Multivariate time series classification (TSC) is critical for various applications in fields such as healthcare and finance. While various approaches for TSC have been explored, important properties of time series, such as shift equivariance and inversion invariance, are largely underexplored by existing works. To fill this gap, we propose a novel multi-view approach to capture patterns with properties like shift equivariance. Our method integrates diverse features, including spectral, temporal, local, and global features, to obtain rich, complementary contexts for TSC. We use continuous wavelet transform to capture time-frequency features that remain consistent even when the input is shifted in time. These features are fused with temporal convolutional or multilayer perceptron features to provide complex local and global contextual information. We utilize the Mamba state space model for efficient and scalable sequence modeling and capturing long-range dependencies in time series. Moreover, we introduce a new scanning scheme for Mamba, called tango scanning, to effectively model sequence relationships and leverage inversion invariance, thereby enhancing our model's generalization and robustness. Experiments on two sets of benchmark datasets (10+20 datasets) demonstrate our approach's effectiveness, achieving average accuracy improvements of 4.01-6.45\% and 7.93\% respectively, over leading TSC models such as TimesNet and TSLANet.
Mammo-Mamba: A Hybrid State-Space and Transformer Architecture with Sequential Mixture of Experts for Multi-View Mammography
Concordia Institute for Information Systems Engineering (CIISE)（康科德信息系统工程研究所）；Concordia University（康科德大学）；Thomas Jefferson University Hospital（托马斯·杰斐逊大学医院）
DART: Decoded Attention over Recurrent States for Efficient Long-Context Sequence Modeling
College of Control Science and Engineering, Zhejiang University（浙江大学控制科学与工程学院）；National University of Singapore（新加坡国立大学）；Hong Kong Polytechnic University（香港理工大学）；School of Science, Huzhou Normal University（湖州师范学院理学院）
MEET-Sepsis: Multi-Endogenous-View Enhanced Time-Series Representation Learning for Early Sepsis Prediction
Guangdong University of Technology（广东技术大学）；Women and Children's Medical Center of Southern Medical University（南方医科大学妇女儿童医疗中心）；Shenzhen Maternity and Child Healthcare Hospital（深圳妇幼保健医院）；Shenzhen BH-Energy Technology Co., Ltd.（深圳BH能源科技有限公司）；Hong Kong Baptist University（香港 Baptist大学）
Southwest Jiaotong University（西南交通大学）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Dalian University of Technology（大连理工大学）
Beyond existing multi-view clustering, this paper studies a more realistic clustering scenario, referred to as incomplete multi-view clustering, where a number of data instances are missing in certain views. To tackle this problem, we explore spectral perturbation theory. In this work, we show a strong link between perturbation risk bounds and incomplete multi-view clustering. That is, as the similarity matrix fed into spectral clustering is a quantity bounded in magnitude O(1), we transfer the missing problem from data to similarity and tailor a matrix completion method for incomplete similar…
In this work we unify a number of inference learning methods, that are proposed in the literature as alternative training algorithms to the ones based on regular error back-propagation. These inference learning methods were developed with very diverse motivations, mainly aiming to enhance the biological plausibility of deep neural networks and to improve the intrinsic parallelism of training methods. We show that these superficially very different methods can all be obtained by successively applying a particular reformulation of bilevel optimization programs. As a by-product it becomes also ev…
