SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2510.22643 · NeurIPS · 2025

Enhancing Graph Classification Robustness with Singular Pooling

Johannes Lutzeyer, Sofiane Ennadir, Oleg Smirnov, Lele Cao

arXiv · PDF · Open in the Atlas

Code that ran

4 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 0 have no contract verdict; 4 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2510.22643.json · badge: /api/ran/2510.22643.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
king/rs-pool canonical (classifier label)
classifier basis: census
4 ran · 1 no recorded run
FunctionStatusWhere it lives
apply_edge_flips Ran
ran; our contract draft was wrong, not the code
king/rs-pool/src/attacks/random_attack.py
pointer only (licence: NOASSERTION) · get_code("80998cdf5a7a164b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, king/rs-pool (NOASSERTION). 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.

normalize_tensor_adj Ran
ran; our contract draft was wrong, not the code
king/rs-pool/src/models/utils.py
pointer only (licence: NOASSERTION) · get_code("2a106b8d2e180647")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, king/rs-pool (NOASSERTION). 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.

random_sample_flip Ran
ran; our contract draft was wrong, not the code
king/rs-pool/src/attacks/random_attack.py
pointer only (licence: NOASSERTION) · get_code("6805f73c93f42f76")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, king/rs-pool (NOASSERTION). 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.

sparse_mx_to_torch_sparse_tensor Ran
ran; our contract draft was wrong, not the code
king/rs-pool/src/models/utils.py
pointer only (licence: NOASSERTION) · get_code("208d1e7dd9c65347")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, king/rs-pool (NOASSERTION). 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.

train_function Not yet run
unverified (harvested, no recorded run)
king/rs-pool/src/models/utils.py
pointer only (licence: NOASSERTION) · get_code("41eab6a5334d5add")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, king/rs-pool (NOASSERTION). 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 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 (1 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
sparse_mx_to_torch_sparse_tensor 32 other papers
31 dated earlier, 1 later · 4 only as an assembly brick
1806.09055 (2018-06)
DARTS: Differentiable Architecture Search
1902.07153 (2019-02)
Simplifying Graph Convolutional Networks
2002.01633 (2020-02)
Structural Deep Clustering Network
and 29 more not named here

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) have achieved strong performance across a range of graph representation learning tasks, yet their adversarial robustness in graph classification remains underexplored compared to node classification. While most existing defenses focus on the message-passing component, this work investigates the overlooked role of pooling operations in shaping robustness. We present a theoretical analysis of standard flat pooling methods (sum, average and max), deriving upper bounds on their adversarial risk and identifying their vulnerabilities under different attack scenarios and graph structures. Motivated by these insights, we propose Robust Singular Pooling (RS-Pool), a novel pooling strategy that leverages the dominant singular vector of the node embedding matrix to construct a robust graph-level representation. We theoretically investigate the robustness of RS-Pool and interpret the resulting bound leading to improved understanding of our proposed pooling operator. While our analysis centers on Graph Convolutional Networks (GCNs), RS-Pool is model-agnostic and can be implemented efficiently via power iteration. Empirical results on real-world benchmarks show that RS-Pool provides better robustness than the considered pooling methods when subject to state-of-the-art adversarial attacks while maintaining competitive clean accuracy. Our code is publicly available at: https://github.com/king/rs-pool.

For agents

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

get_harvested_code_for_paper("2510.22643")
get_code_for_paper("2510.22643")
have("2510.22643")

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

curl https://syntology.ai/api/ran/2510.22643.json

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

[![Syntology run record](https://syntology.ai/api/ran/2510.22643.svg)](https://syntology.ai/paper/2510.22643)

Connect an agent — have() is free.