SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.13538 · 2022

Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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 3 have no contract verdict; 0 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/2202.13538.json · badge: /api/ran/2202.13538.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
Graph-COM/SUREL community (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
FunctionStatusWhere it lives
coarse Ran
ran on a synthesized input
Graph-COM/SUREL/utils.py
code served (permissive licence) · get_code("0fdeb046a801c22b")
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)

# Construct Tx: a list/array of node indices for the coarse level
Tx = np.array([0, 2, 5, 7])

# Construct K: a list of lists, where each sublist contains node indices
# for the fine level that map to a coarse node
K = [
    [10, 11, 12],      # maps to Tx[0]
    [20, 21],          # maps to Tx[1]
    [30, 31, 32, 33],  # maps to Tx[2]
    [40]               # maps to Tx[3]
]

ARGS = {
    "Tx": Tx,
    "K": K
}
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
log_record Ran
ran on a synthesized input
Graph-COM/SUREL/log.py
code served (permissive licence) · get_code("a31e995e7c3a76f0")
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 bool, 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 numpy as np
from unittest.mock import MagicMock

torch.manual_seed(0)

# Create a mock logger
logger = MagicMock()

# Create a mock tensorboard writer
tb = MagicMock()

# Create output dict for 'mrr' metric case
out_mrr = {
    'mode': 'val',
    'metric': 'mrr',
    'auc': 0.85,
    'mrr_list': torch.tensor([0.75, 0.80, 0.82])
}

# Create output dict for 'Hit' metric case
out_hit = {
    'mode': 'val',
    'metric': 'Hit@10',
    'auc': 0.87,
    'hits': {'Hit@1': 0.5, 'Hit@10': 0.75, 'Hit@20': 0.85},
    'num_pos': 100
}

# Create the dic that tracks metrics
dic = {
    'val_mrr': [0.70, 0.72, 0.74],
    'val_AUC': [0.80, 0.82, 0.84],
    'val_Hit@10': [0.70, 0.72, 0.74],
    'test_mrr': [0.68, 0.71],
    'test_AUC': [0.79, 0.81],
    'test_Hit@10': [0.68, 0.70]
}

# Time tracking
b_time = 1000.0  # Arbitrary start time in past

# Batch index
batchIdx = 5

ARGS = {
    'logger': logger,
    'tb': tb,
    'out': out_mrr,
    'dic': dic,
    'b_time': b_time,
    'batchIdx': batchIdx
}
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 bool, 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
sample Ran
ran, honoured the contract we drafted
Graph-COM/SUREL/utils.py
code served (permissive licence) · get_code("bc1dcc2918a66084")
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 int, 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 random
import torch

torch.manual_seed(0)

ARGS = {
    "high": 10,
    "size": 5,
    "device": None
}
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 int, 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
save_to_file Ran
ran on a synthesized input
Graph-COM/SUREL/log.py
code served (permissive licence) · get_code("d4a8ee5b59e3b881")
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 os
import numpy as np
import logging

# Create a simple logger
logger = logging.getLogger('test_logger')
logger.setLevel(logging.INFO)
handler = logging.StreamHandler()
logger.addHandler(handler)

# Create a simple args class
class Args:
    def __init__(self):
        self.use_weight = True
        self.save = False
        self.use_val = True
        self.res_dir = '/tmp/test_res'
        self.dataset = 'test_dataset'
        self.num_step = 5
        self.num_walk = 3
        self.dtype = 'test'

args = Args()

# Create the dictionary with the expected structure
# Based on the function, save_dict should have entries with (walks, ids, freqs) tuples
# and a 'num' key that will be popped
dic = {
    'num': 42,
    'entry_1': ([1, 2, 3], [10, 20], [0.5, 0.6]),
    'entry_2': ([4, 5, 6], [30, 40], [0.7, 0.8]),
}

dtype = 'test'

ARGS = {
    'dic': dic,
    'args': args,
    'logger': logger,
    'dtype': dtype
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — 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

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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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
sample 1 other paper
1 dated earlier
2109.01785 (2021-09)
Node Feature Kernels Increase Graph Convolutional Network Robustness

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

Subgraph-based graph representation learning (SGRL) has been recently proposed to deal with some fundamental challenges encountered by canonical graph neural networks (GNNs), and has demonstrated advantages in many important data science applications such as link, relation and motif prediction. However, current SGRL approaches suffer from scalability issues since they require extracting subgraphs for each training or test query. Recent solutions that scale up canonical GNNs may not apply to SGRL. Here, we propose a novel framework SUREL for scalable SGRL by co-designing the learning algorithm and its system support. SUREL adopts walk-based decomposition of subgraphs and reuses the walks to form subgraphs, which substantially reduces the redundancy of subgraph extraction and supports parallel computation. Experiments over six homogeneous, heterogeneous and higher-order graphs with millions of nodes and edges demonstrate the effectiveness and scalability of SUREL. In particular, compared to SGRL baselines, SUREL achieves 10$\times$ speed-up with comparable or even better prediction performance; while compared to canonical GNNs, SUREL achieves 50% prediction accuracy improvement.

For agents

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

get_harvested_code_for_paper("2202.13538")
get_code_for_paper("2202.13538")
have("2202.13538")

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

curl https://syntology.ai/api/ran/2202.13538.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.13538.svg)](https://syntology.ai/paper/2202.13538)

Connect an agent — have() is free.