CaltechAUTHORS
  A Caltech Library Service

Multi-View, Generative, Transfer Learning for Distributed Time Series Classification

Das Bhattacharjee, Sreyasee and Tolone, William J. and Mahabal, Ashish and Elshambakey, Mohammed and Cho, Isaac and Nayeem, Abdullah al-Raihan and Yuan, Junsong and Djorgovski, George (2019) Multi-View, Generative, Transfer Learning for Distributed Time Series Classification. In: 2019 IEEE International Conference on Big Data (Big Data). IEEE , Piscataway, NJ, pp. 5585-5594. ISBN 9781728108582. https://resolver.caltech.edu/CaltechAUTHORS:20200302-105109375

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20200302-105109375

Abstract

In this paper, we propose an effective, multi-view, generative, transfer learning framework for multivariate timeseries data. While generative models are demonstrated effective for several machine learning tasks, their application to time-series classification problems is underexplored. The need for additional exploration is motivated when data are large, annotations are unbalanced or scarce, or data are distributed and fragmented. Recent advances in computer vision attempt to use synthesized samples with system generated annotations to overcome the lack or imbalance of annotated data. However, in multi-view problem settings, view mismatches between the synthetic data and real data pose additional challenges against harnessing new annotated data collections. The proposed method offers important contributions to facilitate knowledge sharing, while simultaneously ensuring an effective solution for domain-specific, finelevel categorizations. We propose a principled way to perform view adaptation in a cross-view learning environment, wherein pairwise view similarity is identified by a smaller subset of source samples that closely resemble the target data patterns. This approach integrates generative models within a deep classification framework to minimize the gap between source and target data. More precisely, we design category specific conditional, generative models to update the source generator in order for transforming source features so that they appear as target features and simultaneously tune the associated discriminative model to distinguish these features. During each learning iteration, the source generator is conditioned by a source training set represented as some target-like features. This transformation in appearance was performed via a target generator specifically learned for targetspecific customization per category. Afterward, a smaller source training set, indicating close target pattern resemblance in terms of the corresponding generative and discriminative loss, is used to fine-tune the source classification model parameters. Experiments show that compared to existing approaches, our proposed multiview, generative, transfer learning framework improves timeseries classification performance by around 4% in the UCI multiview activity recognition dataset, while also showing a robust, generalized representation capacity in classifying several largescale multi-view light curve collections.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1109/bigdata47090.2019.9005452DOIArticle
ORCID:
AuthorORCID
Mahabal, Ashish0000-0003-2242-0244
Djorgovski, George0000-0002-0603-3087
Additional Information:© 2019 IEEE. Funding for this research was provided by the National Science Foundations (NSF) Data Infrastructure Building Blocks (DIBBs) Progam under award #1640818.
Funders:
Funding AgencyGrant Number
NSFOAC-1640818
Subject Keywords:Generative Model, GAN, LSTM, RNN, Multiview Classification, Transfer Learning, Distributed Time-Series Analysis, Deep Learning
Record Number:CaltechAUTHORS:20200302-105109375
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20200302-105109375
Official Citation:S. D. Bhattacharjee et al., "Multi-View, Generative, Transfer Learning for Distributed Time Series Classification," 2019 IEEE International Conference on Big Data (Big Data), Los Angeles, CA, USA, 2019, pp. 5585-5594. doi: 10.1109/BigData47090.2019.9005452
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:101648
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:02 Mar 2020 20:28
Last Modified:02 Mar 2020 20:28

Repository Staff Only: item control page