Wormhole: Concept-Aware Deep Representation Learning for Co-Evolving Sequences
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913511901233152 |
|---|---|
| author | Xu, Kunpeng Chen, Lifei Wang, Shengrui |
| author_facet | Xu, Kunpeng Chen, Lifei Wang, Shengrui |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_13857 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Wormhole: Concept-Aware Deep Representation Learning for Co-Evolving Sequences Xu, Kunpeng Chen, Lifei Wang, Shengrui Machine Learning Artificial Intelligence 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. |
| title | Wormhole: Concept-Aware Deep Representation Learning for Co-Evolving Sequences |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2409.13857 |