TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning
This addresses the challenge of pattern localization in time series data for applications like ECG analysis, representing an incremental improvement over existing deep learning methods.
The paper tackled the problem of multivariate time series classification by reformulating it as a weakly supervised task to better handle sparse and local patterns, and introduced TimeMIL, which surpassed 26 state-of-the-art methods.
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 modeling time dependencies within time series. Our novel approach, TimeMIL, formulates the temporal correlation and ordering within a time-aware MIL pooling, leveraging a tokenized transformer with a specialized learnable wavelet positional token. The proposed method surpassed 26 recent state-of-the-art methods, underscoring the effectiveness of the weakly supervised TimeMIL in MTSC. The code will be available at https://github.com/xiwenc1/TimeMIL.