SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.13406 · 2023

GNNDelete: A General Strategy for Unlearning in Graph Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 0 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/2302.13406.json · badge: /api/ran/2302.13406.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
mims-harvard/gnndelete canonical (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
FunctionStatusWhere it lives
get_node_embedding Ran
ran, honoured the contract we drafted
mims-harvard/gnndelete/delete_gnn.py
code served (permissive licence) · get_code("b836c7d8aaa7c9a4")
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, 3) as a later run recorded it. 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, 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)

# Build a minimal GNN model that accepts node features and edge_index
class SimpleGNN(nn.Module):
    def __init__(self, in_channels, out_channels):
        super().__init__()
        self.linear = nn.Linear(in_channels, out_channels)
    
    def forward(self, x, edge_index):
        # Just apply linear transformation for this minimal example
        return self.linear(x)

# Create model
model = SimpleGNN(in_channels=4, out_channels=3)

# Create a minimal data object with x and edge_index attributes
class MinimalData:
    def __init__(self, x, edge_index):
        self.x = x
        self.edge_index = edge_index

# Create tensors
# x: [num_nodes, num_features] - 2 nodes, 4 features
x = torch.randn(2, 4)

# edge_index: [2, num_edges] - 3 edges in COO format
edge_index = torch.tensor([[0, 1, 0], [1, 0, 1]], dtype=torch.long)

# Create data object
data = MinimalData(x=x, edge_index=edge_index)

ARGS = {
    'model': model,
    'data': data
}
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, 3) — shape (2, 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
get_output Not yet run
unverified (harvested, no recorded run)
mims-harvard/gnndelete/delete_gnn.py
code served (permissive licence) · get_code("b2407dc1099e083e")
How it ran

no invocation recorded.

load_args Not yet run
unverified (harvested, no recorded run)
mims-harvard/gnndelete/delete_gnn.py
code served (permissive licence) · get_code("3de8c8a7c355b7f5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 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.

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 unlearning, which involves deleting graph elements such as nodes, node labels, and relationships from a trained graph neural network (GNN) model, is crucial for real-world applications where data elements may become irrelevant, inaccurate, or privacy-sensitive. However, existing methods for graph unlearning either deteriorate model weights shared across all nodes or fail to effectively delete edges due to their strong dependence on local graph neighborhoods. To address these limitations, we introduce GNNDelete, a novel model-agnostic layer-wise operator that optimizes two critical properties, namely, Deleted Edge Consistency and Neighborhood Influence, for graph unlearning. Deleted Edge Consistency ensures that the influence of deleted elements is removed from both model weights and neighboring representations, while Neighborhood Influence guarantees that the remaining model knowledge is preserved after deletion. GNNDelete updates representations to delete nodes and edges from the model while retaining the rest of the learned knowledge. We conduct experiments on seven real-world graphs, showing that GNNDelete outperforms existing approaches by up to 38.8% (AUC) on edge, node, and node feature deletion tasks, and 32.2% on distinguishing deleted edges from non-deleted ones. Additionally, GNNDelete is efficient, taking 12.3x less time and 9.3x less space than retraining GNN from scratch on WordNet18.

For agents

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

get_harvested_code_for_paper("2302.13406")
get_code_for_paper("2302.13406")
have("2302.13406")

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

curl https://syntology.ai/api/ran/2302.13406.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.13406.svg)](https://syntology.ai/paper/2302.13406)

Connect an agent — have() is free.