UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

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

Wang, J; Yu, L; Zhang, W; Gong, Y; Xu, Y; Wang, B; Zhang, P; (2017) IRGAN: A minimax game for unifying generative and discriminative information retrieval models. In: SIGIR '17 - Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. (pp. pp. 515-524). ACM: New York, NY, USA. Green open access

[thumbnail of fp078-wang-arxiv.pdf]
Preview
Text
fp078-wang-arxiv.pdf - Published Version

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 querydocument 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 fithing the underlying relevance distribution over documents given the query. On the other hand, the generative model, acting as an aftacker 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 beffer estimation for document rankin g. 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.

Type: Proceedings paper
Title: IRGAN: A minimax game for unifying generative and discriminative information retrieval models
Event: SIGIR 2017 - 40th International ACM SIGIR Conference on Research and Development in Information Retrieval
Location: Shinjuku, Tokyo, Japan
Dates: 07 August 2017 - 11 August 2017
ISBN-13: 9781450350228
Open access status: An open access version is available from UCL Discovery
DOI: 10.1145/3077136.3080786
Publisher version: http://doi.org/10.1145/3077136.3080786
Language: English
Additional information: © 2017 ACM. This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10028075
Downloads since deposit
211Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item