paper-with-me

홈 › Papers

Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions

2023-06-27 · NeurIPS 2023 11 · Lukas Gosch, Simon Geisler, Daniel Sturm, Bertrand Charpentier, Daniel Zügner, Stephan Günnemann

Despite its success in the image domain, adversarial training did not (yet) stand out as an effective defense for Graph Neural Networks (GNNs) against graph structure perturbations. In the pursuit of fixing adversarial training (1) we show and overcome fundamental theoretical as well as practical limitations of the adopted graph learning setting in prior work; (2) we reveal that more flexible GNNs based on learnable graph diffusion are able to adjust to adversarial perturbations, while the learned message passing scheme is naturally interpretable; (3) we introduce the first attack for structure perturbations that, while targeting multiple nodes at once, is capable of handling global (graph-level) as well as local (node-level) constraints. Including these contributions, we demonstrate that adversarial training is a state-of-the-art defense against adversarial structure perturbations.

📄 PDF Abstract BibTeX arXiv:2306.15427

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Learning

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Single-GPU GNN Systems: Traps and Pitfalls

2024-02-05 · Yidong Gong, Arnab Tarafder, Saima Afrin, Pradeep Kumar

The current graph neural network (GNN) systems have established a clear trend of not showing training accuracy results, and directly or indirectly relying on smaller datasets for evaluations majorly. Our in-depth analysi…

GPUGraph Neural Network

Considerations, Good Practices, Risks and Pitfalls in Developing AI Solutions Against COVID-19

2020-08-13 · Alexandra Luccioni, Joseph Bullock, Katherine Hoffmann Pham, Cynthia Sin Nga Lam 외

The COVID-19 pandemic has been a major challenge to humanity, with 12.7 million confirmed cases as of July 13th, 2020 [1]. In previous work, we described how Artificial Intelligence can be used to tackle the pandemic wit…

Evaluation Metrics for Graph Generative Models: Problems, Pitfalls, and Practical Solutions

2021-06-02 · ICLR 2022 4 · Leslie O'Bray, Max Horn, Bastian Rieck, Karsten Borgwardt

Graph generative models are a highly active branch of machine learning. Given the steady development of new models of ever-increasing complexity, it is necessary to provide a principled way to evaluate and compare them. …

A GAN Approach for Node Embedding in Heterogeneous Graphs Using Subgraph Sampling

2023-12-11 · Hung-Chun Hsu, Bo-Jun Wu, Ming-Yi Hong, Che Lin 외

Graph neural networks (GNNs) face significant challenges with class imbalance, leading to biased inference results. To address this issue in heterogeneous graphs, we propose a novel framework that combines Graph Neural N…

Generative Adversarial NetworkGraph Neural Network

SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity

2026-02-09 · Shae McFadden, Myles Foley, Elizabeth Bates, Ilias Tsingenopoulos 외 arxiv

Deep Reinforcement Learning (DRL) has achieved remarkable success in domains requiring sequential decision-making, motivating its application to cybersecurity problems. However, transitioning DRL from laboratory simulati…

Reinforcement Learning