SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.02404 · IJCAI · 2022

A Simple yet Effective Method for Graph Classification

Ke Xu, Junran Wu, Shangzhe Li, Yicheng Pan, Jianhao Li

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 1 failure of our instrument; 1 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/2206.02404.json · badge: /api/ran/2206.02404.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
wu-junran/hierarchicalreporting marked official in Papers with Code
Papers with Code archive
3 ran · 1 no recorded run
FunctionStatusWhere it lives
PartitionTree Ran
ran on a synthesized input · constructed an object; no result was computed
wu-junran/hierarchicalreporting/lib/coding_tree.py
code served (permissive licence) · get_code("3ae8a5fe1798511d")
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, PartitionTree: 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 numpy as np
import math

class PartitionTreeNode:
    def __init__(self, ID, partition, vol, g, children=None, parent=None, child_h=0, child_cut=0):
        self.ID = ID
        self.partition = partition
        self.parent = parent
        self.children = children if children is not None else set()
        self.vol = vol
        self.g = g
        self.merged = False
        self.child_h = child_h
        self.child_cut = child_cut

    def __str__(self):
        return '{' + '{}:{}'.format(self.__class__.__name__, self.gatherAttrs()) + '}'

    def gatherAttrs(self):
        return ','.join(('{}={}'.format(k, getattr(self, k)) for k in self.__dict__.keys()))

# Create a small adjacency matrix for a simple graph
# 4x4 matrix representing 4 nodes with some edges
adj_matrix = np.array([
    [0, 1, 1, 0],
    [1, 0, 1, 1],
    [1, 1, 0, 1],
    [0, 1, 1, 0]
], dtype=np.float32)

ARGS = {
    "adj_matrix": adj_matrix
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numba, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PartitionTree — 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 PartitionTree 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
PartitionTreeNode Ran
ran on a synthesized input · constructed an object; no result was computed
wu-junran/hierarchicalreporting/lib/coding_tree.py
code served (permissive licence) · get_code("fde92ce7415b6f1c")
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, PartitionTreeNode: 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)

# Construct arguments for PartitionTreeNode.__init__
ARGS = {
    'ID': 1,
    'partition': np.array([0, 1, 2, 3]),
    'vol': 42.5,
    'g': torch.randn(4, 3),
    'children': {2, 3},
    'parent': None,
    'child_h': 5,
    'child_cut': 10,
}
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 PartitionTreeNode — 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 PartitionTreeNode 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
graph_parse Ran
ran; our contract draft was wrong, not the code
wu-junran/hierarchicalreporting/lib/coding_tree.py
code served (permissive licence) · get_code("21dda7ecf92b5b2c")
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 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
import numpy as np

torch.manual_seed(0)

# Create a small adjacency matrix
# The function expects a matrix where adj_matrix[i, j] represents edge weight from node i to node j
# Using a 4x4 matrix for a small graph
adj_matrix = np.array([
    [0, 1, 2, 0],
    [1, 0, 0, 3],
    [2, 0, 0, 1],
    [0, 3, 1, 0]
], dtype=np.float32)

ARGS = {
    'adj_matrix': adj_matrix
}
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 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
merge Not yet run
unverified (harvested, no recorded run)
wu-junran/hierarchicalreporting/lib/coding_tree.py
code served (permissive licence) · get_code("d5cbf6bb01288b04")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 1 the same month, 4 later) and 0 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
graph_parse
brick of this paper's assembly: helper
6 other papers
1 the same month, 5 later · 2 only as an assembly brick
2206.13510 (2022-06)
Structural Entropy Guided Graph Hierarchical Pooling
2304.12000 (2023-04)
Hierarchical State Abstraction Based on Structural Information Principles
2305.04501 (2023-05)
SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning
and 3 more not named here
PartitionTreeNode
brick of this paper's assembly: helper
2 other papers
2 later · 2 only as an assembly brick
2304.12000 (2023-04)
Hierarchical State Abstraction Based on Structural Information Principles
2305.04501 (2023-05)
SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning
merge
brick of this paper's assembly: model
2 other papers
2 later · 2 only as an assembly brick
2304.12000 (2023-04)
Hierarchical State Abstraction Based on Structural Information Principles
2305.04501 (2023-05)
SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning
PartitionTree
brick of this paper's assembly: entry
1 other paper
1 later
2304.12000 (2023-04)
Hierarchical State Abstraction Based on Structural Information Principles

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

In deep neural networks, better results can often be obtained by increasing the complexity of previously developed basic models. However, it is unclear whether there is a way to boost performance by decreasing the complexity of such models. Intuitively, given a problem, a simpler data structure comes with a simpler algorithm. Here, we investigate the feasibility of improving graph classification performance while simplifying the learning process. Inspired by structural entropy on graphs, we transform the data sample from graphs to coding trees, which is a simpler but essential structure for graph data. Furthermore, we propose a novel message passing scheme, termed hierarchical reporting, in which features are transferred from leaf nodes to root nodes by following the hierarchical structure of coding trees. We then present a tree kernel and a convolutional network to implement our scheme for graph classification. With the designed message passing scheme, the tree kernel and convolutional network have a lower runtime complexity of O(n) than Weisfeiler-Lehman subtree kernel and other graph neural networks of at least O(hm). We empirically validate our methods with several graph classification benchmarks and demonstrate that they achieve better performance and lower computational consumption than competing approaches.

For agents

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

get_harvested_code_for_paper("2206.02404")
get_code_for_paper("2206.02404")
have("2206.02404")

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

curl https://syntology.ai/api/ran/2206.02404.json

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

[![Syntology run record](https://syntology.ai/api/ran/2206.02404.svg)](https://syntology.ai/paper/2206.02404)

Connect an agent — have() is free.