Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces CANDI, a test-time adaptation (TTA) framework for multivariate time-series anomaly detection (MTSAD) that addresses performance degradation caused by distribution shifts. CANDI employs a False Positive Mining (FPM) strategy to select adaptation samples and a Spatiotemporally-Aware Normality Adaptation (SANA) module for model updates. Experiments show CANDI improves AUROC by up to 14% compared to existing methods, while using fewer adaptation samples.
Adapting anomaly detectors on the fly with carefully curated samples boosts performance by 14% under distribution shift, proving that targeted adaptation beats brute-force fine-tuning.
Multivariate time-series anomaly detection (MTSAD) aims to identify deviations from normality in multivariate time-series and is critical in real-world applications. However, in real-world deployments, distribution shifts are ubiquitous and cause severe performance degradation in pre-trained anomaly detector. Test-time adaptation (TTA) updates a pre-trained model on-the-fly using only unlabeled test data, making it promising for addressing this challenge. In this study, we propose CANDI (Curated test-time adaptation for multivariate time-series ANomaly detection under DIstribution shift), a novel TTA framework that selectively identifies and adapts to potential false positives while preserving pre-trained knowledge. CANDI introduces a False Positive Mining (FPM) strategy to curate adaptation samples based on anomaly scores and latent similarity, and incorporates a plug-and-play Spatiotemporally-Aware Normality Adaptation (SANA) module for structurally informed model updates. Extensive experiments demonstrate that CANDI significantly improves the performance of MTSAD under distribution shift, improving AUROC up to 14% while using fewer adaptation samples.