SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.02514 · ICML · 2022

Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations

Sung Hwang, Jaehyeong Jo, Seul Lee

arXiv · PDF · Open in the Atlas

Code that ran

14 of 26 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 3 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 7 failures of our instrument; 12 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/2202.02514.json · badge: /api/ran/2202.02514.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
harryjo97/gdss canonical (classifier label)
classifier basis: classifier_2025
6 ran · 7 no recorded run
AdrienC21/CCSD community
Papers with Code archive
8 ran · 5 no recorded run
FunctionStatusWhere it lives
DenseGCNConv Ran
ran on a synthesized input · constructed an object; no result was computed
AdrienC21/CCSD/ccsd/src/models/ScoreNetwork_A.py
code served (permissive licence) · get_code("d2e486d574414d1d")
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, DenseGCNConv: 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 math
from torch.nn import Parameter

torch.manual_seed(0)

# Define the helper functions and class from the provided code
def glorot(tensor):
    if tensor is not None:
        stdv = math.sqrt(6.0 / (tensor.size(-2) + tensor.size(-1)))
        tensor.data.uniform_(-stdv, stdv)

def zeros(tensor):
    if tensor is not None:
        tensor.data.fill_(0)

class DenseGCNConv(torch.nn.Module):
    def __init__(self, in_channels: int, out_channels: int, improved: bool=False, bias: bool=True) -> None:
        super(DenseGCNConv, self).__init__()
        self.in_channels = in_channels
        self.out_channels = out_channels
        self.improved = improved
        self.weight = Parameter(torch.Tensor(self.in_channels, out_channels))
        if bias:
            self.bias = Parameter(torch.Tensor(out_channels))
        else:
            self.register_parameter('bias', None)
        self.reset_parameters()

    def reset_parameters(self) -> None:
        glorot(self.weight)
        zeros(self.bias)

    def __repr__(self) -> str:
        return '{}({}, {})'.format(self.__class__.__name__, self.in_channels, self.out_channels)

    def forward(self, x: torch.Tensor, adj: torch.Tensor, mask=None, add_loop: bool=True) -> torch.Tensor:
        x = x.unsqueeze(0) if x.dim() == 2 else x
        adj = adj.unsqueeze(0) if adj.dim() == 2 else adj
        B, N, _ = adj.size()
        if add_loop:
            adj = adj.clone()
            idx = torch.arange(N, dtype=torch.long, device=adj.device)
            adj[:, idx, idx] = 1 if not self.improved else 2
        out = torch.matmul(x, self.weight)
        deg_inv_sqrt = adj.sum(dim=-1).clamp(min=1).pow(-0.5)
        adj = deg_inv_sqrt.unsqueeze(-1) * adj * deg_inv_sqrt.unsqueeze(-2)
        out = torch.matmul(adj, out)
        if self.bias is not None:
            out = out + self.bias
        if mask is not None:
            out = out * mask.view(B, N, 1).to(x.dtype)
        return out

# Create test arguments
# Batch size: 2, Nodes: 4, Input features: 3, Output features: 5
in_channels = 3
out_channels = 5
batch_size = 2
num_nodes = 4

# Create node feature matrix (B * N * F_i): (2, 4, 3)
x = torch.randn(batch_size, num_nodes, in_channels)

# Create adjacency matrix (B * N * N): (2, 4, 4)
adj = torch.randint(0, 2, (batch_size, num_nodes, num_nodes)).float()

# Create optional mask (B * N): (2, 4)
mask = torch.ones(batch_size, num_nodes)

ARGS = {
    'in_channels': in_channels,
    'out_channels': out_channels,
    'improved': False,
    'bias': True
}
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 DenseGCNConv — 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 DenseGCNConv 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
DenseGCNConv Ran
ran on a synthesized input
harryjo97/gdss/models/ScoreNetwork_A.py
pointer only (licence: NONE) · get_code("5a02983f323406e0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harryjo97/gdss 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.

