BIROn - Birkbeck Institutional Research Online

    IRGAN: a minimax game for unifying generative and discriminative information retrieval models

    Wang, Jun and Yu, Lantao and Zhang, Weinan and Gong, Yu and Xu, Yinghui and Wang, Benyou and Zhang, Peng and Zhang, Dell (2017) IRGAN: a minimax game for unifying generative and discriminative information retrieval models. In: UNSPECIFIED (ed.) Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, U.S.: ACM, pp. 515-524. ISBN 9781450350228.

    [img]
    Preview
    Text
    18782.pdf - Author's Accepted Manuscript

    Download (1MB) | Preview

    Abstract

    This paper provides a unified account of two schools of thinking in information retrieval modelling: the generative retrieval focusing on predicting relevant documents given a query, and the discriminative retrieval focusing on predicting relevancy given a query-document pair. We propose a game theoretical minimax game to iteratively optimise both models. On one hand, the discriminative model, aiming to mine signals from labelled and unlabelled data, provides guidance to train the generative model towards fitting the underlying relevance distribution over documents given the query. On the other hand, the generative model, acting as an attacker to the current discriminative model, generates difficult examples for the discriminative model in an adversarial way by minimising its discrimination objective. With the competition between these two models, we show that the unified framework takes advantage of both schools of thinking: (i) the generative model learns to fit the relevance distribution over documents via the signals from the discriminative model, and (ii) the discriminative model is able to exploit the unlabelled data selected by the generative model to achieve a better estimation for document ranking. Our experimental results have demonstrated significant performance gains as much as 23.96% on Precision@5 and 15.50% on MAP over strong baselines in a variety of applications including web search, item recommendation, and question answering.

    Metadata

    Item Type: Book Section
    Keyword(s) / Subject(s): Information Retrieval, Generative Adversarial Networks
    School: Birkbeck Schools and Departments > School of Business, Economics & Informatics > Computer Science and Information Systems
    Research Centre: Birkbeck Knowledge Lab
    Depositing User: Dr Dell Zhang
    Date Deposited: 27 Sep 2017 10:20
    Last Modified: 27 Sep 2017 10:20
    URI: http://eprints.bbk.ac.uk/id/eprint/18782

    Statistics

    Downloads
    Activity Overview
    351Downloads
    91Hits

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item