Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/152799
Title: Mitigating performance saturation in neural marked point processes : architectures and loss functions
Authors: Li, Tianbo
Luo, Tianze
Ke, Yiping
Pan, Sinno Jialin
Keywords: Engineering::Computer science and engineering
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Issue Date: 2021
Source: Li, T., Luo, T., Ke, Y. & Pan, S. J. (2021). Mitigating performance saturation in neural marked point processes : architectures and loss functions. 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining (KDD '21), 986-994. https://dx.doi.org/10.1145/3447548.3467436
Project: SDSC-2020-004
M4081532.020
2018-T1-002-143 (RG131/18 (S)
Abstract: Attributed event sequences are commonly encountered in practice. A recent research line focuses on incorporating neural networks with the statistical model -- marked point processes, which is the conventional tool for dealing with attributed event sequences. Neural marked point processes possess good interpretability of probabilistic models as well as the representational power of neural networks. However, we find that performance of neural marked point processes is not always increasing as the network architecture becomes more complicated and larger, which is what we call the performance saturation phenomenon. This is due to the fact that the generalization error of neural marked point processes is determined by both the network representational ability and the model specification at the same time. Therefore we can draw two major conclusions: first, simple network structures can perform no worse than complicated ones for some cases; second, using a proper probabilistic assumption is as equally, if not more, important as improving the complexity of the network. Based on this observation, we propose a simple graph-based network structure called GCHP, which utilizes only graph convolutional layers, thus it can be easily accelerated by the parallel mechanism. We directly consider the distribution of interarrival times instead of imposing a specific assumption on the conditional intensity function, and propose to use a likelihood ratio loss with a moment matching mechanism for optimization and model selection. Experimental results show that GCHP can significantly reduce training time and the likelihood ratio loss with interarrival time probability assumptions can greatly improve the model performance.
URI: https://hdl.handle.net/10356/152799
ISBN: 9781450383325
DOI: 10.1145/3447548.3467436
Rights: © 2021 Copyright held by the owner/author(s). Publication rights licensed to ACM. All rgihts reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:SCSE Conference Papers

Page view(s)

53
Updated on Jan 21, 2022

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.