MLP Ran
ran on a synthesized input · constructed an object; no result was computed
AdrienC21/CCSD/ccsd/src/models/ScoreNetwork_A.py
code served (permissive licence) · get_code("63298408c7c090f1")
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, MLP: 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.functional as F

torch.manual_seed(0)

ARGS = {
    "num_layers": 3,
    "input_dim": 4,
    "hidden_dim": 8,
    "output_dim": 5,
    "use_bn": True,
    "activate_func": F.relu
}
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 MLP — 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 MLP 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
MLP Ran
ran on a synthesized input · constructed an object; no result was computed
harryjo97/gdss/models/ScoreNetwork_A.py
pointer only (licence: NONE) · get_code("040c0c8297f0b85e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harryjo97/gdss 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.

default_mask Ran
ran, honoured the contract we drafted
AdrienC21/CCSD/ccsd/src/models/ScoreNetwork_A.py
code served (permissive licence) · get_code("f024485a6f7e3fcd")
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 (5, 5) 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)

ARGS = {
    "n": 5,
    "device": "cpu",
}
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 (5, 5) — shape (5, 5) 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_ones Ran
ran; our contract draft was wrong, not the code
AdrienC21/CCSD/ccsd/src/models/ScoreNetwork_A.py
code served (permissive licence) · get_code("748e4359ea4a572a")
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
from typing import Sequence

torch.manual_seed(0)

# The function get_ones takes:
# - shape: Sequence[int] - a sequence of integers representing tensor shape
# - device: str - a device string like 'cpu'

# Based on the function body, it:
# 1. Calls torch.ones(shape, dtype=torch.float32, device=device)
# 2. Clones the result
# Both operations work with any valid shape and device string

ARGS = {
    "shape": (2, 4),
    "device": "cpu"
}
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, 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
get_ones_cache Ran
ran; our contract draft was wrong, not the code
AdrienC21/CCSD/ccsd/src/models/ScoreNetwork_A.py
code served (permissive licence) · get_code("ad6a260e14f905b6")
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
from typing import Sequence

torch.manual_seed(0)

# The function takes:
# 1. shape: Sequence[int] - a sequence of integers defining tensor shape
# 2. device: str - a string specifying the device (e.g., 'cpu')

ARGS = {
    "shape": (2, 4),
    "device": "cpu"
}
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, 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
mask_adjs Ran
ran; our contract draft was wrong, not the code
AdrienC21/CCSD/ccsd/src/models/ScoreNetwork_A.py
code served (permissive licence) · get_code("accdc25084458694")
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 3, dtype family float, shape (2, 4, 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 torch.nn as nn

torch.manual_seed(0)

# Test case 1: 3D adjacency matrices (B x N x N) without flags
adjs_3d = torch.randn(2, 4, 4)

# Test case 2: 4D adjacency matrices (B x C x N x N) without flags
adjs_4d = torch.randn(2, 3, 4, 4)

# Test case 3: flags tensor (B x N)
flags = torch.randint(0, 2, (2, 4)).float()

# Define ARGS with the main use case
ARGS = {
    "adjs": adjs_3d,
    "flags": None
}
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 3, dtype family float, shape (2, 4, 4) — shape (2, 4, 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
mask_adjs Ran
ran; our contract draft was wrong, not the code
harryjo97/gdss/models/ScoreNetwork_A.py
pointer only (licence: NONE) · get_code("48beee2482c52c79")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harryjo97/gdss 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.

mask_x Ran
ran, honoured the contract we drafted
AdrienC21/CCSD/ccsd/src/models/ScoreNetwork_A.py
code served (permissive licence) · get_code("6ab53333836fe2fd")
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 3, dtype family float, shape (2, 4, 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

torch.manual_seed(0)

# Set up arguments for mask_x function
# x: batch of node features - shape (batch_size, num_nodes, feature_dim)
# flags: optional 0-1 flags tensor - shape (batch_size, num_nodes)

x = torch.randn(2, 4, 3)  # batch_size=2, num_nodes=4, feature_dim=3
flags = torch.ones(2, 4)  # batch_size=2, num_nodes=4 (0-1 flags)

