IVP-VAE: Modeling EHR Time Series with Initial Value Problem Solvers
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916122832404480 |
|---|---|
| author | Xiao, Jingge Basso, Leonie Nejdl, Wolfgang Ganguly, Niloy Sikdar, Sandipan |
| author_facet | Xiao, Jingge Basso, Leonie Nejdl, Wolfgang Ganguly, Niloy Sikdar, Sandipan |
| contents | Continuous-time models such as Neural ODEs and Neural Flows have shown promising results in analyzing irregularly sampled time series frequently encountered in electronic health records. Based on these models, time series are typically processed with a hybrid of an initial value problem (IVP) solver and a recurrent neural network within the variational autoencoder architecture. Sequentially solving IVPs makes such models computationally less efficient. In this paper, we propose to model time series purely with continuous processes whose state evolution can be approximated directly by IVPs. This eliminates the need for recurrent computation and enables multiple states to evolve in parallel. We further fuse the encoder and decoder with one IVP solver utilizing its invertibility, which leads to fewer parameters and faster convergence. Experiments on three real-world datasets show that the proposed method can systematically outperform its predecessors, achieve state-of-the-art results, and have significant advantages in terms of data efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_06741 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | IVP-VAE: Modeling EHR Time Series with Initial Value Problem Solvers Xiao, Jingge Basso, Leonie Nejdl, Wolfgang Ganguly, Niloy Sikdar, Sandipan Machine Learning Artificial Intelligence Continuous-time models such as Neural ODEs and Neural Flows have shown promising results in analyzing irregularly sampled time series frequently encountered in electronic health records. Based on these models, time series are typically processed with a hybrid of an initial value problem (IVP) solver and a recurrent neural network within the variational autoencoder architecture. Sequentially solving IVPs makes such models computationally less efficient. In this paper, we propose to model time series purely with continuous processes whose state evolution can be approximated directly by IVPs. This eliminates the need for recurrent computation and enables multiple states to evolve in parallel. We further fuse the encoder and decoder with one IVP solver utilizing its invertibility, which leads to fewer parameters and faster convergence. Experiments on three real-world datasets show that the proposed method can systematically outperform its predecessors, achieve state-of-the-art results, and have significant advantages in terms of data efficiency. |
| title | IVP-VAE: Modeling EHR Time Series with Initial Value Problem Solvers |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2305.06741 |