arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.00987cs.LG
收藏

面向多元点过程的自监督对比预训练

Self-Supervised Contrastive Pre-Training for Multivariate Point Processes

RPI(伦斯勒理工学院);IBM AI Research(IBM人工智能研究院)

Xiao Shou, Dharmashankar Subramanian, Debarun Bhattacharjya, Tian Gao, Kristin P. Bennet

AI总结:

针对多元点过程自监督研究空白,提出基于Transformer编码器、结合掩码(含空时刻插入)与对比模块的自监督预训练范式,可微调适配下游任务,在下一事件预测任务上最高提升20%性能。

摘要:

自监督是当前日益流行的基础模型(包括BERT、GPT-3等大语言模型)系列中表示学习的标志性特征之一,但据我们所知,尚未有人在多元事件流场景下开展相关研究。我们提出了一种基于Transformer编码器的多元点过程自监督学习新范式。具体而言,我们为编码器设计了一种新颖的预训练策略:不仅对随机事件时刻进行掩码,还插入随机采样的无事件发生的“空”时刻;这与BERT中词掩码这类典型的离散时间前置任务不同,而是拓展了掩码的有效性,以更好地捕捉连续时间动态。为提升下游任务性能,我们引入了一个对比模块,用于将真实事件与模拟的空样本进行对比。预训练后的模型随后可在规模可能小得多的事件数据集上进行微调,这在概念上与流行预训练语言模型的典型迁移方式类似。我们在合成数据集和3个真实应用的下一事件预测任务上验证了所提范式的有效性,观察到与现有最优模型相比,性能相对提升最高可达20%。

英文摘要:

Self-supervision is one of the hallmarks of representation learning in the increasingly popular suite of foundation models including large language models such as BERT and GPT-3, but it has not been pursued in the context of multivariate event streams, to the best of our knowledge. We introduce a new paradigm for self-supervised learning for multivariate point processes using a transformer encoder. Specifically, we design a novel pre-training strategy for the encoder where we not only mask random event epochs but also insert randomly sampled "void" epochs where an event does not occur; this differs from the typical discrete-time pretext tasks such as word-masking in BERT but expands the effectiveness of masking to better capture continuous-time dynamics. To improve downstream tasks, we introduce a contrasting module that compares real events to simulated void instances. The pre-trained model can subsequently be fine-tuned on a potentially much smaller event dataset, similar conceptually to the typical transfer of popular pre-trained language models. We demonstrate the effectiveness of our proposed paradigm on the next-event prediction task using synthetic datasets and 3 real applications, observing a relative performance boost of as high as up to 20% compared to state-of-the-art models.

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。

↑