SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2201.00491 · AAAI · 2022

KerGNNs: Interpretable Graph Neural Networks with Graph Kernels

Shiqiang Wang, Chenyu You, Aosong Feng, Leandros Tassiulas

arXiv · PDF · Open in the Atlas

Code that ran

1 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; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 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/2201.00491.json · badge: /api/ran/2201.00491.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
asfeng/kergnns marked official in Papers with Code
Papers with Code archive
1 ran · 3 no recorded run
FunctionStatusWhere it lives
MLP Ran
ran on a synthesized input
asfeng/kergnns/model.py
code served (permissive licence) · get_code("0e8fe71f2a962fa3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 2, dtype family float, shape (2, 3) 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 torch.nn as nn
import torch.nn.functional as F

class MLP(nn.Module):

    def __init__(self, num_layers, input_dim, hidden_dim, output_dim, dropout_rate=0.5):
        """
            num_layers: number of layers in the neural networks (EXCLUDING the input layer). If num_layers=1, this reduces to linear model.
            input_dim: dimensionality of input features
            hidden_dim: dimensionality of hidden units at ALL layers
            output_dim: number of classes for prediction
        """
        super(MLP, self).__init__()
        self.linear_or_not = True
        self.num_layers = num_layers
        self.dropout_rate = dropout_rate
        if num_layers < 1:
            raise ValueError('number of layers should be positive!')
        elif num_layers == 1:
            self.linear = nn.Linear(input_dim, output_dim)
        else:
            self.linear_or_not = False
            self.linears = torch.nn.ModuleList()
            self.linears.append(nn.Linear(input_dim, hidden_dim))
            for layer in range(num_layers - 2):
                self.linears.append(nn.Linear(hidden_dim, hidden_dim))
            self.linears.append(nn.Linear(hidden_dim, output_dim))

    def forward(self, x):
        if self.linear_or_not:
            return self.linear(x)
        else:
            h = x
            for layer in range(self.num_layers - 1):
                h = nn.Dropout(p=self.dropout_rate)(F.relu(self.linears[layer](h)))
            return self.linears[self.num_layers - 1](h)


INIT_ARGS = {
    'num_layers': 2,
    'input_dim': 4,
    'hidden_dim': 8,
    'output_dim': 3,
    'dropout_rate': 0.5
}

ARGS = {
    'x': torch.randn(2, 4)
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 2, dtype family float, shape (2, 3) — shape (2, 3) 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
DRW_layer Not yet run
unverified (harvested, no recorded run)
asfeng/kergnns/model.py
code served (permissive licence) · get_code("62fe7577be7d670a")
How it ran

no invocation recorded.

RW_layer Not yet run
unverified (harvested, no recorded run)
asfeng/kergnns/model.py
code served (permissive licence) · get_code("3aca1782f944ffe6")
How it ran

no invocation recorded.

kergnn Not yet run
unverified (harvested, no recorded run)
asfeng/kergnns/model.py
code served (permissive licence) · get_code("19220fd0a5bccd0c")
How it ran

no invocation recorded.

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, 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 4 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

Graph kernels are historically the most widely-used technique for graph classification tasks. However, these methods suffer from limited performance because of the hand-crafted combinatorial features of graphs. In recent years, graph neural networks (GNNs) have become the state-of-the-art method in downstream graph-related tasks due to their superior performance. Most GNNs are based on Message Passing Neural Network (MPNN) frameworks. However, recent studies show that MPNNs can not exceed the power of the Weisfeiler-Lehman (WL) algorithm in graph isomorphism test. To address the limitations of existing graph kernel and GNN methods, in this paper, we propose a novel GNN framework, termed Kernel Graph Neural Networks (KerGNNs), which integrates graph kernels into the message passing process of GNNs. Inspired by convolution filters in convolutional neural networks (CNNs), KerGNNs adopt trainable hidden graphs as graph filters which are combined with subgraphs to update node embeddings using graph kernels. In addition, we show that MPNNs can be viewed as special cases of KerGNNs. We apply KerGNNs to multiple graph-related tasks and use cross-validation to make fair comparisons with benchmarks. We show that our method achieves competitive performance compared with existing state-of-the-art methods, demonstrating the potential to increase the representation ability of GNNs. We also show that the trained graph filters in KerGNNs can reveal the local graph structures of the dataset, which significantly improves the model interpretability compared with conventional GNN models.

For agents

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

get_harvested_code_for_paper("2201.00491")
get_code_for_paper("2201.00491")
have("2201.00491")

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

curl https://syntology.ai/api/ran/2201.00491.json

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

[![Syntology run record](https://syntology.ai/api/ran/2201.00491.svg)](https://syntology.ai/paper/2201.00491)

Connect an agent — have() is free.