SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.06211 · NeurIPS · 2020

Implicit Graph Neural Networks

Fangda Gu, Heng Chang, Wenwu Zhu, Somayeh Sojoudi, Laurent El Ghaoui

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 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; 1 failure of our instrument; 1 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/2009.06211.json · badge: /api/ran/2009.06211.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
SwiftieH/IGNN marked official in Papers with Code
Papers with Code archive
3 ran · 1 no recorded run
FunctionStatusWhere it lives
IGNN Ran
ran on a synthesized input · constructed an object; no result was computed
SwiftieH/IGNN/graphclassification/models.py
code served (permissive licence) · get_code("c09107a246d99eb8")
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 an instance of its own class, IGNN: the run constructed the object and did not call it, so no result was computed. 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
import torch.nn as nn
import numpy as np
import math
from torch.nn import Parameter

torch.manual_seed(0)
np.random.seed(0)

# Create minimal valid arguments for IGNN.__init__
nfeat = 4           # input feature dimension
nhid = 3            # hidden dimension
nclass = 2          # output class dimension
num_node = 5        # number of nodes
dropout = 0.5       # dropout rate
kappa = 0.9         # contraction coefficient
adj_orig = None     # optional original adjacency matrix

ARGS = {
    'nfeat': nfeat,
    'nhid': nhid,
    'nclass': nclass,
    'num_node': num_node,
    'dropout': dropout,
    'kappa': kappa,
    'adj_orig': adj_orig,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, torch_geometric — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type IGNN — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a IGNN 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
ImplicitFunction Ran
ran on a synthesized input · constructed an object; no result was computed
SwiftieH/IGNN/graphclassification/models.py
code served (permissive licence) · get_code("6b16eb46601b6a33")
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 an instance of its own class, ImplicitFunction: the run constructed the object and did not call it, so no result was computed. 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
import numpy as np

torch.manual_seed(0)

# Define a simple activation function
def phi_fn(x):
    return torch.relu(x)

# Create small tensors with distinct dimensions
batch_size = 2
input_dim = 4
output_dim = 3
feature_dim = 5

# W: weight matrix for the implicit function
W = torch.randn(output_dim, input_dim)

# X_0: initial state (can be None)
X_0 = torch.randn(batch_size, output_dim)

# A: sparse adjacency or transformation matrix
# Create a small sparse matrix
A_indices = torch.tensor([[0, 1, 2, 3], [1, 2, 3, 0]])
A_values = torch.ones(4)
A = torch.sparse_coo_tensor(A_indices, A_values, (output_dim, output_dim))

# B: bias or offset term
B = torch.randn(batch_size, output_dim)

# phi: activation function (callable)
phi = phi_fn

# fd_mitr: forward iterations (optional, defaults to 300)
fd_mitr = 50

# bw_mitr: backward iterations (optional, defaults to 300)
bw_mitr = 50

ARGS = {
    'W': W,
    'X_0': X_0,
    'A': A,
    'B': B,
    'phi': phi,
    'fd_mitr': fd_mitr,
    'bw_mitr': bw_mitr,
}
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 ImplicitFunction — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ImplicitFunction 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
projection_norm_inf Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SwiftieH/IGNN/graphclassification/models.py
code served (permissive licence) · get_code("cd1700e22c688900")
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, 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 numpy as np

torch.manual_seed(0)

# Create a small tensor A with shape (2, 4)
# The function expects A to be a torch tensor with requires_grad or at least cloneable
A = torch.randn(2, 4, dtype=torch.float32, requires_grad=False)

ARGS = {
    "A": A,
    "kappa": 0.99,
    "transpose": False,
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
ImplicitGraph Not yet run
unverified (harvested, no recorded run)
SwiftieH/IGNN/graphclassification/models.py
code served (permissive licence) · get_code("439e3542d9e882ac")
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, 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 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
projection_norm_inf
brick of this paper's assembly: helper
1 other paper
1 later
2106.01680 (2021-06)
Convergent Graph Solvers

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 Neural Networks (GNNs) are widely used deep learning models that learn meaningful representations from graph-structured data. Due to the finite nature of the underlying recurrent structure, current GNN methods may struggle to capture long-range dependencies in underlying graphs. To overcome this difficulty, we propose a graph learning framework, called Implicit Graph Neural Networks (IGNN 2 ), where predictions are based on the solution of a fixed-point equilibrium equation involving implicitly defined "state" vectors. We use the Perron-Frobenius theory to derive sufficient conditions that ensure well-posedness of the framework. Leveraging implicit differentiation, we derive a tractable projected gradient descent method to train the framework. Experiments on a comprehensive range of tasks show that IGNNs consistently capture long-range dependencies and outperform the state-of-the-art GNN models. * Equal contributions. Work done during Heng's visit to University of California at Berkeley.

For agents

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

get_harvested_code_for_paper("2009.06211")
get_code_for_paper("2009.06211")
have("2009.06211")

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

curl https://syntology.ai/api/ran/2009.06211.json

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

[![Syntology run record](https://syntology.ai/api/ran/2009.06211.svg)](https://syntology.ai/paper/2009.06211)

Connect an agent — have() is free.