AI Paper Atlas

Research map / Time series / Anomaly detection

Cluster-Aware Causal Mixer for Online Anomaly Detection in Multivariate Time Series

Md Mahmuddun Nabi Murad, Yasin Yilmaz

ICML 2026 · Time series › Anomaly detection · approach: Multivariate anomaly detection · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace point-based scoring with sequential evidence accumulation plus boundary correction (ablation)CCM-TAD · PSMbest-F1: 0.657 -> 0.716Improved
replace point-based scoring with sequential evidence accumulation plus boundary correction (ablation)CCM-TAD · MSLbest-F1: 0.557 -> 0.638Improved
add boundary correction to sequential scoring (ablation)CCM-TAD · SWaTbest-F1: 0.879 -> 0.883No clear effect
add channel clustering (Case 5 vs Case 10) (ablation)CCM-TAD · PSMbest-F1: 0.703 -> 0.716Improved
add channel clustering (Case 5 vs Case 10) (ablation)CCM-TAD · SWaTbest-F1: 0.865 -> 0.883Improved
use causal temporal mixer instead of non-causal mixer (with clustering) (ablation)CCM-TAD · PSMbest-F1: 0.652 -> 0.716Improved
add non-causal temporal mixer (vs none, with clustering) (ablation)CCM-TAD · PSMbest-F1: 0.657 -> 0.652No clear effect
add embedding mixer (causal mixer, with clustering) (ablation)CCM-TAD · PSMbest-F1: 0.681 -> 0.716Improved
add channel clustering to embedding (ablation)CCM-TAD · SWaTNN-sep: 65.63 -> 91.30Improved
add channel clustering to embedding (ablation)CCM-TAD · PSMNN-sep: 66.74 -> 66.78No clear effect
use spectral clustering on full correlation profile instead of K-Means on profiles (ablation)CCM-TAD · PSMbest-F1: 0.673 -> 0.716Improved
use CCM-TAD instead of SensitiveHUE (Offline)CCM-TAD · SWaTbest-F1: 0.911 -> 0.883Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy