Graph-Spectral Flow Matching for Multivariate Time Series Anomaly Detection

arXiv:2609.36765 · cs.LG · Submitted 2026-09-29 · Read on arXiv

cs.LG

Submitted: 2026-09-29

Updated: 2026-09-29

Terminology

• Flow Matching — 1× in this paper · explained in 10 episodes

Sources

• Layer Normalization
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Flow Mismatching: Unsupervised Anomaly Detection via Velocity Discrepancies in Flow Matching Models
• Lagrangian Flow Matching: A Least-Action Framework for Principled Path Design
• Escaping the Euclidean Void: Manifold-Informed Flow Matching for Sequential Recommendation
• GSLAD: Prototype-Regularized Graph Structure Learning for Multivariate Time Series Anomaly Detection

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks