Guardado en:
Detalles Bibliográficos
Autores principales: Shou, Xiao, Subramanian, Dharmashankar, Bhattacharjya, Debarun, Gao, Tian, Bennet, Kristin P.
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2402.00987
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913220776689664
author Shou, Xiao
Subramanian, Dharmashankar
Bhattacharjya, Debarun
Gao, Tian
Bennet, Kristin P.
author_facet Shou, Xiao
Subramanian, Dharmashankar
Bhattacharjya, Debarun
Gao, Tian
Bennet, Kristin P.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_00987
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Self-Supervised Contrastive Pre-Training for Multivariate Point Processes
Shou, Xiao
Subramanian, Dharmashankar
Bhattacharjya, Debarun
Gao, Tian
Bennet, Kristin P.
Machine Learning
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.
title Self-Supervised Contrastive Pre-Training for Multivariate Point Processes
topic Machine Learning
url https://arxiv.org/abs/2402.00987