SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2201.12433 · 2022

FedGCN: Convergence-Communication Tradeoffs in Federated Training of Graph Convolutional Networks

arXiv · PDF · Open in the Atlas

Code that ran

13 of 19 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 13 have no contract verdict; 0 failures of our instrument; 6 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/2201.12433.json · badge: /api/ran/2201.12433.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
yh-yao/FedGCN canonical (classifier label)
classifier basis not recorded on the link
7 ran · 1 no recorded run
fedgraph/fedgraph community (classifier label)
classifier basis not recorded on the link
6 ran · 5 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran on a synthesized input
yh-yao/FedGCN/src/train_func.py
code served (permissive licence) · get_code("08ad57e4c786ce2c")
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 0, dtype family float, shape () 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)

# Create output tensor with shape (batch_size=2, num_classes=4)
# This represents logits from a model with 4 classes
output = torch.randn(2, 4)

# Create labels tensor with shape (batch_size=2,)
# Labels should be class indices in range [0, num_classes)
labels = torch.tensor([0, 3], dtype=torch.long)

ARGS = {
    "output": output,
    "labels": labels,
}
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 0, dtype family float, shape () — shape () 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
convert_time Ran
ran on a synthesized input
fedgraph/fedgraph/fedgraph/utils_lp.py
code served (permissive licence) · get_code("484f676e1159b7c5")
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 float, ndim 0, dtype family float, shape () 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 datetime
import time

# The function expects a time_string in a specific format
# Based on the parsing logic:
# - current_list[5] is the year
# - current_list[1] is the month (abbreviated like 'Jan', 'Feb', etc.)
# - current_list[2] is the day
# - current_list[3] contains time in format HH:MM:SS (sliced as [0:2], [3:5], [6:8])
# - current_list[0], current_list[4] are other fields (likely day of week and timezone)

# Example time string format: "Mon Jan 15 12:34:56 EST 2024"
time_string_example = "Mon Jan 15 12:34:56 EST 2024"

ARGS = {
    "time_string": time_string_example
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () 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
get_max_degree Ran
ran on a synthesized input
fedgraph/fedgraph/fedgraph/utils_gc.py
code served (permissive licence) · get_code("e17c9a65f27c7056")
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 int, ndim 0, dtype family int, shape () 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_geometric
from torch_geometric.data import Data

torch.manual_seed(0)

# Create small synthetic graphs for testing
# Each graph needs edge_index to work with to_networkx
graph1 = Data(
    edge_index=torch.tensor([
        [0, 1, 2, 1],
        [1, 0, 1, 2]
    ], dtype=torch.long),
    num_nodes=3
)

graph2 = Data(
    edge_index=torch.tensor([
        [0, 1, 2, 3, 0],
        [1, 2, 3, 0, 3]
    ], dtype=torch.long),
    num_nodes=4
)

# Create a list of graphs
graphs = [graph1, graph2]

ARGS = {
    "graphs": graphs
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torch_geometric — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () 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
intersect1d Ran
ran on a synthesized input
fedgraph/fedgraph/fedgraph/utils_nc.py
code served (permissive licence) · get_code("d930367eb9a10566")
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 1, dtype family int, shape (2,) 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)

# Create two small 1D tensors with some common elements
t1 = torch.tensor([1, 2, 3, 4], dtype=torch.long)
t2 = torch.tensor([3, 4, 5, 6], dtype=torch.long)

ARGS = {
    "t1": t1,
    "t2": t2,
}
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 1, dtype family int, shape (2,) — shape (2,) 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
intersect1d Ran
ran on a synthesized input
yh-yao/FedGCN/src/utils.py
code served (permissive licence) · get_code("46bdb85edbc8f2ae")
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 1, dtype family int, shape (2,) 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)

# Create two small 1D tensors with some common elements
t1 = torch.tensor([1, 2, 3, 4])
t2 = torch.tensor([3, 4, 5, 6])

ARGS = {
    "t1": t1,
    "t2": t2,
}
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 1, dtype family int, shape (2,) — shape (2,) 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
normalize Ran
ran on a synthesized input
fedgraph/fedgraph/fedgraph/utils_nc.py
code served (permissive licence) · get_code("5bcc012bb7cebef2")
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 csr_matrix. 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 numpy as np
import scipy.sparse as sp

# Create a small sparse matrix for testing
# Using a 4x3 sparse matrix with some non-zero entries
row = np.array([0, 1, 2, 3, 0, 2])
col = np.array([0, 1, 2, 0, 2, 1])
data = np.array([1.0, 2.0, 3.0, 4.0, 5.0, 6.0])
mx = sp.coo_matrix((data, (row, col)), shape=(4, 3))
mx = mx.tocsc()  # Convert to csc_matrix as required by the function signature

