arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2410.03399cs.LGcs.AI
收藏

EBES:事件序列的简易基准测试

EBES: Easy Benchmarking for Event Sequences

Skolkovo Institute of Science and Technology(斯科尔科沃科学技术学院);Vega Institute Foundation(维加研究所基金会);HSE University(高等经济大学);Artificial Intelligence Research Institute(人工智能研究院)

Dmitry Osin, Igor Udovichenko, Viktor Moskvoretskii, Egor Shvetsov, Evgeny Burnaev

AI总结:

针对事件序列分类缺乏标准化基准的问题,提出EBES基准,含标准化评估协议、开源库及10个数据集,实验显示GRU模型性能最佳,旨在促进可重复研究。

摘要:

事件序列(EvS)指以不规则采样间隔以及分类和数值特征混合为特征的序列数据。对这些序列的准确分类对于各种现实应用至关重要,包括医疗保健、金融和用户交互。尽管EvS分类任务很流行,但目前没有标准化的基准或严格的评估协议。这种标准化的缺乏使得跨研究比较结果变得困难,这可能导致不可靠的结论并阻碍该领域的进展。为了解决这一空白,我们提出了EBES,一个针对具有序列级目标的事件序列分类的综合基准。EBES具有标准化的评估场景和协议,以及一个实现9种现代模型的开源PyTorch库。此外,它还包括最大的EvS数据集集合,包含10个精选数据集,包括一个新的合成数据集和具有最大公开可用银行数据集的真实世界数据。该库提供了用于集成新方法和数据集的用户友好接口。我们的基准测试结果突出了EvS与其他序列数据类型相比的独特性质,提供了现代模型的性能排名,其中基于GRU的模型取得了最佳结果,并揭示了与稳健EvS学习相关的挑战。EBES的目标是促进可重复研究,加快该领域的进展,并增加EvS分类技术对现实世界的影响。

英文摘要:

Event Sequences (EvS) refer to sequential data characterized by irregular sampling intervals and a mix of categorical and numerical features. Accurate classification of these sequences is crucial for various real-life applications, including healthcare, finance, and user interaction. Despite the popularity of the EvS classification task, there is currently no standardized benchmark or rigorous evaluation protocol. This lack of standardization makes it difficult to compare results across studies, which can result in unreliable conclusions and hinder progress in the field. To address this gap, we present EBES, a comprehensive benchmark for EvS classification with sequence-level targets. EBES features standardized evaluation scenarios and protocols, along with an open-source PyTorch library that implements 9 modern models. Additionally, it includes the largest collection of EvS datasets, featuring 10 curated datasets, including a novel synthetic dataset and real-world data with the largest publicly available banking dataset. The library offers user-friendly interfaces for integrating new methods and datasets. Our benchmarking results highlight the unique properties of EvS compared to other sequential data types, provide a performance ranking of modern models with GRU-based models achieving the best results and reveal the challenges associated with robust EvS learning. The goal of EBES is to facilitate reproducible research, expedite progress in the field, and increase the real-world impact of EvS classification techniques.

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。

↑