ARGS = {
    "x": x,
    "flags": flags,
}
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 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 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: none by the harness; any seed is in the setup block
mask_x Ran
ran, honoured the contract we drafted
harryjo97/gdss/models/ScoreNetwork_A.py
pointer only (licence: NONE) · get_code("9e2571123018843f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harryjo97/gdss 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.

node_feature_to_matrix Ran
ran; our contract draft was wrong, not the code
harryjo97/gdss/models/ScoreNetwork_A.py
pointer only (licence: NONE) · get_code("0d1b1ea523b61fc1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harryjo97/gdss 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.

pow_tensor Ran
ran; our contract draft was wrong, not the code
AdrienC21/CCSD/ccsd/src/models/ScoreNetwork_A.py
code served (permissive licence) · get_code("4950af49e1d0760a")
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 4, dtype family float, shape (2, 3, 4, 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 a small batch of adjacency matrices
# Shape: B x N x N where B=2 (batch size), N=4 (matrix dimension)
x = torch.randn(2, 4, 4)

# Number of higher order matrices to create
cnum = 3

ARGS = {
    "x": x,
    "cnum": cnum,
}
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 4, dtype family float, shape (2, 3, 4, 4) — shape (2, 3, 4, 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
pow_tensor Ran
ran; our contract draft was wrong, not the code
harryjo97/gdss/models/ScoreNetwork_A.py
pointer only (licence: NONE) · get_code("f336fdfe65a2d094")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harryjo97/gdss 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.

Attention Not yet run
unverified (harvested, no recorded run)
AdrienC21/CCSD/ccsd/src/models/ScoreNetwork_A.py
code served (permissive licence) · get_code("7b774bdd34c82a39")
How it ran

no invocation recorded.

Attention Not yet run
unverified (harvested, no recorded run)
harryjo97/gdss/models/ScoreNetwork_A.py
pointer only (licence: NONE) · get_code("33bc3c99206d9a3e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harryjo97/gdss 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.

AttentionLayer Not yet run
unverified (harvested, no recorded run)
AdrienC21/CCSD/ccsd/src/models/ScoreNetwork_A.py
code served (permissive licence) · get_code("e3d26a1b52a8e0cd")
How it ran

no invocation recorded.

AttentionLayer Not yet run
unverified (harvested, no recorded run)
harryjo97/gdss/models/ScoreNetwork_A.py
pointer only (licence: NONE) · get_code("4459f5d4f76fdabb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harryjo97/gdss 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.

BaselineNetwork Not yet run
unverified (harvested, no recorded run)
harryjo97/gdss/models/ScoreNetwork_A.py
pointer only (licence: NONE) · get_code("94df2c222ce171b3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harryjo97/gdss 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.

BaselineNetworkLayer Not yet run
unverified (harvested, no recorded run)
harryjo97/gdss/models/ScoreNetwork_A.py
pointer only (licence: NONE) · get_code("23a353751b044a84")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harryjo97/gdss 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.

ScoreNetworkA Not yet run
unverified (harvested, no recorded run)
AdrienC21/CCSD/ccsd/src/models/ScoreNetwork_A.py
code served (permissive licence) · get_code("f778f8f279b1775e")
How it ran

no invocation recorded.

ScoreNetworkA Not yet run
unverified (harvested, no recorded run)
harryjo97/gdss/models/ScoreNetwork_A.py
pointer only (licence: NONE) · get_code("e4c3555e138cd8e7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harryjo97/gdss 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.

glorot Not yet run
unverified (harvested, no recorded run)
AdrienC21/CCSD/ccsd/src/models/ScoreNetwork_A.py
code served (permissive licence) · get_code("b26ee0603cfc49f5")
How it ran

no invocation recorded.

glorot Not yet run
unverified (harvested, no recorded run)
harryjo97/gdss/models/ScoreNetwork_A.py
pointer only (licence: NONE) · get_code("99fea4b7e50f6464")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harryjo97/gdss 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.

zeros Not yet run
unverified (harvested, no recorded run)
AdrienC21/CCSD/ccsd/src/models/ScoreNetwork_A.py
code served (permissive licence) · get_code("5f1a4e1cb60dea51")
How it ran

no invocation recorded.

zeros Not yet run
unverified (harvested, no recorded run)
harryjo97/gdss/models/ScoreNetwork_A.py
pointer only (licence: NONE) · get_code("ea9c6ff61fbc9c4e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, harryjo97/gdss 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.

