arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.14013cs.LGcs.AI
收藏

ChronoGAN:用于时间序列生成的监督式与嵌入式生成对抗网络

ChronoGAN: Supervised and Embedded Generative Adversarial Networks for Time Series Generation

Utah State University(犹他州立大学)

MohammadReza EskandariNasab, Shah Muhammad Hamdi, Soukaina Filali Boubrahimi

AI总结:

针对时间序列生成中收敛慢、嵌入信息丢失和不稳定等挑战,提出ChronoGAN框架,结合自编码器嵌入与GANs对抗训练,利用监督网络和时序损失捕获条件分布,通过早期生成算法和改进架构提升稳定性,在多种数据集上优于现有基准。

摘要:

使用生成对抗网络(GANs)生成时间序列数据面临着几个普遍的挑战,如收敛缓慢、嵌入空间的信息丢失、不稳定性以及取决于序列长度的性能差异。为了克服这些障碍,我们引入了一个稳健的框架,旨在有效解决和缓解这些问题。该先进框架将自编码器生成的嵌入空间的优势与GANs的对抗训练动态相结合。该框架利用基于时间序列的损失函数和来自监督网络的监督,两者均能有效捕获数据的逐步条件分布。生成器在潜空间中运行,而判别器基于特征空间提供必要的反馈。此外,我们引入了早期生成算法和改进的神经网络架构,以增强稳定性并确保在短时间和长时间序列上实现有效泛化。通过联合训练,我们的框架始终优于现有基准,在具有不同特征的一系列真实和合成数据集上生成高质量的时间序列数据。

英文摘要:

Generating time series data using Generative Adversarial Networks (GANs) presents several prevalent challenges, such as slow convergence, information loss in embedding spaces, instability, and performance variability depending on the series length. To tackle these obstacles, we introduce a robust framework aimed at addressing and mitigating these issues effectively. This advanced framework integrates the benefits of an Autoencoder-generated embedding space with the adversarial training dynamics of GANs. This framework benefits from a time series-based loss function and oversight from a supervisory network, both of which capture the stepwise conditional distributions of the data effectively. The generator functions within the latent space, while the discriminator offers essential feedback based on the feature space. Moreover, we introduce an early generation algorithm and an improved neural network architecture to enhance stability and ensure effective generalization across both short and long time series. Through joint training, our framework consistently outperforms existing benchmarks, generating high-quality time series data across a range of real and synthetic datasets with diverse characteristics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