paper-with-me

홈 › Papers

Correlated Attention in Transformers for Multivariate Time Series

2023-11-20 · Quang Minh Nguyen, Lam M. Nguyen, Subhro Das

Multivariate time series (MTS) analysis prevails in real-world applications such as finance, climate science and healthcare. The various self-attention mechanisms, the backbone of the state-of-the-art Transformer-based models, efficiently discover the temporal dependencies, yet cannot well capture the intricate cross-correlation between different features of MTS data, which inherently stems from complex dynamical systems in practice. To this end, we propose a novel correlated attention mechanism, which not only efficiently captures feature-wise dependencies, but can also be seamlessly integrated within the encoder blocks of existing well-known Transformers to gain efficiency improvement. In particular, correlated attention operates across feature channels to compute cross-covariance matrices between queries and keys with different lag values, and selectively aggregate representations at the sub-series level. This architecture facilitates automated discovery and representation learning of not only instantaneous but also lagged cross-correlations, while inherently capturing time series auto-correlation. When combined with prevalent Transformer baselines, correlated attention mechanism constitutes a better alternative for encoder-only architectures, which are suitable for a wide range of tasks including imputation, anomaly detection and classification. Extensive experiments on the aforementioned tasks consistently underscore the advantages of correlated attention mechanism in enhancing base Transformer models, and demonstrate our state-of-the-art results in imputation, anomaly detection and classification.

📄 PDF Abstract BibTeX arXiv:2311.11959

Code (0)

등록된 구현이 없습니다.

Tasks

Anomaly DetectionImputationRepresentation LearningTime Series

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

Using Pre-trained LLMs for Multivariate Time Series Forecasting

2025-01-10 · Malcolm L. Wolff, Shenghao Yang, Kari Torkkola, Michael W. Mahoney

Pre-trained Large Language Models (LLMs) encapsulate large amounts of knowledge and take enormous amounts of compute to train. We make use of this resource, together with the observation that LLMs are able to transfer kn…

DecoderMultivariate Time Series ForecastingTime SeriesTime Series Forecasting

MICA: Multivariate Infini Compressive Attention for Time Series Forecasting

2026-04-07 · Willa Potosnak, Nina Żukowska, Michał Wiliński, Dan Howarth 외 arxiv

Multivariate forecasting with Transformers faces a core scalability challenge: modeling cross-channel dependencies via attention compounds attention's quadratic sequence complexity with quadratic channel scaling, making …

Time Series Forecasting

STING: Self-attention based Time-series Imputation Networks using GAN

2022-09-22 · Eunkyu Oh, Taehun Kim, Yunhu Ji, Sushil Khyalia

Time series data are ubiquitous in real-world applications. However, one of the most common problems is that the time series data could have missing values by the inherent nature of the data collection process. So imputi…

ImputationMissing ValuesTime SeriesTime Series Analysis

A Deep Structural Model for Analyzing Correlated Multivariate Time Series

2020-01-02 · Changwei Hu, Yifan Hu, Sungyong Seo

Multivariate time series are routinely encountered in real-world applications, and in many cases, these time series are strongly correlated. In this paper, we present a deep learning structural time series model which ca…

Time SeriesTime Series Analysis

Deep Generative Transformers for Probabilistic Time Series and Spatiotemporal Forecasting

2026-03-12 · Rajdeep Pathak, Rahul Goswami, Madhurima Panja, Palash Ghosh 외 arxiv

Reliable uncertainty quantification is paramount for forecasting multivariate time series and spatiotemporal data. While Transformer architectures excel at sequence modeling, current probabilistic approaches typically re…