DeepAI AI Chat
Log In Sign Up

Proximal Policy Optimization for Improved Convergence in IRGAN

by   Moksh Jain, et al.

IRGAN is an information retrieval (IR) modeling approach that uses a theoretical minimax game between a generative and a discriminative model to iteratively optimize both of them, hence unifying the generative and discriminative approaches. Despite significant performance improvements in several information retrieval tasks, IRGAN training is an unstable process, and the solution varies largely with the random parameter initialization. In this work, we present an improved training objective based on proximal policy optimization objective and Gumbel-Softmax based sampling for the generator. We also propose a modified training algorithm which takes a single gradient update on both the generator as well as discriminator for each iteration step. We present empirical evidence of the improved convergence of the proposed model over the original IRGAN and a comparison on three different IR tasks on benchmark datasets is also discussed, emphasizing the proposed model's superior performance.


page 1

page 2

page 3

page 4


Evaluating a Generative Adversarial Framework for Information Retrieval

Recent advances in Generative Adversarial Networks (GANs) have resulted ...

Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering

Multi-hop question answering (QA) requires an information retrieval (IR)...

Relevance Judgment Convergence Degree – A Measure of Inconsistency among Assessors for Information Retrieval

Relevance judgment of human assessors is inherently subjective and dynam...

Multi-stage Information Retrieval for Vietnamese Legal Texts

This study deals with the problem of information retrieval (IR) for Viet...

A Survey of Quantum Theory Inspired Approaches to Information Retrieval

Since 2004, researchers have been using the mathematical framework of Qu...

Prototype-to-Style: Dialogue Generation with Style-Aware Editing on Retrieval Memory

The ability of a dialog system to express prespecified language style du...