Wormhole: Concept-Aware Deep Representation Learning for Co-Evolving Sequences
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 21 of its 46 references that are in the map. First posted on arXiv 20 Sep 2024.
Builds on
21 of 46 references.
References · 21
- 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
- 2022Non-stationary Transformers: Exploring the Stationarity in Time Series Forecastingcited by 391
- 2023Dish-TS: A General Paradigm for Alleviating Distribution Shift in Time Series Forecastingcited by 93
- 2022Temporal Action Segmentation: An Analysis of Modern Techniquescited by 85
- 2023OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensemblingcited by 74
- 2024Kolmogorov-Arnold Networks for Time Series: Bridging Predictive Power and Interpretabilitycited by 70
- 2022Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting--Full Versioncited by 59
- 2017Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Datacited by 47
- 2022Learning Fast and Slow for Online Time Series Forecastingcited by 45
- 2022Temporal Domain Generalization with Drift-Aware Dynamic Neural Networkscited by 33
- 2019The FacT: Taming Latent Factor Models for Explainability with Factorization Treescited by 27
- 2024Real-Time Pill Identification for the Visually Impaired Using Deep Learningcited by 21
9 more
- 2023Online Boosting Adaptive Learning under Concept Drift for Multistream Classificationcited by 17
- 2023ZeroPrompt: Streaming Acoustic Encoders are Zero-Shot Masked LMscited by 13
- 2024Fostc3net:A Lightweight YOLOv5 Based On the Network Structure Optimizationcited by 12
- 2024Towards Invariant Time Series Forecasting in Smart Citiescited by 6
- 2024Learning Flexible Time-windowed Granger Causality Integrating Heterogeneous Interventional Time Series Datacited by 4
- 2022A Distributed Block Chebyshev-Davidson Algorithm for Parallel Spectral Clusteringcited by 2
- 2023DRNet: A Decision-Making Method for Autonomous Lane Changingwith Deep Reinforcement Learningcited by 2
- 2023Spectral Clustering via Orthogonalization-Free Methodscited by 1
- 2024Analyzing the factors that are involved in length of inpatient stay at the hospital for diabetes patientscited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.