Related papers: Multi-scale Attention Flow for Probabilistic Time …

The non-stationary nature of real-world Multivariate Time Series (MTS) data presents forecasting models with a formidable challenge of the time-variant distribution of time series, referred to as distribution shift. Existing studies on the…

We propose an unsupervised anomaly detection approach based on a physics-informed diffusion model for multivariate time series data. Over the past years, diffusion model has demonstrated its effectiveness in forecasting, imputation,…

Unsupervised detection of anomaly points in time series is a challenging problem, which requires the model to derive a distinguishable criterion. Previous methods tackle the problem mainly through learning pointwise representation or…

Multi-horizon forecasting problems often contain a complex mix of inputs -- including static (i.e. time-invariant) covariates, known future inputs, and other exogenous time series that are only observed historically -- without any prior…

Probabilistic time series forecasting involves estimating the distribution of future based on its history, which is essential for risk management in downstream decision-making. We propose a deep state space model for probabilistic time…

This work contributes to the development of neural forecasting models with novel randomization-based learning methods. These methods improve the fitting abilities of the neural model, in comparison to the standard method, by generating…

Non-stationarity is an intrinsic property of real-world time series and plays a crucial role in time series forecasting. Previous studies primarily adopt instance normalization to attenuate the non-stationarity of original series for better…

In the hydrology field, time series forecasting is crucial for efficient water resource management, improving flood and drought control and increasing the safety and quality of life for the general population. However, predicting long-term…

A variety of real-world applications rely on far future information to make decisions, thus calling for efficient and accurate long sequence multivariate time series forecasting. While recent attention-based forecasting models show strong…

Forecasting with multivariate time series, which aims to predict future values given previous and current several univariate time series data, has been studied for decades, with one example being ARIMA. Because it is difficult to measure…

Multivariate time series classification (MTSC) plays a crucial role in various domains, including biomedical signal analysis and motion monitoring. However, existing approaches, particularly deep learning models, often require high…

Traffic time series forecasting is challenging due to complex spatio-temporal dynamics time series from different locations often have distinct patterns; and for the same time series, patterns may vary across time, where, for example, there…

Analyzing and interpreting time-dependent stochastic data requires accurate and robust density estimation. In this paper we extend the concept of normalizing flows to so-called temporal Normalizing Flows (tNFs) to estimate time dependent…

The task of multi-channel time series forecasting is ubiquitous in numerous fields such as finance, supply chain management, and energy planning. It is critical to effectively capture complex dynamic dependencies within and between channels…

Unsupervised learning from continuous visual streams is a challenging problem that cannot be naturally and efficiently managed in the classic batch-mode setting of computation. The information stream must be carefully processed accordingly…

Neural attention has become central to many state-of-the-art models in natural language processing and related domains. Attention networks are an easy-to-train and effective method for softly simulating alignment; however, the approach does…

The rise of mobile devices equipped with numerous sensors, such as LiDAR and cameras, has spurred the adoption of multi-modal deep intelligence for distributed sensing tasks, such as smart cabins and driving assistance. However, the arrival…

Feature selection is essential for high-dimensional biomedical data, enabling stronger predictive performance, reduced computational cost, and improved interpretability in precision medicine applications. Existing approaches face notable…

Monitoring complex systems results in massive multivariate time series data, and anomaly detection of these data is very important to maintain the normal operation of the systems. Despite the recent emergence of a large number of anomaly…

This paper is a contribution towards interpretability of the deep learning models in different applications of time-series. We propose a temporal attention layer that is capable of selecting the relevant information to perform various…