paper-with-me

Papers

Expressivity of Graph Neural Networks Through the Lens of Adversarial Robustness

2023-08-16 · Francesco Campi, Lukas Gosch, Tom Wollschläger, Yan Scholten, Stephan Günnemann

We perform the first adversarial robustness study into Graph Neural Networks (GNNs) that are provably more powerful than traditional Message Passing Neural Networks (MPNNs). In particular, we use adversarial robustness as a tool to uncover a significant gap between their theoretically possible and empirically achieved expressive power. To do so, we focus on the ability of GNNs to count specific subgraph patterns, which is an established measure of expressivity, and extend the concept of adversarial robustness to this task. Based on this, we develop efficient adversarial attacks for subgraph counting and show that more powerful GNNs fail to generalize even to small perturbations to the graph's structure. Expanding on this, we show that such architectures also fail to count substructures on out-of-distribution graphs.

📄 PDF Abstract BibTeX arXiv:2308.08173

Code (1)

francesco-campi/rob-subgraphs 공식 구현 pytorch

Tasks

Adversarial RobustnessSubgraph Counting

Methods 이 논문이 사용한 방법론

fail 설명 없음
Focus 설명 없음

Similar Papers 제목 키워드 기반

The Geometry of ReLU Networks through the ReLU Transition Graph

2025-05-16 · Sahil Rajesh Dhayalkar

We develop a novel theoretical framework for analyzing ReLU neural networks through the lens of a combinatorial object we term the ReLU Transition Graph (RTG). In this graph, each node corresponds to a linear region indu…

Expressive Losses for Verified Robustness via Convex Combinations

2023-05-23 · Alessandro De Palma, Rudy Bunel, Krishnamurthy Dvijotham, M. Pawan Kumar 외

In order to train networks for verified adversarial robustness, it is common to over-approximate the worst-case loss over perturbation regions, resulting in networks that attain verifiability at the expense of standard p…

Adversarial Robustness

On the Expressive Power of GNNs for Boolean Satisfiability

2026-02-09 · Saku Peltonen, Roger Wattenhofer arxiv

Machine learning approaches to solving Boolean Satisfiability (SAT) aim to replace handcrafted heuristics with learning-based models. Graph Neural Networks have emerged as the main architecture for SAT solving, due to th…

Resilient Graph Neural Networks: A Coupled Dynamical Systems Approach

2023-11-12 · Moshe Eliasof, Davide Murari, Ferdia Sherry, Carola-Bibiane Schönlieb

Graph Neural Networks (GNNs) have established themselves as a key component in addressing diverse graph-based tasks. Despite their notable successes, GNNs remain susceptible to input perturbations in the form of adversar…

Audio-Visual Event Recognition through the lens of Adversary

2020-11-15 · Juncheng B Li, Kaixin Ma, Shuhui Qu, Po-Yao Huang 외

As audio/visual classification models are widely deployed for sensitive tasks like content filtering at scale, it is critical to understand their robustness along with improving the accuracy. This work aims to study seve…