Graph Information Bottleneck

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

Given the input graph and its label/property, several key problems of graph learning, such as finding interpretable subgraphs, graph denoising and graph compression, can be attributed to the fundamental problem of recognizing a subgraph of the original one. This subgraph shall be as informative as possible, yet contains less redundant and noisy structure. This problem setting is closely related to the well-known information bottleneck (IB) principle, which, however, has less been studied for the irregular graph data and graph neural networks (GNNs). In this paper, we propose a framework of Graph Information Bottleneck (GIB) for the subgraph recognition problem in deep graph learning. Under this framework, one can recognize the maximally informative yet compressive subgraph, named IB-subgraph. However, the GIB objective is notoriously hard to optimize, mostly due to the intractability of the mutual information of irregular graph data and the unstable optimization process. In order to tackle these challenges, we propose: i) a GIB objective based-on a mutual information estimator for the irregular graph data; ii) a bi-level optimization scheme to maximize the GIB objective; iii) a connectivity loss to stabilize the optimization process. We evaluate the properties of the IB-subgraph in three application scenarios: improvement of graph classification, graph interpretation and graph denoising. Extensive experiments demonstrate that the information-theoretic IB-subgraph enjoys superior graph properties.

For agents

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

get_harvested_code_for_paper("2010.05563")
get_code_for_paper("2010.05563")
have("2010.05563")

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

curl https://syntology.ai/api/ran/2010.05563.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.05563.svg)](https://syntology.ai/paper/2010.05563)

Connect an agent — have() is free.