← Back to all news
arXiv AI

Reachability-Based Formal Verification of Graph Neural Networks with Node and Edge Features

The paper extends the neural network verification framework to graph neural networks by introducing GraphStar sets, which model uncertainty over both node and edge features. This allows sound propagation of linear message‑passing operations and ReLU nonlinearities for GCN and GINE layers. Experiments on power system tasks (PF, OPF, CFA) and graph classification benchmarks (ENZYMES, PROTEINS) show that the method, called GNNV, yields tighter robustness guarantees than CORA and provides, for the first time, edge‑aware guarantees for GINE‑based models under joint node and edge perturbations.

Related stories

arXiv Machine Learning
Sep 7

Physics-Aware Random Walk Fingerprints for Scalable Power Grid Graph Classification

The paper introduces Multi-Channel Physics-Aware Random Walk Fingerprints (MC-PA-RWF), a lightweight graph-level representation that incorporates physical edge states into random-walk propagation for power grid graphs. By constructing multiple edge-weighted channels from domain-relevant attributes and concatenating channel-specific fingerprints, the method achieves high balanced accuracy on PowerGraph benchmarks, outperforming topology-only RWF and matching or surpassing several graph neural network baselines. Experiments on three benchmark systems show statistically significant improvements, with the node-edge extension reaching up to 99.32% balanced accuracy and boosting failure-class F1 scores by 1.60–5.84 percentage points.

By Adnan Anwar
llmsbenchmarks
More like this →
arXiv AI
Sep 25

NNV3: Expanding Neural Network Verification to New Architectures and Domains

NNV3 is the latest version of the Neural Network Verification tool, a MATLAB framework for formally verifying deep learning models and learning‑enabled cyber‑physical systems. It builds on earlier NNV releases by adding new Star‑set members—ModelStar for weight perturbation, VolumeStar for video and 3D volumetric inputs, and GraphStar for graph neural networks—alongside a probabilistic reachability mode and FairNNV for fairness certification. The update also introduces benchmarks in malware detection, power‑system modeling, medical imaging, variable‑length time series, and action recognition, and provides unified documentation and tutorials.

By Anne M. Tumlin, Samuel Sasaki, Ben Wooding, Diego Manzanas Lopez, Muhammad Usama Zubair, Navid Hashemi, Hongchao Zhang, Waseem Abbas, Ipek Oguz, Meiyi Ma, Taylor T. Johnson
benchmarkssafety
More like this →
arXiv AI
Aug 18

Graph Machine Learning: An Opportunity for Power Systems

arXiv:2608. 16494v1 Announce Type: cross Abstract: Modern power systems face growing operational complexity driven by the integration of renewable energy sources, decentralization, and the need for real-time decision-making across a wide range of timescales.

By Martin Sadric, Sebastian P\"utz, Christian Nauck, Veit Hagenmeyer, Frank Hellmann, Dirk Witthaut, Benjamin Sch\"afer
benchmarkssafety
More like this →
arXiv AI
Jul 16

MxGPS: Multiplex Graph Transformers for a Power Grid Foundation Model

arXiv:2607. 13763v1 Announce Type: cross Abstract: Single-task fine-tuning of graph neural networks (GNNs) for power grid problems exhibits a systematic failure mode: models that achieve the lowest in-distribution error degrade the most under topology shift.

By Charilaos Papaioannou, Ioannis Tsantilas, Dimitris Giannakakos, Vasilis Michalakopoulos, Sotiris Pelekis, Vangelis Marinakis, Arsam Aryandoust, Antonello Monti, Ricardo J. Bessa, Perdo P. Vergara, Jochen Cremer, Elissaios Sarmas
llmsfine-tuningbenchmarks
More like this →
Hugging Face Trending Papers
Jul 15

MxGPS: Multiplex Graph Transformers for a Power Grid Foundation Model

Single-task fine-tuning of graph neural networks (GNNs) for power grid problems exhibits a systematic failure mode: models that achieve the lowest in-distribution error degrade the most under topology shift. We term this topology overfitting: the tendency of task-specific gradient signals to encode relational structure particular to the training topologies rather than the underlying physics, causing models to fail on unseen grids despite strong in-distribution performance.

llmsfine-tuningbenchmarks
More like this →
Hugging Face Trending Papers
Jun 1

GJDNet: Robust Graph Neural Networks via Joint Disentangled Learning Against Adversarial Attacks

Graph Neural Networks (GNNs) are vulnerable to adversarial attacks, which inherently invert connectivity patterns by introducing disassortative edges in assortative graphs and assortative edges in disassortative graphs. This structural inversion creates structure-feature mismatches that disrupt neighborhood aggregation across different graph types.

ragsafety
More like this →