Time-series Anomaly Detection via Contextual Discriminative Contrastive Learning

no code implementations • 16 Apr 2023 • Katrina Chen, Mingbin Feng, Tony S. Wirjanto

We provide a theoretical analysis to demonstrate that the incorporation of the deterministic contrastive loss can effectively prevent the occurrence of a constant encoder solution.

Contrastive Learning One-Class Classification +3

Multivariate Time Series Anomaly Detection via Dynamic Graph Forecasting

no code implementations • 4 Feb 2023 • Katrina Chen, Mingbin Feng, Tony S. Wirjanto

Some other works detect anomalies based on reconstructing or forecasting a list of inter-series graphs, which inadvertently weakens their power to capture temporal patterns within the data due to the discrete nature of graphs.

Anomaly Detection Time Series +2

GEDI: A Graph-based End-to-end Data Imputation Framework

no code implementations • 13 Aug 2022 • Katrina Chen, Xiuqin Liang, Zheng Ma, Zhibin Zhang

Data imputation is an effective way to handle missing data, which is common in practical applications.

Graph structure learning Imputation +1