SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.13604 · ICML · 2024

CKGConv: General Graph Convolution with Continuous Kernels

Soumyasundar Pal, Liheng Ma, Yingxue Zhang, Mark Coates, Yitian Zhang, Jiaming Zhou

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 3 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/2404.13604.json · badge: /api/ran/2404.13604.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
networkslab/CKGConv canonical (classifier label)
classifier basis: census
8 ran · 3 no recorded run
FunctionStatusWhere it lives
accuracy_SBM Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
networkslab/CKGConv/ckgconv/logger.py
pointer only (licence: NONE) · get_code("ecf14287d3465c48")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, networkslab/CKGConv when it was checked. 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.

eval_spearmanr Ran
ran; our contract draft was wrong, not the code
networkslab/CKGConv/ckgconv/logger.py
pointer only (licence: NONE) · get_code("9dc78001d467fc9d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, networkslab/CKGConv when it was checked. 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.

get_final_pretrained_ckpt Ran
ran; our contract draft was wrong, not the code
networkslab/CKGConv/ckgconv/finetuning.py
pointer only (licence: NONE) · get_code("1bb331bf70a78136")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, networkslab/CKGConv when it was checked. 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.

get_log_deg Ran
ran, honoured the contract we drafted
networkslab/CKGConv/ckgconv/layer/ckgconv_layer.py
pointer only (licence: NONE) · get_code("b5c9e7acf599a98a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, networkslab/CKGConv when it was checked. 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.

get_sqrt_deg Ran
ran, honoured the contract we drafted
networkslab/CKGConv/ckgconv/layer/ckgconv_layer.py
pointer only (licence: NONE) · get_code("ef96c45530e5a76b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, networkslab/CKGConv when it was checked. 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.

init_model_from_pretrained Ran
ran; our contract draft was wrong, not the code
networkslab/CKGConv/ckgconv/finetuning.py
pointer only (licence: NONE) · get_code("309b367fdc9f4994")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, networkslab/CKGConv when it was checked. 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.

load_pretrained_model_cfg Ran
ran; our contract draft was wrong, not the code
networkslab/CKGConv/ckgconv/finetuning.py
pointer only (licence: NONE) · get_code("bdfc097c2a07782f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, networkslab/CKGConv when it was checked. 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.

subtoken_cross_entropy Ran
ran; our contract draft was wrong, not the code
networkslab/CKGConv/ckgconv/loss/subtoken_prediction_loss.py
pointer only (licence: NONE) · get_code("47e492109e6d308f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, networkslab/CKGConv when it was checked. 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.

adj_l1_losses Not yet run
unverified (harvested, no recorded run)
networkslab/CKGConv/ckgconv/loss/adj.py
pointer only (licence: NONE) · get_code("dc82c18c9d42c1c1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, networkslab/CKGConv when it was checked. 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.

l1_losses Not yet run
unverified (harvested, no recorded run)
networkslab/CKGConv/ckgconv/loss/l1.py
pointer only (licence: NONE) · get_code("d59c374db2cf64ae")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, networkslab/CKGConv when it was checked. 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.

multilabel_cross_entropy Not yet run
unverified (harvested, no recorded run)
networkslab/CKGConv/ckgconv/loss/multilabel_classification_loss.py
pointer only (licence: NONE) · get_code("f1cbbbc857d8b871")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, networkslab/CKGConv when it was checked. 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.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 2 the same month, 8 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
get_final_pretrained_ckpt 27 other papers
14 dated earlier, 1 the same month, 12 later
2302.04181 (2023-02)
Attending to Graph Transformers
2302.08647 (2023-02)
Multiresolution Graph Transformers and Wavelet Positional Encoding for Learning Hierarchical Structures
2305.08018 (2023-05)
DRew: Dynamically Rewired Message Passing with Delay
and 24 more not named here
eval_spearmanr 6 other papers
1 dated earlier, 5 later
2305.17589 (2023-05)
Graph Inductive Biases in Transformers without Message Passing
2405.13806 (2024-05)
A General Graph Spectral Wavelet Convolution via Chebyshev Order Decomposition
2405.16435 (2024-05)
Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning
and 3 more not named here
accuracy_SBM 5 other papers
1 dated earlier, 4 later
2305.17589 (2023-05)
Graph Inductive Biases in Transformers without Message Passing
2405.13806 (2024-05)
A General Graph Spectral Wavelet Convolution via Chebyshev Order Decomposition
2411.16278 (2024-11)
Even Sparser Graph Transformers
and 2 more not named here
get_log_deg 5 other papers
2 dated earlier, 1 the same month, 2 later
2305.17589 (2023-05)
Graph Inductive Biases in Transformers without Message Passing
2310.19285 (2023-10)
Facilitating Graph Neural Networks with Random Walk on Simplicial Complexes
2404.03380 (2024-04)
On the Theoretical Expressive Power and the Design Space of Higher-Order Graph Transformers
and 2 more not named here
l1_losses 5 other papers
1 dated earlier, 4 later
2305.17589 (2023-05)
Graph Inductive Biases in Transformers without Message Passing
2405.13806 (2024-05)
A General Graph Spectral Wavelet Convolution via Chebyshev Order Decomposition
2411.16278 (2024-11)
Even Sparser Graph Transformers
and 2 more not named here
multilabel_cross_entropy 5 other papers
1 dated earlier, 4 later
2305.17589 (2023-05)
Graph Inductive Biases in Transformers without Message Passing
2405.13806 (2024-05)
A General Graph Spectral Wavelet Convolution via Chebyshev Order Decomposition
2411.16278 (2024-11)
Even Sparser Graph Transformers
and 2 more not named here
subtoken_cross_entropy 3 other papers
1 dated earlier, 2 later
2305.17589 (2023-05)
Graph Inductive Biases in Transformers without Message Passing
2502.09263 (2025-02)
Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence
2606.14259 (2026-06)
Beyond a Single Explanation of the Adam-SGD Gap
adj_l1_losses 2 other papers
1 dated earlier, 1 later
2305.17589 (2023-05)
Graph Inductive Biases in Transformers without Message Passing
2606.14259 (2026-06)
Beyond a Single Explanation of the Adam-SGD Gap

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

The existing definitions of graph convolution, either from spatial or spectral perspectives, are inflexible and not unified. Defining a general convolution operator in the graph domain is challenging due to the lack of canonical coordinates, the presence of irregular structures, and the properties of graph symmetries. In this work, we propose a novel and general graph convolution framework by parameterizing the kernels as continuous functions of pseudo-coordinates derived via graph positional encoding. We name this Continuous Kernel Graph Convolution (CKG-Conv). Theoretically, we demonstrate that CK-GConv is flexible and expressive. CKGConv encompasses many existing graph convolutions, and exhibits a stronger expressiveness, as powerful as graph transformers in terms of distinguishing non-isomorphic graphs. Empirically, we show that CKGConv-based Networks outperform existing graph convolutional networks and perform comparably to the best graph transformers across a variety of graph datasets. The code and models are publicly available at https: //github.com/networkslab/CKGConv.

For agents

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

get_harvested_code_for_paper("2404.13604")
get_code_for_paper("2404.13604")
have("2404.13604")

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

curl https://syntology.ai/api/ran/2404.13604.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.13604.svg)](https://syntology.ai/paper/2404.13604)

Connect an agent — have() is free.