**KDD 2021: Multivariate Time Series Anomaly Detection and Interpretation using Hierarchical Inter-Metric and Temporal Embedding**
InterFusion is an unsupervised MTS anomaly detection and interpretation method. It's core idea is to model the normal patterns of MTS using HVAE with jointly trained hierarchical stochastic latent variables, each of which explicitly learns low-dimensional inter-metric or temporal embeddings. You may refer to our [paper](https://dl.acm.org/doi/abs/10.1145/3447548.3467075) for more details.