# Wormhole: Concept-Aware Deep Representation Learning for Co-Evolving Sequences

arXiv: https://arxiv.org/abs/2409.13857 · HTML: https://mlsanity.com/paper/2409.13857/

## Key facts

- Cited by 1 papers 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 (most cited first, 21 of 21)

- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting](https://mlsanity.com/paper/2205.14415/) (2022)
- [Dish-TS: A General Paradigm for Alleviating Distribution Shift in Time Series Forecasting](https://mlsanity.com/paper/2302.14829/) (2023)
- [Temporal Action Segmentation: An Analysis of Modern Techniques](https://mlsanity.com/paper/2210.10352/) (2022)
- [OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling](https://mlsanity.com/paper/2309.12659/) (2023)
- [Kolmogorov-Arnold Networks for Time Series: Bridging Predictive Power and Interpretability](https://mlsanity.com/paper/2406.02496/) (2024)
- [Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting--Full Version](https://mlsanity.com/paper/2204.13767/) (2022)
- [Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Data](https://mlsanity.com/paper/1706.03161/) (2017)
- [Learning Fast and Slow for Online Time Series Forecasting](https://mlsanity.com/paper/2202.11672/) (2022)
- [Temporal Domain Generalization with Drift-Aware Dynamic Neural Networks](https://mlsanity.com/paper/2205.10664/) (2022)
- [The FacT: Taming Latent Factor Models for Explainability with Factorization Trees](https://mlsanity.com/paper/1906.02037/) (2019)
- [Real-Time Pill Identification for the Visually Impaired Using Deep Learning](https://mlsanity.com/paper/2405.05983/) (2024)
- [Online Boosting Adaptive Learning under Concept Drift for Multistream Classification](https://mlsanity.com/paper/2312.10841/) (2023)
- [ZeroPrompt: Streaming Acoustic Encoders are Zero-Shot Masked LMs](https://mlsanity.com/paper/2305.10649/) (2023)
- [Fostc3net:A Lightweight YOLOv5 Based On the Network Structure Optimization](https://mlsanity.com/paper/2403.13703/) (2024)
- [Towards Invariant Time Series Forecasting in Smart Cities](https://mlsanity.com/paper/2405.05430/) (2024)
- [Learning Flexible Time-windowed Granger Causality Integrating Heterogeneous Interventional Time Series Data](https://mlsanity.com/paper/2406.10419/) (2024)
- [A Distributed Block Chebyshev-Davidson Algorithm for Parallel Spectral Clustering](https://mlsanity.com/paper/2212.04443/) (2022)
- [DRNet: A Decision-Making Method for Autonomous Lane Changingwith Deep Reinforcement Learning](https://mlsanity.com/paper/2311.01602/) (2023)
- [Spectral Clustering via Orthogonalization-Free Methods](https://mlsanity.com/paper/2305.10356/) (2023)
- [Analyzing the factors that are involved in length of inpatient stay at the hospital for diabetes patients](https://mlsanity.com/paper/2406.05189/) (2024)

## Built on by (most cited first, 1 of 1)

- [Towards Robust Nonlinear Subspace Clustering: A Kernel Learning Approach](https://mlsanity.com/paper/2501.06368/) (2025)

## 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.