HpGAN: Sequence Search with Generative Adversarial Networks

TL;DR

HpGAN introduces a novel sequence search method using generative adversarial networks combined with Hopfield networks, effectively discovering complex sequences with desired properties for applications like wireless communications and radar systems.

Contribution

The paper presents HpGAN, a new GAN-based approach with Hopfield network encoding for sequence search, addressing limitations of traditional algebraic methods and enabling intractable problem solving.

Findings

Successfully found mutually orthogonal complementary code sets and Z-complementary pairs.

Achieved four-times SNR improvement over Legendre sequences in radar pulse compression.

Outperformed existing sequence search methods like AlphaSeq.

Abstract

Sequences play an important role in many engineering applications and systems. Searching sequences with desired properties has long been an interesting but also challenging research topic. This article proposes a novel method, called HpGAN, to search desired sequences algorithmically using generative adversarial networks (GAN). HpGAN is based on the idea of zero-sum game to train a generative model, which can generate sequences with characteristics similar to the training sequences. In HpGAN, we design the Hopfield network as an encoder to avoid the limitations of GAN in generating discrete data. Compared with traditional sequence construction by algebraic tools, HpGAN is particularly suitable for intractable problems with complex objectives which prevent mathematical analysis. We demonstrate the search capabilities of HpGAN in two applications: 1) HpGAN successfully found many different mutually orthogonal complementary code sets (MOCCS) and optimal odd-length Z-complementary pairs (OB-ZCPs) which are not part of the training set. In the literature, both MOCSSs and OB-ZCPs have found wide applications in wireless communications. 2) HpGAN found new sequences which achieve four-times increase of signal-to-interference ratio--benchmarked against the well-known Legendre sequence--of a mismatched filter (MMF) estimator in pulse compression radar systems. These sequences outperform those found by AlphaSeq.