SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.06707 · 2021

Graph Neural Networks with Local Graph Parameters

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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 5 have no contract verdict; 2 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/2106.06707.json · badge: /api/ran/2106.06707.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
LGP-GNN-2021/LGP-GNN canonical (classifier label)
classifier basis: census
7 ran · 2 no recorded run
FunctionStatusWhere it lives
diag_offdiag_maxpool Ran
ran on a synthesized input
LGP-GNN-2021/LGP-GNN/layers/three_wl_gnn_layers.py
code served (permissive licence) · get_code("15bb4b29cca9b4a1")
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 Tensor, ndim 2, dtype family float, shape (2, 6) 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)

# The function expects a tensor input with shape that allows:
# - input.shape[-1] to get N (last dimension size)
# - torch.diagonal(input, dim1=-2, dim2=-1) to work (needs at least 2D for the last two dims)
# - Indexing with dim=2 after diagonal, so needs at least 3 dimensions
# - Operations that preserve batch dimensions

# Looking at the function:
# - diagonal extracts diagonal across last 2 dims, result has shape [..., N]
# - max(..., dim=2)[0] suggests the result before max has at least 3 dims
# - The output concatenates on dim=1, suggesting (batch, channels, ...)
# - min_mat is reshaped to (1, 1, N, N), then subtracted from input
# - max operations on dim=3 and dim=2 suggest input is 4D: (batch, channels, N, N)

# So input should be: (batch_size, num_channels, N, N)
N = 4
batch_size = 2
num_channels = 3

input_tensor = torch.randn(batch_size, num_channels, N, N)

ARGS = {
    "input": input_tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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, 6) — shape (2, 6) 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
gpu_setup Ran
ran; our contract draft was wrong, not the code
LGP-GNN-2021/LGP-GNN/CLUSTER_Node_Classification.py
pointer only (licence: MIT); the stored copy get_code serves, from trustworthygnn/mia-gnn, is pointer only (licence: NONE) · get_code("f72434c0dcd5d11b")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from trustworthygnn/mia-gnn, and GitHub detected no licence in that repository 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.

gpu_setup Ran
ran on a synthesized input
LGP-GNN-2021/LGP-GNN/COLLAB_Prediction.py
code served (permissive licence) · get_code("7017768b3c816295")
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 device. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 os
import torch

torch.manual_seed(0)

ARGS = {
    'use_gpu': False,
    'gpu_id': 0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type device — a device output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a device 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
gpu_setup Ran
ran; our contract draft was wrong, not the code
LGP-GNN-2021/LGP-GNN/ZINC_Regression.py
code served (permissive licence) · get_code("0c1a813c3ad86bd9")
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 device. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
import os

torch.manual_seed(0)

# The function takes two parameters:
# 1. use_gpu: a boolean indicating whether to use GPU
# 2. gpu_id: an integer specifying which GPU to use

# Since we're running CPU-only, we set use_gpu=False
# gpu_id can be any integer (it will be set in CUDA_VISIBLE_DEVICES but won't be used on CPU)

ARGS = {
    'use_gpu': False,
    'gpu_id': 0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type device — a device output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a device 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
ops_2_to_2 Ran
ran on a synthesized input
LGP-GNN-2021/LGP-GNN/layers/ring_gnn_equiv_layer.py
code served (permissive licence) · get_code("8a8a1e482dac9901")
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 list, ndim 5, dtype family float; 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 torch

torch.manual_seed(0)

# The function expects:
# - inputs: a 4D tensor (batch_size, ..., dim, dim) where last two dims are square matrices
# - dim: an integer representing the dimension of the square matrices
# - normalization: a string or None
# - normalization_val: a float (not used in the function body)

# Create a small 4D tensor: batch_size=2, intermediate=3, dim=4, dim=4
inputs = torch.randn(2, 3, 4, 4)

# dim parameter - used for repeat operations and must match last two dimensions of inputs
dim = 4

# normalization parameter
normalization = 'inf'

# normalization_val parameter
normalization_val = 1.0

ARGS = {
    'inputs': inputs,
    'dim': dim,
    'normalization': normalization,
    'normalization_val': normalization_val,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 5, dtype family float — 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
set_all_params Ran
ran on a synthesized input
LGP-GNN-2021/LGP-GNN/CLUSTER_Node_Classification.py
code served (permissive licence) · get_code("0bc0c5ad5989b170")
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, ndim 1, dtype family float; 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create a minimal dataset object
class MinimalDataset:
    def __init__(self):
        # Create minimal graph data with required attributes
        self.train = []
        
