SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1611.08402 · 2016

Geometric deep learning on graphs and manifolds using mixture model CNNs

arXiv · PDF · Open in the Atlas

Code that ran

2 of 5 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 2 have 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/1611.08402.json · badge: /api/ran/1611.08402.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
theswgong/MoNet community (classifier label)
classifier basis not recorded on the link
2 ran · 3 no recorded run
FunctionStatusWhere it lives
test Ran
ran on a synthesized input
theswgong/MoNet/image/train_eval.py
code served (permissive licence) · get_code("a70eb3051c972797")
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 simple model that takes graph data and outputs class logits
class SimpleGraphModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, data):
        # Expects data to have an x attribute (node features)
        return self.linear(data.x)

# Create a simple data class that mimics graph data
class SimpleData:
    def __init__(self, x, y):
        self.x = x
        self.y = y
    
    def to(self, device):
        self.x = self.x.to(device)
        self.y = self.y.to(device)
        return self

# Create test data: batch of 2 samples, 4 features, 3 classes
data1 = SimpleData(
    x=torch.randn(2, 4),
    y=torch.tensor([0, 1])
)

data2 = SimpleData(
    x=torch.randn(2, 4),
    y=torch.tensor([2, 1])
)

# Create test loader as a list of data objects
test_loader = [data1, data2]

# Add __len__ to the loader to support len(test_loader.dataset)
class TestDataLoader(list):
    @property
    def dataset(self):
        class Dataset:
            def __init__(self, data_list):
                self.data_list = data_list
            def __len__(self):
                return sum(d.y.shape[0] for d in self.data_list)
        return Dataset(self)

test_loader = TestDataLoader([data1, data2])

# Create model
model = SimpleGraphModel()

# Device
device = torch.device('cpu')

ARGS = {
    'model': model,
    'test_loader': test_loader,
    'device': device
}
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
test Ran
ran on a synthesized input
theswgong/MoNet/manifolds/train_eval.py
code served (permissive licence) · get_code("fa42f81c7ba963a8")
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
import torch.nn.functional as F

torch.manual_seed(0)

# Create a minimal model that takes data and outputs logits
class MinimalGNNModel(nn.Module):
    def __init__(self, num_classes=3):
        super().__init__()
        self.linear = nn.Linear(4, num_classes)
    
    def forward(self, data):
        # Minimal forward pass that works with graph data
        # Assumes data has x attribute (node features)
        return self.linear(data.x)

# Create a minimal batch object that mimics torch_geometric Data
class MinimalBatch:
    def __init__(self, x, num_graphs=2):
        self.x = x
        self.num_graphs = num_graphs
    
    def to(self, device):
        self.x = self.x.to(device)
        return self

# Setup model
model = MinimalGNNModel(num_classes=3)

# Create test loader with minimal batches
# Each batch has node features and num_graphs attribute
batch1 = MinimalBatch(torch.randn(6, 4), num_graphs=2)
batch2 = MinimalBatch(torch.randn(6, 4), num_graphs=2)
test_loader = [batch1, batch2]

# Parameters
num_nodes = 3
target = torch.tensor([0, 1, 2, 0, 1, 2])  # 6 targets for 6 nodes in a batch
device = torch.device('cpu')

ARGS = {
    'model': model,
    'test_loader': test_loader,
    'num_nodes': num_nodes,
    'target': target,
    'device': device
}
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
evaluate Not yet run
unverified (harvested, no recorded run)
theswgong/MoNet/graph/train_eval.py
pointer only (licence: MIT); the stored copy get_code serves, from bywmm/Bi-GCN, is pointer only (licence: NONE) · get_code("4ac4a1493301e71a")
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 bywmm/Bi-GCN, 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. No invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
theswgong/MoNet/image/train_eval.py
code served (permissive licence) · get_code("668c5f7e61273fc2")
How it ran

no invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
theswgong/MoNet/manifolds/train_eval.py
code served (permissive licence) · get_code("b38fca4c55c291bc")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 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.

FunctionAlso present inEarliest-datedOthers named
evaluate 1 other paper
1 later
2010.07565 (2020-10)
Bi-GCN: Binary Graph Convolutional Network

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

Deep learning has achieved a remarkable performance breakthrough in several fields, most notably in speech recognition, natural language processing, and computer vision. In particular, convolutional neural network (CNN) architectures currently produce state-of-the-art performance on a variety of image analysis tasks such as object detection and recognition. Most of deep learning research has so far focused on dealing with 1D, 2D, or 3D Euclidean-structured data such as acoustic signals, images, or videos. Recently, there has been an increasing interest in geometric deep learning, attempting to generalize deep learning methods to non-Euclidean structured data such as graphs and manifolds, with a variety of applications from the domains of network analysis, computational social science, or computer graphics. In this paper, we propose a unified framework allowing to generalize CNN architectures to non-Euclidean domains (graphs and manifolds) and learn local, stationary, and compositional task-specific features. We show that various non-Euclidean CNN methods previously proposed in the literature can be considered as particular instances of our framework. We test the proposed method on standard tasks from the realms of image-, graph- and 3D shape analysis and show that it consistently outperforms previous approaches.

For agents

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

get_harvested_code_for_paper("1611.08402")
get_code_for_paper("1611.08402")
have("1611.08402")

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

curl https://syntology.ai/api/ran/1611.08402.json

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

[![Syntology run record](https://syntology.ai/api/ran/1611.08402.svg)](https://syntology.ai/paper/1611.08402)

Connect an agent — have() is free.