SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.06986 · 2021

How Framelets Enhance Graph Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

4 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 2 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/2102.06986.json · badge: /api/ran/2102.06986.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
YuGuangWang/UFG canonical (classifier label)
classifier basis: classifier_2025
4 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
0 ran · 1 no recorded run
FunctionStatusWhere it lives
multiScales Ran
ran; our contract draft was wrong, not the code
YuGuangWang/UFG/UFGConv_shrinkage.py
code served (permissive licence) · get_code("b3025b0ff7068ed8")
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 Tensor, ndim 1, dtype family float, shape (4,) 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

torch.manual_seed(0)

# Parameters for multiScales function
r = 3  # integer parameter
Lev = 2  # integer parameter (number of levels)
num_nodes = 4  # integer parameter (number of nodes in graph)

# x: shape [r * Lev * num_nodes, num_hid_features]
# r * Lev * num_nodes = 3 * 2 * 4 = 24 rows
# num_hid_features = 5 columns
num_hid_features = 5
x = torch.randn(r * Lev * num_nodes, num_hid_features)

ARGS = {
    "x": x,
    "r": r,
    "Lev": Lev,
    "num_nodes": num_nodes
}
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 Tensor, ndim 1, dtype family float, shape (4,) — shape (4,) 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
rigrsure Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
YuGuangWang/UFG/UFGConv_shrinkage.py
code served (permissive licence) · get_code("2aa2e71b340fc78d")
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 Tensor, ndim 1, dtype family float, shape (4,) 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

torch.manual_seed(0)

# Create small tensors with distinct dimensions
num_nodes = 2
num_hid_features = 4

# x: shape [num_nodes, num_hid_features]
x = torch.randn(num_nodes, num_hid_features)

# N1: shape [num_nodes, num_hid_features]
N1 = torch.randn(num_nodes, num_hid_features)

# N2: shape [num_nodes, num_hid_features]
N2 = torch.randn(num_nodes, num_hid_features)

# col_idx: shape [num_hid_features]
col_idx = torch.arange(num_hid_features)

ARGS = {
    "x": x,
    "N1": N1,
    "N2": N2,
    "col_idx": col_idx,
}
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 Tensor, ndim 1, dtype family float, shape (4,) — shape (4,) 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
scipy_to_torch_sparse Ran
ran; our contract draft was wrong, not the code
YuGuangWang/UFG/UFGConv_relu.py
code served (permissive licence) · get_code("de85f6168a586bd8")
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 Tensor. 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 scipy import sparse
import numpy as np

torch.manual_seed(0)

# Create a small sparse matrix using scipy
# The function expects something that can be converted to coo_matrix
data = np.array([1.0, 2.0, 3.0])
row = np.array([0, 1, 2])
col = np.array([0, 1, 2])
A_scipy = sparse.coo_matrix((data, (row, col)), shape=(3, 4))

ARGS = {
    "A": A_scipy
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, scipy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, shape (3, 4) — shape (3, 4) as a later run recorded it
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
simpleLambda Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
YuGuangWang/UFG/UFGConv_shrinkage.py
code served (permissive licence) · get_code("56a01306df343332")
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 Tensor, ndim 1, dtype family float, shape (4,) 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 math

torch.manual_seed(0)

# x: one block of wavelet coefficients, shape [num_nodes, num_hid_features]
x = torch.randn(2, 4)

# scale: a zero-dimensional torch tensor
scale = torch.tensor(0.5)

# sigma: a scalar constant, standard deviation of noise
sigma = 1.0

ARGS = {
    "x": x,
    "scale": scale,
    "sigma": sigma
}
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 Tensor, ndim 1, dtype family float, shape (4,) — shape (4,) 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
ChebyshevApprox Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from thisisforreview/svd-gcn
pointer only; the stored copy get_code serves, from thisisforreview/svd-gcn, is pointer only (licence: GPL-3.0) · get_code("34b82f5922857186")
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. No invocation recorded.

get_operator Not yet run
unverified (harvested, no recorded run)
YuGuangWang/UFG/UFGConv_relu.py
code served (permissive licence) · get_code("25d0341431feab5e")
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, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 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
ChebyshevApprox 2 other papers
2 later
2205.09335 (2022-05)
A Simple Yet Effective SVD-GCN for Directed Graphs
2307.09768 (2023-07)
How Curvature Enhance the Adaptation Power of Framelet GCNs
scipy_to_torch_sparse 2 other papers
2 later
2205.09335 (2022-05)
A Simple Yet Effective SVD-GCN for Directed Graphs
2307.09768 (2023-07)
How Curvature Enhance the Adaptation Power of Framelet GCNs
get_operator 1 other paper
1 later
2307.09768 (2023-07)
How Curvature Enhance the Adaptation Power of Framelet GCNs

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

This paper presents a new approach for assembling graph neural networks based on framelet transforms. The latter provides a multi-scale representation for graph-structured data. We decompose an input graph into low-pass and high-pass frequencies coefficients for network training, which then defines a framelet-based graph convolution. The framelet decomposition naturally induces a graph pooling strategy by aggregating the graph feature into low-pass and high-pass spectra, which considers both the feature values and geometry of the graph data and conserves the total information. The graph neural networks with the proposed framelet convolution and pooling achieve state-of-the-art performance in many node and graph prediction tasks. Moreover, we propose shrinkage as a new activation for the framelet convolution, which thresholds high-frequency information at different scales. Compared to ReLU, shrinkage activation improves model performance on denoising and signal compression: noises in both node and structure can be significantly reduced by accurately cutting off the high-pass coefficients from framelet decomposition, and the signal can be compressed to less than half its original size with well-preserved prediction performance.

For agents

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

get_harvested_code_for_paper("2102.06986")
get_code_for_paper("2102.06986")
have("2102.06986")

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

curl https://syntology.ai/api/ran/2102.06986.json

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

[![Syntology run record](https://syntology.ai/api/ran/2102.06986.svg)](https://syntology.ai/paper/2102.06986)

Connect an agent — have() is free.