Multi-stream based marked point process

Sujun Hong, Hirotaka Hachiya
Proceedings of The 13th Asian Conference on Machine Learning, PMLR 157:1269-1284, 2021.

Abstract

When using a point process, a specific form of the model needs to be designed for intensity function, based on physical and mathematical prior knowledge about the data. Recently, a fully trainable deep learning-based approach has been developed for temporal point processes. This approach models a cumulative hazard function (CHF), which is capable of systematic computation of adaptive intensity function in a data-driven manner. However, this approach does not take the attribute information of events into account although many applications of point processes generate with a variety of marked information such as location, magnitude, and depth of seismic activity. To overcome this limitation, we propose a fully trainable marked point process method, modeling decomposed CHFs for time and mark using multi-stream deep neural networks. In addition, we also propose to encode multiple marked information into a single image and extract necessary information adaptively without detailed knowledge about the data. We show the effectiveness of our proposed method through experiments with simulated toy data and real seismic data.

Cite this Paper


BibTeX
@InProceedings{pmlr-v157-hong21a, title = {Multi-stream based marked point process}, author = {Hong, Sujun and Hachiya, Hirotaka}, booktitle = {Proceedings of The 13th Asian Conference on Machine Learning}, pages = {1269--1284}, year = {2021}, editor = {Balasubramanian, Vineeth N. and Tsang, Ivor}, volume = {157}, series = {Proceedings of Machine Learning Research}, month = {17--19 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v157/hong21a/hong21a.pdf}, url = {https://proceedings.mlr.press/v157/hong21a.html}, abstract = {When using a point process, a specific form of the model needs to be designed for intensity function, based on physical and mathematical prior knowledge about the data. Recently, a fully trainable deep learning-based approach has been developed for temporal point processes. This approach models a cumulative hazard function (CHF), which is capable of systematic computation of adaptive intensity function in a data-driven manner. However, this approach does not take the attribute information of events into account although many applications of point processes generate with a variety of marked information such as location, magnitude, and depth of seismic activity. To overcome this limitation, we propose a fully trainable marked point process method, modeling decomposed CHFs for time and mark using multi-stream deep neural networks. In addition, we also propose to encode multiple marked information into a single image and extract necessary information adaptively without detailed knowledge about the data. We show the effectiveness of our proposed method through experiments with simulated toy data and real seismic data.} }
Endnote
%0 Conference Paper %T Multi-stream based marked point process %A Sujun Hong %A Hirotaka Hachiya %B Proceedings of The 13th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Vineeth N. Balasubramanian %E Ivor Tsang %F pmlr-v157-hong21a %I PMLR %P 1269--1284 %U https://proceedings.mlr.press/v157/hong21a.html %V 157 %X When using a point process, a specific form of the model needs to be designed for intensity function, based on physical and mathematical prior knowledge about the data. Recently, a fully trainable deep learning-based approach has been developed for temporal point processes. This approach models a cumulative hazard function (CHF), which is capable of systematic computation of adaptive intensity function in a data-driven manner. However, this approach does not take the attribute information of events into account although many applications of point processes generate with a variety of marked information such as location, magnitude, and depth of seismic activity. To overcome this limitation, we propose a fully trainable marked point process method, modeling decomposed CHFs for time and mark using multi-stream deep neural networks. In addition, we also propose to encode multiple marked information into a single image and extract necessary information adaptively without detailed knowledge about the data. We show the effectiveness of our proposed method through experiments with simulated toy data and real seismic data.
APA
Hong, S. & Hachiya, H.. (2021). Multi-stream based marked point process. Proceedings of The 13th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 157:1269-1284 Available from https://proceedings.mlr.press/v157/hong21a.html.

Related Material