Wormhole: Concept-Aware Deep Representation Learning for Co-Evolving Sequences
This addresses the need for better analysis of complex temporal patterns in domains like IoT and finance, though it appears incremental as it builds on existing representation learning methods.
The paper tackles the problem of identifying dynamic concepts in co-evolving sequences, such as IoT or financial data, by introducing Wormhole, a deep learning framework that segments time series into meaningful concepts and detects transitions with enhanced interpretability.
Identifying and understanding dynamic concepts in co-evolving sequences is crucial for analyzing complex systems such as IoT applications, financial markets, and online activity logs. These concepts provide valuable insights into the underlying structures and behaviors of sequential data, enabling better decision-making and forecasting. This paper introduces Wormhole, a novel deep representation learning framework that is concept-aware and designed for co-evolving time sequences. Our model presents a self-representation layer and a temporal smoothness constraint to ensure robust identification of dynamic concepts and their transitions. Additionally, concept transitions are detected by identifying abrupt changes in the latent space, signifying a shift to new behavior - akin to passing through a wormhole. This novel mechanism accurately discerns concepts within co-evolving sequences and pinpoints the exact locations of these wormholes, enhancing the interpretability of the learned representations. Experiments demonstrate that this method can effectively segment time series data into meaningful concepts, providing a valuable tool for analyzing complex temporal patterns and advancing the detection of concept drifts.