SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1802.06257 · 2018

REGAL: Representation Learning-based Graph Alignment

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 (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; 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/1802.06257.json · badge: /api/ran/1802.06257.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
GemsLab/REGAL canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
get_degree_sequence Ran
ran; our contract draft was wrong, not the code
GemsLab/REGAL/xnetmf.py
code served (permissive licence) · get_code("c21f49823f5c274f")
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 list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 math
import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a stand-in class for rep_method
class RepMethod:
    def __init__(self, num_buckets=None):
        self.num_buckets = num_buckets

# Create a stand-in class for graph
class Graph:
    def __init__(self, max_degree, node_degrees):
        self.max_degree = max_degree
        self.node_degrees = node_degrees

# Set up test data
max_degree = 10
node_degrees = {0: 2, 1: 5, 2: 8, 3: 3, 4: 1}
kneighbors = [0, 1, 2, 3, 4]

graph = Graph(max_degree=max_degree, node_degrees=node_degrees)
rep_method = RepMethod(num_buckets=None)
current_node = 0

ARGS = {
    "graph": graph,
    "rep_method": rep_method,
    "kneighbors": kneighbors,
    "current_node": current_node
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
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
get_features Ran
ran, honoured the contract we drafted
GemsLab/REGAL/xnetmf.py
code served (permissive licence) · get_code("91a5d50365f220e5")
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 ndarray, ndim 2, dtype family float, shape (4, 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 numpy as np
import math

class MockGraph:
    def __init__(self):
        # Create a small graph with 4 nodes
        self.N = 4
        # Adjacency matrix: sparse representation
        # Node 0 connects to 1, 2
        # Node 1 connects to 0, 2, 3
        # Node 2 connects to 0, 1
        # Node 3 connects to 1
        self.G_adj = np.array([
            [0, 1, 1, 0],
            [1, 0, 1, 1],
            [1, 1, 0, 0],
            [0, 1, 0, 0]
        ], dtype=np.int32)
        
        # Calculate node degrees
        self.node_degrees = np.array([2, 3, 2, 1], dtype=np.int32)
        self.max_degree = 3
        self.khop_neighbors = {}

class MockRepMethod:
    def __init__(self):
        self.max_layer = None
        self.num_buckets = 2
        self.alpha = 0.5

graph = MockGraph()
rep_method = MockRepMethod()

ARGS = {
    "graph": graph,
    "rep_method": rep_method,
    "verbose": True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
networkx, numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (4, 2) — shape (4, 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
get_khop_neighbors Ran
ran; our contract draft was wrong, not the code
GemsLab/REGAL/xnetmf.py
code served (permissive licence) · get_code("0a599cedefca516a")
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 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 numpy as np
import scipy as sp
import networkx as nx

class Graph:
    def __init__(self, N, G_adj):
        self.N = N
        self.G_adj = G_adj

class RepMethod:
    def __init__(self, max_layer=None):
        self.max_layer = max_layer

# Create a small graph with 4 nodes
N = 4
# Adjacency matrix: sparse representation
# Node 0 connects to 1, 2
# Node 1 connects to 0, 2, 3
# Node 2 connects to 0, 1
# Node 3 connects to 1
G_adj = np.array([
    [0, 1, 1, 0],
    [1, 0, 1, 1],
    [1, 1, 0, 0],
    [0, 1, 0, 0]
], dtype=np.int32)

graph = Graph(N=N, G_adj=G_adj)
rep_method = RepMethod(max_layer=None)

ARGS = {
    "graph": graph,
    "rep_method": rep_method
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
networkx, numpy, scipy — 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 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, 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 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.

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

Problems involving multiple networks are prevalent in many scientific and other domains. In particular, network alignment, or the task of identifying corresponding nodes in different networks, has applications across the social and natural sciences. Motivated by recent advancements in node representation learning for single-graph tasks, we propose REGAL (REpresentation learning-based Graph ALignment), a framework that leverages the power of automatically-learned node representations to match nodes across different graphs. Within REGAL we devise xNetMF, an elegant and principled node embedding formulation that uniquely generalizes to multi-network problems. Our results demonstrate the utility and promise of unsupervised representation learning-based network alignment in terms of both speed and accuracy. REGAL runs up to 30x faster in the representation learning stage than comparable methods, outperforms existing network alignment methods by 20 to 30% accuracy on average, and scales to networks with millions of nodes each.

For agents

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

get_harvested_code_for_paper("1802.06257")
get_code_for_paper("1802.06257")
have("1802.06257")

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

curl https://syntology.ai/api/ran/1802.06257.json

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

[![Syntology run record](https://syntology.ai/api/ran/1802.06257.svg)](https://syntology.ai/paper/1802.06257)

Connect an agent — have() is free.