ARGS = {
    "mx": mx
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type csr_matrix — a csr_matrix output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a csr_matrix 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
normalize Ran
ran on a synthesized input
yh-yao/FedGCN/src/data_process.py
code served (permissive licence) · get_code("4dd253367a1dc7e0")
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 csr_matrix. 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 numpy as np
import scipy.sparse as sp

# Create a small sparse matrix for testing
# Using a 4x3 sparse matrix with some non-zero entries
row_indices = np.array([0, 1, 2, 3, 0, 2])
col_indices = np.array([0, 1, 2, 0, 2, 1])
data = np.array([2.0, 3.0, 1.0, 4.0, 2.0, 5.0])

mx = sp.csr_matrix((data, (row_indices, col_indices)), shape=(4, 3))
mx = mx.tocsc()

ARGS = {
    "mx": mx
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type csr_matrix — a csr_matrix output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a csr_matrix 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
parse_index_file Ran
ran on a synthesized input
yh-yao/FedGCN/src/data_process.py
code served (permissive licence) · get_code("d2d6d7748327bbb9")
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 1, dtype family int; 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 tempfile
import os

# Create a temporary file with integer content
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("42\n")
temp_file.write("100\n")
temp_file.write("7\n")
temp_file.close()

ARGS = {
    "filename": temp_file.name
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — 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
setdiff1d Ran
ran on a synthesized input
fedgraph/fedgraph/fedgraph/utils_nc.py
code served (permissive licence) · get_code("820236895e53ef14")
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 1, dtype family int, shape (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

torch.manual_seed(0)

# Create two small tensors with some overlapping and non-overlapping elements
t1 = torch.tensor([1, 2, 3, 4], dtype=torch.int64)
t2 = torch.tensor([3, 4, 5, 6], dtype=torch.int64)

ARGS = {
    "t1": t1,
    "t2": t2,
}
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 1, dtype family int, shape (4,) — shape (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
setdiff1d Ran
ran on a synthesized input
yh-yao/FedGCN/src/utils.py
code served (permissive licence) · get_code("90f4f30341740d13")
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 1, dtype family int, shape (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

torch.manual_seed(0)

# Create two small tensors for set difference computation
t1 = torch.tensor([1, 2, 3, 4])
t2 = torch.tensor([3, 4, 5, 6])

ARGS = {
    "t1": t1,
    "t2": t2,
}
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 1, dtype family int, shape (4,) — shape (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
test Ran
ran on a synthesized input
fedgraph/fedgraph/fedgraph/train_func.py
code served (permissive licence) · get_code("8064636d75c58de8")
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)

# Build a minimal model that takes (features, adj) and outputs log probabilities
class SimpleGNN(nn.Module):
    def __init__(self, input_dim, output_dim):
        super().__init__()
        self.linear = nn.Linear(input_dim, output_dim)
    
    def forward(self, features, adj):
        # Simple forward pass: just apply linear layer to features
        # Output shape: (num_nodes, output_dim)
        return F.log_softmax(self.linear(features), dim=1)

# Create model
num_nodes = 2
input_dim = 4
output_dim = 3
model = SimpleGNN(input_dim, output_dim)

# Create input tensors
features = torch.randn(num_nodes, input_dim)  # (2, 4)
adj = torch.randn(num_nodes, num_nodes)  # (2, 2) - adjacency matrix

# Create test labels and indices
test_labels = torch.tensor([0, 2], dtype=torch.long)  # Ground truth labels for 2 nodes
idx_test = torch.tensor([0, 1], dtype=torch.long)  # Indices of test nodes

ARGS = {
    "model": model,
    "features": features,
    "adj": adj,
    "test_labels": test_labels,
    "idx_test": idx_test,
}
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
yh-yao/FedGCN/src/train_func.py
code served (permissive licence) · get_code("58b6937e51285f53")
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)

# Define a minimal model that satisfies the function's usage
class SimpleGCN(nn.Module):
    def __init__(self, input_dim, output_dim):
        super().__init__()
        self.fc = nn.Linear(input_dim, output_dim)
    
    def forward(self, features, adj):
        # The function calls model(features, adj) and expects output
        # that can be passed to F.nll_loss and argmax
        output = self.fc(features)
        return F.log_softmax(output, dim=1)