Also present in other papers' code

Of 26 samples lifted from this paper's linked repositories, 26 carry a function identity and 0 do not. Of the 26 distinct functions with an identity, 11 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 11 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.

FunctionAlso present inEarliest-datedOthers named
mask_adjs
brick of this paper's assembly: helper
3 other papers
3 later · 2 only as an assembly brick
2303.10108 (2023-03)
Data-Centric Learning from Unlabeled Graphs with Diffusion Model
2305.18407 (2023-05)
A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining
2403.16883 (2024-03)
GLAD: Improving Latent Graph Generative Modeling with Simple Quantization
mask_x
brick of this paper's assembly: helper
3 other papers
3 later · 2 only as an assembly brick
2303.10108 (2023-03)
Data-Centric Learning from Unlabeled Graphs with Diffusion Model
2305.18407 (2023-05)
A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining
2403.16883 (2024-03)
GLAD: Improving Latent Graph Generative Modeling with Simple Quantization
Attention
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2303.10108 (2023-03)
Data-Centric Learning from Unlabeled Graphs with Diffusion Model
AttentionLayer
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2303.10108 (2023-03)
Data-Centric Learning from Unlabeled Graphs with Diffusion Model
BaselineNetworkLayer
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2303.10108 (2023-03)
Data-Centric Learning from Unlabeled Graphs with Diffusion Model
DenseGCNConv
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2303.10108 (2023-03)
Data-Centric Learning from Unlabeled Graphs with Diffusion Model
MLP
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2303.10108 (2023-03)
Data-Centric Learning from Unlabeled Graphs with Diffusion Model
glorot
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2303.10108 (2023-03)
Data-Centric Learning from Unlabeled Graphs with Diffusion Model
node_feature_to_matrix
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2303.10108 (2023-03)
Data-Centric Learning from Unlabeled Graphs with Diffusion Model
pow_tensor
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2303.10108 (2023-03)
Data-Centric Learning from Unlabeled Graphs with Diffusion Model
zeros
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2303.10108 (2023-03)
Data-Centric Learning from Unlabeled Graphs with Diffusion Model

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

Generating graph-structured data requires learning the underlying distribution of graphs. Yet, this is a challenging problem, and the previous graph generative methods either fail to capture the permutation-invariance property of graphs or cannot sufficiently model the complex dependency between nodes and edges, which is crucial for generating real-world graphs such as molecules. To overcome such limitations, we propose a novel score-based generative model for graphs with a continuous-time framework. Specifically, we propose a new graph diffusion process that models the joint distribution of the nodes and edges through a system of stochastic differential equations (SDEs). Then, we derive novel score matching objectives tailored for the proposed diffusion process to estimate the gradient of the joint logdensity with respect to each component, and introduce a new solver for the system of SDEs to efficiently sample from the reverse diffusion process. We validate our graph generation method on diverse datasets, on which it either achieves significantly superior or competitive performance to the baselines. Further analysis shows that our method is able to generate molecules that lie close to the training distribution yet do not violate the chemical valency rule, demonstrating the effectiveness of the system of SDEs in modeling the node-edge relationships. Our code is available at https://github.com/harryjo97/GDSS.

For agents

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

get_harvested_code_for_paper("2202.02514")
get_code_for_paper("2202.02514")
have("2202.02514")

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

curl https://syntology.ai/api/ran/2202.02514.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.02514.svg)](https://syntology.ai/paper/2202.02514)

Connect an agent — have() is free.