AI Paper Atlas

Research map / Time series / Anomaly detection

TeamWork: Multivariate Time Series Anomaly Detection via Asymmetric Role-aware Channel Modeling

Shiyan Hu, Tengxue Zhang, Jianxin Jin, Xiangfei Qiu, Bin Yang, Chenjuan Guo

ICML 2026 · Time series › Anomaly detection · approach: Multivariate anomaly detection

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
add dominant/auxiliary role-aware channel modeling instead of channel-independent modeling (ablation)TeamWork · Credit, Genesis, SMD (avg)Affiliated-F1: 0.864 -> 0.927Improved
add role-aware channel modeling instead of channel-dependent modeling (ablation)TeamWork · Credit, Genesis, SMD (avg)Affiliated-F1: 0.899 -> 0.927Improved
include dominant variables with their own branch (ablation)TeamWork · Credit, Genesis, SMD (avg)Affiliated-F1: 0.673 -> 0.927Improved
include auxiliary variables with a lightweight branch (ablation)TeamWork · Credit, Genesis, SMD (avg)Affiliated-F1: 0.902 -> 0.927Improved
assign roles by entropy reduction index instead of random assignment (ablation)TeamWork · Credit, Genesis, SMD (avg)Affiliated-F1: 0.867 -> 0.927Improved
use gated interaction instead of simple add fusion (ablation)TeamWork · Credit, Genesis, SMD (avg)Affiliated-F1: 0.889 -> 0.927Improved
add dominant-guided extraction block (ablation)TeamWork · Credit, Genesis, SMD (avg)Affiliated-F1: 0.908 -> 0.927Improved
add interaction gate layer (ablation)TeamWork · Credit, Genesis, SMD (avg)Affiliated-F1: 0.904 -> 0.927Improved
let auxiliary variables also guide dominant representation (bidirectional) (ablation)TeamWork · Credit, Genesis, SMD (avg)Affiliated-F1: 0.927 -> 0.917No clear effect
model auxiliary variables with the same period-aware masked modeling as dominant ones (ablation)TeamWork · Credit, Genesis, SMD (avg)Affiliated-F1: 0.927 -> 0.905No clear effect
use period-aware maskers instead of a fixed single masker (ablation)TeamWork · Credit, Genesis, SMD (avg)Affiliated-F1: 0.918 -> 0.927 (vs segment masker only)Improved
add maskers to the self-supervised reconstruction task (ablation)TeamWork · Credit, Genesis, SMD (avg)Affiliated-F1: 0.890 -> 0.927Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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