        # Create a minimal graph with ndata containing 'feat'
        class Graph:
            def __init__(self):
                self.ndata = {}
                # Feature tensor: shape [num_nodes, in_dim]
                # Using 3 nodes with 4-dimensional features
                self.ndata['feat'] = torch.randn(3, 4)
        
        # Create minimal labels tensor
        # Using 3 labels (one per node or per graph)
        labels = torch.tensor([0, 1, 0])
        
        graph = Graph()
        self.train.append((graph, labels))

dataset = MinimalDataset()

MODEL_NAME = 'GatedGCN'
random_seed = 42

ARGS = {
    'dataset': dataset,
    'MODEL_NAME': MODEL_NAME,
    'random_seed': random_seed
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple 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
set_all_params Ran
ran on a synthesized input
LGP-GNN-2021/LGP-GNN/ZINC_Regression.py
code served (permissive licence) · get_code("453d550b99ad08aa")
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, ndim 1, dtype family float; 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 torch
import numpy as np

class MockDataset:
    def __init__(self):
        self.num_atom_type = 5
        self.num_bond_type = 3

dataset = MockDataset()
MODEL_NAME = 'GatedGCN'
random_seed = 42

ARGS = {
    'dataset': dataset,
    'MODEL_NAME': MODEL_NAME,
    'random_seed': random_seed
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple 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
set_all_params Not yet run
unverified (harvested, no recorded run)
LGP-GNN-2021/LGP-GNN/COLLAB_Prediction.py
code served (permissive licence) · get_code("d8c92da424abefcd")
How it ran

no invocation recorded.

set_all_params Not yet run
unverified (harvested, no recorded run)
LGP-GNN-2021/LGP-GNN/PATTERN_Node_Classification.py
code served (permissive licence) · get_code("a5a0bd2cb0cbd115")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 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
gpu_setup 8 other papers
4 dated earlier, 4 later
2003.00982 (2020-03)
Benchmarking Graph Neural Networks
2009.11746 (2020-09)
Learning Graph Normalization for Graph Neural Networks
2010.02863 (2020-10)
Directional Graph Networks
and 5 more not named here
diag_offdiag_maxpool 2 other papers
2 dated earlier
1905.11136 (2019-05)
Provably Powerful Graph Networks
2003.00982 (2020-03)
Benchmarking Graph Neural Networks
ops_2_to_2 1 other paper
1 dated earlier
2003.00982 (2020-03)
Benchmarking Graph Neural Networks

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

Various recent proposals increase the distinguishing power of Graph Neural Networks GNNs by propagating features between $k$-tuples of vertices. The distinguishing power of these "higher-order'' GNNs is known to be bounded by the $k$-dimensional Weisfeiler-Leman (WL) test, yet their $\mathcal O(n^k)$ memory requirements limit their applicability. Other proposals infuse GNNs with local higher-order graph structural information from the start, hereby inheriting the desirable $\mathcal O(n)$ memory requirement from GNNs at the cost of a one-time, possibly non-linear, preprocessing step. We propose local graph parameter enabled GNNs as a framework for studying the latter kind of approaches and precisely characterize their distinguishing power, in terms of a variant of the WL test, and in terms of the graph structural properties that they can take into account. Local graph parameters can be added to any GNN architecture, and are cheap to compute. In terms of expressive power, our proposal lies in the middle of GNNs and their higher-order counterparts. Further, we propose several techniques to aide in choosing the right local graph parameters. Our results connect GNNs with deep results in finite model theory and finite variable logics. Our experimental evaluation shows that adding local graph parameters often has a positive effect for a variety of GNNs, datasets and graph learning tasks.

For agents

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

get_harvested_code_for_paper("2106.06707")
get_code_for_paper("2106.06707")
have("2106.06707")

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

curl https://syntology.ai/api/ran/2106.06707.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.06707.svg)](https://syntology.ai/paper/2106.06707)

Connect an agent — have() is free.