← Back to all news
arXiv Machine Learning By Ayse Tursucular, Ayush Mohanty, Nazal Mohamed, Nagi Gebraeel

Federated Learning of Nonlinear Temporal Dynamics with Graph Attention-based Cross-Client Interpretability

Read the original on arXiv Machine Learning →

The paper introduces a vertical federated learning framework that learns one‑step‑ahead cross‑client temporal interdependencies in decentralized industrial systems with heterogeneous, proprietary models. Each client compresses high‑dimensional sensor data into low‑dimensional latent states via a nonlinear state‑space model, while a central Graph Attention Network (GAT) learns a state‑transition model and derives attention coefficients that reflect cross‑client interactions. The authors analytically link these attention coefficients to the Jacobian of the transition model, proving bounded closeness to a centralized oracle, and validate the approach with synthetic and real‑world experiments showing improved federated root‑cause analysis.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Sep 25

Beyond Static Graph World Models: Learning Stochastic Latent Dynamics over Evolving Topologies

The paper introduces the Graph Dynamics Model (GDM), a world model that learns stochastic latent dynamics over evolving graph topologies. GDM employs a sparse recurrent adjacency matrix for topology updates and a recurrent state‑space architecture for stochastic transitions, enabling it to handle partially observable, stochastic environments. The authors also propose the Graph Distribution Distance (GDD) metric, using maximum mean discrepancy with a graph kernel, to compare predicted and true joint graph state distributions, and demonstrate GDM’s superior performance and zero‑shot generalisation on large graphs.

By Alex Schutz, Nick Hawes, Victor-Alexandru Darvariu
More like this →
arXiv Machine Learning
Oct 9

Uncertainty Quantification in Federated Granger Causality Learning

The paper studies uncertainty quantification in federated Granger causality learning, where multiple parties cannot share data but need to infer predictive dependencies across clients. It addresses the challenge that clients observe different features and that cross-client edges must be estimated indirectly through iterative client‑server communication, which propagates both aleatoric and epistemic uncertainty. By deriving closed‑form variance recursions and steady‑state variances, the authors show that initial model‑parameter uncertainty diminishes asymptotically, enabling statistically principled selection of genuine cross‑client dependencies and improving edge recovery in synthetic and real industrial datasets.

By Ayush Mohanty, Nazal Mohamed, Nagi Gebraeel
More like this →
arXiv Machine Learning
Jul 20

Discovering Generalizable Governing Equations for Graph Dynamical Systems with Interpretable Neural Networks

arXiv:2508. 18173v2 Announce Type: replace Abstract: The discovery of symbolic governing equations is a central goal in science; yet, it remains challenging particularly for graph dynamical systems, where the network topology further shapes the system behavior.

By Riccardo Cappi, Paolo Frazzetto, Nicol\`o Navarin, Alessandro Sperduti
benchmarks
More like this →