Cross-modal Recurrent Models for Weight Objective Prediction from Multimodal Time-series Data
Abstract
We analyse multimodal time-series data corresponding to weight, sleep and steps measurements. We focus on predicting whether a user will successfully achieve his/her weight objective. For this, we design several deep long short-term memory (LSTM) architectures, including a novel cross-modal LSTM (X-LSTM), and demonstrate their superiority over baseline approaches. The X-LSTM improves parameter efficiency by processing each modality separately and allowing for information flow between them by way of recurrent cross-connections. We present a general hyperparameter optimisation technique for X-LSTMs, which allows us to significantly improve on the LSTM and a prior state-of-the-art cross-modal approach, using a comparable number of parameters. Finally, we visualise the model's predictions, revealing implications about latent variables in this task.
Cite
@article{arxiv.1709.08073,
title = {Cross-modal Recurrent Models for Weight Objective Prediction from Multimodal Time-series Data},
author = {Petar Veličković and Laurynas Karazija and Nicholas D. Lane and Sourav Bhattacharya and Edgar Liberis and Pietro Liò and Angela Chieh and Otmane Bellahsen and Matthieu Vegreville},
journal= {arXiv preprint arXiv:1709.08073},
year = {2018}
}
Comments
To appear in NIPS ML4H 2017 and NIPS TSW 2017