AI Paper Atlas

Research map / Time series / Anomaly detection

TimeLAVA: Learning-Agnostic Valuation for Time Series Data

Wenqin Liu, Weizhi Quan, Aoqi Zuo, Erdun Gao, Vu Nguyen, Dino Sejdinovic, Howard Bondell, Mingming Gong

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
use TimeLAVA instead of TimeInf for anomaly scoringTimeInf · SMDAUC: 0.87 -> 0.91Improved
use TimeLAVA instead of TimeInf for anomaly scoringTimeInf · PSMF1: 0.02 -> 0.58Improved
use TimeLAVA instead of Isolation Forest for anomaly scoringIsolation Forest · MSLAUC: 0.68 -> 0.81Improved
use TimeLAVA instead of TimeInf for anomaly runtimeTimeInf · SMAPruntime (s): 10.59 -> 0.72Improved
use TimeLAVA instead of TimeInf for corrupted-segment detectionTimeInf · ExchangeROC AUC: 0.542 -> 0.782Improved
use TimeLAVA instead of KNN-Shapley for corrupted-segment detectionKNN-Shapley · ExchangeROC AUC: 0.520 -> 0.782Improved
use TimeLAVA instead of TimeInf under periodic label noiseTimeInf · Moving periodic noise 15%F1: 0.65 -> 0.78Improved
use TimeLAVA instead of KNN-Shapley under random label noiseKNN-Shapley · Moving random noiseF1No clear effect
vary wavelet basis and decomposition level (ablation)TimeLAVA · SMDAUC: 0.87 to 0.91No clear effect
increase segment length beyond 100-150 (ablation)TimeLAVA · anomaly detectionAUCNo clear effect
vary label consistency weight c away from 1 (ablation)TimeLAVA · label-aware valuationperformanceHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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