SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.00583 · 2022

Calibrate and Debias Layer-wise Sampling for Graph Convolutional Networks

arXiv · PDF · Open in the Atlas

Code that ran

2 of 6 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; 1 failure of our instrument; 4 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/2206.00583.json · badge: /api/ran/2206.00583.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
ychen-stat-ml/gcn-layer-wise-sampling canonical (classifier label)
classifier basis: classifier_2025
1 ran · 4 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
load_data_graphsage Ran
ran; our contract draft was wrong, not the code
ychen-stat-ml/gcn-layer-wise-sampling/sketch/utils_new.py
code served (permissive licence) · get_code("643e0b76db2096e9")
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 numpy as np
import json
import tempfile
import os
import networkx as nx
from networkx.readwrite import json_graph

# Create temporary directory for files
temp_dir = tempfile.mkdtemp()
prefix = os.path.join(temp_dir, "test_graph")

# Create a simple graph structure
G = nx.Graph()
nodes = [0, 1, 2, 3, 4]
for node in nodes:
    G.add_node(node, val=False, test=False)

G.add_edges_from([(0, 1), (1, 2), (2, 3), (3, 4), (0, 2)])

# Add train_removed attribute to edges
for edge in G.edges():
    G[edge[0]][edge[1]]['train_removed'] = False

# Save graph as JSON
G_data = json_graph.node_link_data(G)
with open(prefix + '-G.json', 'w') as f:
    json.dump(G_data, f)

# Create feature matrix (5 nodes x 4 features)
feats = np.random.randn(5, 4).astype(np.float32)
np.save(prefix + '-feats.npy', feats)

# Create id_map (node id to feature index)
id_map = {str(i): i for i in range(5)}
with open(prefix + '-id_map.json', 'w') as f:
    json.dump(id_map, f)

# Create class_map (node id to class label)
class_map = {str(i): i % 2 for i in range(5)}
with open(prefix + '-class_map.json', 'w') as f:
    json.dump(class_map, f)

# Create walks file
with open(prefix + '-walks.txt', 'w') as f:
    f.write("0 1 2 3\n")
    f.write("4 3 2 1\n")

ARGS = {
    'prefix': prefix,
    'normalize': True,
    'load_walks': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
networkx, numpy, sklearn — 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
parse_index_file Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from DSL-Lab/Specformer
pointer only; the stored copy get_code serves, from DSL-Lab/Specformer, is pointer only (licence: GPL-3.0) · get_code("c1d6392f89c5e495")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

fastgcn_sampler Not yet run
unverified (harvested, no recorded run)
ychen-stat-ml/gcn-layer-wise-sampling/sketch/samplers.py
code served (permissive licence) · get_code("0671c5cd513a2c2b")
How it ran

no invocation recorded.

fastgcn_sampler_custom Not yet run
unverified (harvested, no recorded run)
ychen-stat-ml/gcn-layer-wise-sampling/sketch/samplers.py
code served (permissive licence) · get_code("260cca862d49474d")
How it ran

no invocation recorded.

ladies_sampler Not yet run
unverified (harvested, no recorded run)
ychen-stat-ml/gcn-layer-wise-sampling/sketch/samplers.py
code served (permissive licence) · get_code("28a9028cace2e0ac")
How it ran

no invocation recorded.

run_random_walks Not yet run
unverified (harvested, no recorded run)
ychen-stat-ml/gcn-layer-wise-sampling/sketch/utils_new.py
code served (permissive licence) · get_code("be0d0a2bfb17216b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 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
parse_index_file 53 other papers
34 dated earlier, 1 the same month, 15 later, 3 same year, order not determinable · 1 only as an assembly brick
1603.08861 (2016-03)
Revisiting Semi-Supervised Learning with Graph Embeddings
1611.07308 (2016-11)
Variational Graph Auto-Encoders
1710.10568 (2017-10)
Stochastic Training of Graph Convolutional Networks with Variance Reduction
and 50 more not named here

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

Multiple sampling-based methods have been developed for approximating and accelerating node embedding aggregation in graph convolutional networks (GCNs) training. Among them, a layer-wise approach recursively performs importance sampling to select neighbors jointly for existing nodes in each layer. This paper revisits the approach from a matrix approximation perspective, and identifies two issues in the existing layer-wise sampling methods: suboptimal sampling probabilities and estimation biases induced by sampling without replacement. To address these issues, we accordingly propose two remedies: a new principle for constructing sampling probabilities and an efficient debiasing algorithm. The improvements are demonstrated by extensive analyses of estimation variance and experiments on common benchmarks. Code and algorithm implementations are publicly available at https://github.com/ychen-stat-ml/GCN-layer-wise-sampling .

For agents

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

get_harvested_code_for_paper("2206.00583")
get_code_for_paper("2206.00583")
have("2206.00583")

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

curl https://syntology.ai/api/ran/2206.00583.json

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

[![Syntology run record](https://syntology.ai/api/ran/2206.00583.svg)](https://syntology.ai/paper/2206.00583)

Connect an agent — have() is free.