arXiv Machine Learning
Jun 2
Modeling Spectral Energy Shifts in Spatio-Temporal Graph Anomaly Detection
arXiv:2606. 00304v1 Announce Type: new Abstract: Graph anomaly detection methods aim to distinguish anomalous nodes.
Graph-Spectral Flow Matching for Multivariate Time Series Anomaly Detection
Related stories
arXiv Machine Learning
Sep 15
GSLAD: Prototype-Regularized Graph Structure Learning for Multivariate Time Series Anomaly Detection
arXiv:2609.15483v1 Announce Type: new Abstract: Unsupervised multivariate time series anomaly detection methods typically identify anomalies through forecasting, reconstruction, or representation dis...
arXiv AI
Jun 2
Learning Discriminative and Generalizable Anomaly Detector for Dynamic Graph with Limited Supervision
arXiv:2602. 20019v2 Announce Type: replace-cross Abstract: Dynamic graph anomaly detection is critical for many real-world applications but remains challenging due to the scarcity of labeled anomalies.
arXiv AI
Jul 9
Anomaly detection in time-series via inductive biases in the latent space of conditional normalizing flows
arXiv:2603. 11756v2 Announce Type: replace Abstract: Deep generative models for anomaly detection in multivariate time-series are typically trained by maximizing observed data likelihood.
arXiv Machine Learning
Jul 31
ARES: Anomaly Recognition Model For Edge Streams
arXiv:2511. 22078v2 Announce Type: replace Abstract: Many real-world scenarios involving streaming information can be represented as temporal graphs, where data flows through dynamic changes in edges over time.
arXiv AI
Sep 1
Zero-shot Generalizable Graph Anomaly Detection with Mixture of Riemannian Experts
arXiv:2602.06859v3 Announce Type: replace-cross Abstract: Graph Anomaly Detection (GAD) aims to identify irregular patterns in graph data, and recent works have explored zero-shot generalist GAD to e...
arXiv AI
Jul 20
Knowledge-Assisted Multi-Graph Dependency Learning for Multivariate Time Series Anomaly Detection in Multi-Stage Industrial Processes
arXiv:2607. 15799v1 Announce Type: cross Abstract: Industrial processes often generate complex, interdependent time-series data from multiple sensors across multiple stages, forming complex dependencies among variables and process stages.
arXiv Machine Learning
Sep 7
GLASS: Graph-Language Alignment with Spherical Scoring for Transferable Graph-Level Anomaly Detection
GLASS is a graph‑level anomaly detection framework that aligns graph and language representations on a unit hypersphere to achieve cross‑domain transferability. It constructs a Graph Descriptor Prompt to encode local, global, and semantic graph properties, and uses a multi‑slice soft cosine objective to unify graph and text embeddings. Anomaly scoring is performed via spherical density estimation with von Mises‑Fisher kernels, enabling zero‑shot detection and few‑shot adaptation across twelve benchmarks and three meta‑domains, outperforming recent GLAD baselines.
arXiv Machine Learning
Aug 21
Unsupervised Anomaly Detection Using Flow Matching on Tabular Data
arXiv:2608. 19801v1 Announce Type: new Abstract: Financial anomaly detection often relies on large unlabeled transaction logs, where anomalous samples may already be present during training.
Hugging Face Trending Papers
Jul 14
The Geometry of Memorization: Finite-Time Spectral Sensitivity as a Diagnostic for Flow Matching Models
Continuous-time generative frameworks construct probability paths between base and target domains by optimizing time-dependent velocity fields. While theoretical targets favor straight trajectories, empirical networks develop complex path deformations.
arXiv Machine Learning
Sep 24
CAST: Context- and Anomaly Structure-Conditioned Time Series Anomaly Generation
CAST is a framework for generating anomalous time series that addresses the scarcity and heterogeneity of anomaly data. It uses a two‑stage approach: pretraining on abundant normal data to learn system dynamics, then finetuning with anomaly structure representations to capture diverse anomaly morphologies. Experiments on real‑world datasets show that CAST outperforms existing methods in both generation quality and downstream task performance.
arXiv Machine Learning
Aug 18
Beat the Counter First: A Baseline for Temporal-Graph Anomaly Detectors
arXiv:2608. 15965v1 Announce Type: new Abstract: Progress in streaming, edge-level graph anomaly detection (GAD) has been marked by increasingly elaborate architectures, from count-min-sketch chi square tests to memory-augmented attention networks.