TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning

arXiv:2405.03140v1 Announce Type: new
Abstract: Deep neural networks, including transformers and convolutional neural networks, have significantly improved multivariate time series classification (MTSC). However, these methods often rely on supervised learning, which does not fully account for the sparsity and locality of patterns in time series data (e.g., diseases-related anomalous points in ECG). To address this challenge, we formally reformulate MTSC as a weakly supervised problem, introducing a novel multiple-instance learning (MIL) framework for better localization of patterns of interest and …

abstract arxiv classification convolutional convolutional neural networks cs.lg data diseases however instance multiple multivariate networks neural networks patterns series sparsity supervised learning time series transformers type via