# Create tiny tensors
num_nodes = 2
num_features = 4
num_classes = 3

features = torch.randn(num_nodes, num_features)
adj = torch.randn(num_nodes, num_nodes)
labels = torch.tensor([0, 2], dtype=torch.long)
idx_test = torch.tensor([0, 1], dtype=torch.long)

# Instantiate the model
model = SimpleGCN(input_dim=num_features, output_dim=num_classes)

ARGS = {
    "model": model,
    "features": features,
    "adj": adj,
    "labels": labels,
    "idx_test": idx_test,
}
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
train Ran
ran on a synthesized input
yh-yao/FedGCN/src/train_func.py
code served (permissive licence) · get_code("8f8a4abab99a52e6")
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.optim as optim

torch.manual_seed(0)

# Create a simple model that takes features and adjacency matrix
class SimpleGNNModel(nn.Module):
    def __init__(self, input_dim, output_dim):
        super().__init__()
        self.linear = nn.Linear(input_dim, output_dim)
    
    def forward(self, features, adj):
        # Simple forward pass - just linear transformation
        output = self.linear(features)
        return output

# Set up dimensions
num_nodes = 2
input_dim = 4
num_classes = 3

# Create model
model = SimpleGNNModel(input_dim, num_classes)

# Create optimizer
optimizer = optim.Adam(model.parameters(), lr=0.01)

# Create features tensor (num_nodes x input_dim)
features = torch.randn(num_nodes, input_dim)

# Create adjacency matrix (num_nodes x num_nodes)
adj = torch.randn(num_nodes, num_nodes)

# Create labels tensor (num_nodes,) with class indices
labels = torch.tensor([0, 2], dtype=torch.long)

# Create training indices (select first node for training)
idx_train = torch.tensor([0], dtype=torch.long)

# Epoch number
epoch = 1

ARGS = {
    "epoch": epoch,
    "model": model,
    "optimizer": optimizer,
    "features": features,
    "adj": adj,
    "labels": labels,
    "idx_train": idx_train,
}
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
accuracy Not yet run
unverified (harvested, no recorded run)
fedgraph/fedgraph/fedgraph/train_func.py
code served (permissive licence) · get_code("142d715a1e53af0c")
How it ran

no invocation recorded.

gc_avg_accuracy Not yet run
unverified (harvested, no recorded run)
fedgraph/fedgraph/fedgraph/train_func.py
code served (permissive licence) · get_code("f86d7b5b6badae56")
How it ran

no invocation recorded.

label_dirichlet_partition Not yet run
unverified (harvested, no recorded run)
yh-yao/FedGCN/src/utils.py
code served (permissive licence) · get_code("69257d45cbe4742b")
How it ran

no invocation recorded.

load_edge_csv Not yet run
unverified (harvested, no recorded run)
fedgraph/fedgraph/fedgraph/utils_lp.py
code served (permissive licence) · get_code("6595dc12515fe027")
How it ran

no invocation recorded.

load_node_csv Not yet run
unverified (harvested, no recorded run)
fedgraph/fedgraph/fedgraph/utils_lp.py
code served (permissive licence) · get_code("58ae9f65d93b79a2")
How it ran

no invocation recorded.

load_trainer_data_from_hugging_face Not yet run
unverified (harvested, no recorded run)
fedgraph/fedgraph/fedgraph/trainer_class.py
code served (permissive licence) · get_code("6fab0094c3f80711")
How it ran

no invocation recorded.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 15 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 15 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

Methods for training models on graphs distributed across multiple clients have recently grown in popularity, due to the size of these graphs as well as regulations on keeping data where it is generated. However, the cross-client edges naturally exist among clients. Thus, distributed methods for training a model on a single graph incur either significant communication overhead between clients or a loss of available information to the training. We introduce the Federated Graph Convolutional Network (FedGCN) algorithm, which uses federated learning to train GCN models for semi-supervised node classification with fast convergence and little communication. Compared to prior methods that require extra communication among clients at each training round, FedGCN clients only communicate with the central server in one pre-training step, greatly reducing communication costs and allowing the use of homomorphic encryption to further enhance privacy. We theoretically analyze the tradeoff between FedGCN's convergence rate and communication cost under different data distributions. Experimental results show that our FedGCN algorithm achieves better model accuracy with 51.7% faster convergence on average and at least 100X less communication compared to prior work.

For agents

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

get_harvested_code_for_paper("2201.12433")
get_code_for_paper("2201.12433")
have("2201.12433")

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

curl https://syntology.ai/api/ran/2201.12433.json

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

[![Syntology run record](https://syntology.ai/api/ran/2201.12433.svg)](https://syntology.ai/paper/2201.12433)

Connect an agent — have() is free.