相关论文: Transformer autoencoder with local attention for s…

Time series anomaly detection is crucial for maintaining stable systems. Existing methods face two main challenges. First, it is difficult to directly model the dependencies of diverse and complex patterns within the sequences. Second, many…

Recently, sparse autoencoders (SAEs) have emerged as a promising technique for interpreting activations in foundation models by disentangling features into a sparse set of concepts. However, identifying the optimal level of sparsity for…

The reliability assessment of a machine learning model's prediction is an important quantity for the deployment in safety critical applications. Not only can it be used to detect novel sceneries, either as out-of-distribution or anomaly…

Using a convGRU-based autoencoder, this thesis proposes a framework to learn spatial-temporal aspects of raw network traffic in an unsupervised and protocol-agnostic manner. The learned representations are used to measure the effect on the…

A new line of research for feature selection based on neural networks has recently emerged. Despite its superiority to classical methods, it requires many training iterations to converge and detect informative features. The computational…

Various modifications of TRANSFORMER were recently used to solve time-series forecasting problem. We propose Query Selector - an efficient, deterministic algorithm for sparse attention matrix. Experiments show it achieves state-of-the art…

The nuclear industry is advancing toward more new reactor designs, with next-generation reactors expected to be smaller in scale and power output. These systems have the potential to produce large volumes of information in the form of…

Irregularly-sampled time series occur in many domains including healthcare. They can be challenging to model because they do not naturally yield a fixed-dimensional representation as required by many standard machine learning models. In…

In this paper, we introduce \texttt{IAFormer}, a novel Transformer-based architecture that efficiently integrates pairwise particle interactions through a dynamic sparse attention mechanism. \texttt{IAFormer} has two new mechanisms within…

Irregular sampling occurs in many time series modeling applications where it presents a significant challenge to standard deep learning models. This work is motivated by the analysis of physiological time series data in electronic health…

Change point detection (CPD) aims to locate abrupt property changes in time series data. Recent CPD methods demonstrated the potential of using deep learning techniques, but often lack the ability to identify more subtle changes in the…

Anomalies refer to data points or events that deviate from normal and homogeneous events, which can include fraudulent activities, network infiltrations, equipment malfunctions, process changes, or other significant but infrequent events.…

Financial markets are inherently volatile and prone to sudden disruptions such as market crashes, flash collapses, and liquidity crises. Accurate anomaly detection and early risk forecasting in financial time series are therefore crucial…

Predicting high-dimensional dynamical systems with irregular time steps presents significant challenges for current data-driven algorithms. These irregularities arise from missing data, sparse observations, or adaptive computational…

Hacking and false data injection from adversaries can threaten power grids' everyday operations and cause significant economic loss. Anomaly detection in power grids aims to detect and discriminate anomalies caused by cyber attacks against…

This paper introduces an algorithm for the detection of change-points and the identification of the corresponding subsequences in transient multivariate time-series data (MTSD). The analysis of such data has become more and more important…

Many machine learning models use the manipulation of dimensions as a driving force to enable models to identify and learn important features in data. In the case of sequential data this manipulation usually happens on the token dimension…

The attention mechanism of a transformer has a quadratic complexity, leading to high inference costs and latency for long sequences. However, attention matrices are mostly sparse, which implies that many entries may be omitted from…

Vehicle platooning, with vehicles traveling in close formation coordinated through Vehicle-to-Everything (V2X) communications, offers significant benefits in fuel efficiency and road utilization. However, it is vulnerable to sophisticated…

Accurate P-wave detection is critical for earthquake early warning, yet strong-motion records pose challenges due to high noise levels, limited labeled data, and complex waveform characteristics. This study reframes P-wave arrival detection…