Directed Chain Generative Adversarial Networks

TL;DR

This paper introduces directed chain GANs (DC-GANs), a novel generative model capable of producing multimodal time series data by incorporating neighborhood processes into stochastic differential equations, outperforming existing methods.

Contribution

The paper presents the first generative adversarial network designed specifically for multimodal time series data using directed chain SDEs with distributional constraints.

Findings

DC-GANs successfully generate multimodal time series data.

DC-GANs outperform state-of-the-art benchmarks in distribution and similarity measures.

Effective on diverse datasets including social sciences, neuroscience, stock prices, and energy consumption.

Abstract

Real-world data can be multimodal distributed, e.g., data describing the opinion divergence in a community, the interspike interval distribution of neurons, and the oscillators natural frequencies. Generating multimodal distributed real-world data has become a challenge to existing generative adversarial networks (GANs). For example, neural stochastic differential equations (Neural SDEs), treated as infinite-dimensional GANs, have demonstrated successful performance mainly in generating unimodal time series data. In this paper, we propose a novel time series generator, named directed chain GANs (DC-GANs), which inserts a time series dataset (called a neighborhood process of the directed chain or input) into the drift and diffusion coefficients of the directed chain SDEs with distributional constraints. DC-GANs can generate new time series of the same distribution as the neighborhood process, and the neighborhood process will provide the key step in learning and generating multimodal distributed time series. The proposed DC-GANs are examined on four datasets, including two stochastic models from social sciences and computational neuroscience, and two real-world datasets on stock prices and energy consumption. To our best knowledge, DC-GANs are the first work that can generate multimodal time series data and consistently outperforms state-of-the-art benchmarks with respect to measures of distribution, data similarity, and predictive ability.