Generative Adversarial Nets for Information Retrieval: Fundamentals and Advances

TL;DR

This paper reviews the fundamentals and recent advances of Generative Adversarial Networks (GANs) applied to various information retrieval tasks, focusing on discrete data generation, IRGAN framework, and graph data fitting.

Contribution

It provides a comprehensive overview of GAN techniques tailored for discrete data in information retrieval, including IRGAN and recent developments in text and graph data applications.

Findings

Introduces the fundamentals and theoretical properties of GANs.

Discusses solutions for extending GANs to discrete data generation.

Highlights recent work on GANs for graph/network data fitting.

Abstract

Generative adversarial nets (GANs) have been widely studied during the recent development of deep learning and unsupervised learning. With an adversarial training mechanism, GAN manages to train a generative model to fit the underlying unknown real data distribution under the guidance of the discriminative model estimating whether a data instance is real or generated. Such a framework is originally proposed for fitting continuous data distribution such as images, thus it is not straightforward to be directly applied to information retrieval scenarios where the data is mostly discrete, such as IDs, text and graphs. In this tutorial, we focus on discussing the GAN techniques and the variants on discrete data fitting in various information retrieval scenarios. (i) We introduce the fundamentals of GAN framework and its theoretic properties; (ii) we carefully study the promising solutions to extend GAN onto discrete data generation; (iii) we introduce IRGAN, the fundamental GAN framework of fitting single ID data distribution and the direct application on information retrieval; (iv) we further discuss the task of sequential discrete data generation tasks, e.g., text generation, and the corresponding GAN solutions; (v) we present the most recent work on graph/network data fitting with node embedding techniques by GANs. Meanwhile, we also introduce the relevant open-source platforms such as IRGAN and Texygen to help audience conduct research experiments on GANs in information retrieval. Finally, we conclude this tutorial with a comprehensive summarization and a prospect of further research directions for GANs in information retrieval.