Unified Multi-Domain Learning and Data Imputation using Adversarial Autoencoder

Andre Mendes, Julian Togelius, Leandro Dos Santos Coelho

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    We present a novel framework that can combine multi-domain learning (MDL), data imputation (DI) and multi-task learning (MTL) to improve performance for classification and regression tasks in different domains. The core of our method is an adversarial autoencoder that can: (1) learn to produce domain-invariant embeddings to reduce the difference between domains; (2) learn the data distribution for each domain and correctly perform data imputation on missing data. For MDL, we use the Maximum Mean Discrepancy (MMD) measure to align the domain distributions. For DI, we use an adversarial approach where a generator fill in information for missing data and a discriminator tries to distinguish between real and imputed values. Finally, using the universal feature representation in the embeddings, we train a classifier using MTL that given input from any domain, can predict labels for all domains. We demonstrate the superior performance of our approach compared to other state-of-art methods in three distinct settings, DG-DI in image recognition with unstructured data, MTL-DI in grade estimation with structured data and MDMTL-DI in a selection process using mixed data.

    Original languageEnglish (US)
    Title of host publication2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    ISBN (Electronic)9781728169262
    DOIs
    StatePublished - Jul 2020
    Event2020 International Joint Conference on Neural Networks, IJCNN 2020 - Virtual, Glasgow, United Kingdom
    Duration: Jul 19 2020Jul 24 2020

    Publication series

    NameProceedings of the International Joint Conference on Neural Networks

    Conference

    Conference2020 International Joint Conference on Neural Networks, IJCNN 2020
    CountryUnited Kingdom
    CityVirtual, Glasgow
    Period7/19/207/24/20

    Keywords

    • data imputation
    • multi-domain
    • multi-task

    ASJC Scopus subject areas

    • Software
    • Artificial Intelligence

    Fingerprint Dive into the research topics of 'Unified Multi-Domain Learning and Data Imputation using Adversarial Autoencoder'. Together they form a unique fingerprint.

    Cite this