Learning to Generate Time Series Conditioned Graphs with Generative Adversarial Nets
This addresses a novel problem in graph generation for domains like bioinformatics, enabling conditioned graph inference from node-level time series, though it appears incremental as it builds on existing GAN frameworks.
The paper tackles the problem of generating relation graphs from multivariate time series, proposing TSGG-GAN to infer interrelationships between nodes based on time series data, with experiments on synthetic and real-world gene regulatory networks showing effectiveness and generalizability.
Deep learning based approaches have been utilized to model and generate graphs subjected to different distributions recently. However, they are typically unsupervised learning based and unconditioned generative models or simply conditioned on the graph-level contexts, which are not associated with rich semantic node-level contexts. Differently, in this paper, we are interested in a novel problem named Time Series Conditioned Graph Generation: given an input multivariate time series, we aim to infer a target relation graph modeling the underlying interrelationships between time series with each node corresponding to each time series. For example, we can study the interrelationships between genes in a gene regulatory network of a certain disease conditioned on their gene expression data recorded as time series. To achieve this, we propose a novel Time Series conditioned Graph Generation-Generative Adversarial Networks (TSGG-GAN) to handle challenges of rich node-level context structures conditioning and measuring similarities directly between graphs and time series. Extensive experiments on synthetic and real-word gene regulatory networks datasets demonstrate the effectiveness and generalizability of the proposed TSGG-GAN.