On the Predictive Accuracy of Neural Temporal Point Process Models for Continuous-time Event Data

• URL: http://arxiv.org/abs/2306.17066v2
• Date: Mon, 10 Jul 2023 15:44:47 GMT
• Title: On the Predictive Accuracy of Neural Temporal Point Process Models for Continuous-time Event Data
• Authors: Tanguy Bosser and Souhaib Ben Taieb
• Abstract summary: Temporal Point Processes (TPPs) serve as the standard mathematical framework for modeling asynchronous event sequences in continuous time. Researchers have proposed Neural TPPs, which leverage neural network parametrizations to offer more flexible and efficient modeling. This study systematically evaluates the predictive accuracy of state-of-the-art neural TPP models.
• Score: 3.13468877208035
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Temporal Point Processes (TPPs) serve as the standard mathematical framework for modeling asynchronous event sequences in continuous time. However, classical TPP models are often constrained by strong assumptions, limiting their ability to capture complex real-world event dynamics. To overcome this limitation, researchers have proposed Neural TPPs, which leverage neural network parametrizations to offer more flexible and efficient modeling. While recent studies demonstrate the effectiveness of Neural TPPs, they often lack a unified setup, relying on different baselines, datasets, and experimental configurations. This makes it challenging to identify the key factors driving improvements in predictive accuracy, hindering research progress. To bridge this gap, we present a comprehensive large-scale experimental study that systematically evaluates the predictive accuracy of state-of-the-art neural TPP models. Our study encompasses multiple real-world and synthetic event sequence datasets, following a carefully designed unified setup. We thoroughly investigate the influence of major architectural components such as event encoding, history encoder, and decoder parametrization on both time and mark prediction tasks. Additionally, we delve into the less explored area of probabilistic calibration for neural TPP models. By analyzing our results, we draw insightful conclusions regarding the significance of history size and the impact of architectural components on predictive accuracy. Furthermore, we shed light on the miscalibration of mark distributions in neural TPP models. Our study aims to provide valuable insights into the performance and characteristics of neural TPP models, contributing to a better understanding of their strengths and limitations.

Related papers

• CogDPM: Diffusion Probabilistic Models via Cognitive Predictive Coding [62.075029712357]
  This work introduces the Cognitive Diffusion Probabilistic Models (CogDPM) CogDPM features a precision estimation method based on the hierarchical sampling capabilities of diffusion models and weight the guidance with precision weights estimated by the inherent property of diffusion models. We apply CogDPM to real-world prediction tasks using the United Kindom precipitation and surface wind datasets.
  arXiv  Detail & Related papers  (2024-05-03T15:54:50Z)
• Cumulative Distribution Function based General Temporal Point Processes [49.758080415846884]
  CuFun model represents a novel approach to TPPs that revolves around the Cumulative Distribution Function (CDF) Our approach addresses several critical issues inherent in traditional TPP modeling. Our contributions encompass the introduction of a pioneering CDF-based TPP model, the development of a methodology for incorporating past event information into future event prediction.
  arXiv  Detail & Related papers  (2024-02-01T07:21:30Z)
• Spatio-Temporal Attention Graph Neural Network for Remaining Useful Life Prediction [1.831835396047386]
  This study presents the Spatio-Temporal Attention Graph Neural Network. Our model combines graph neural networks and temporal convolutional neural networks for spatial and temporal feature extraction. Comprehensive experiments were conducted on the C-MAPSS dataset to evaluate the impact of unified versus clustering normalization.
  arXiv  Detail & Related papers  (2024-01-29T08:49:53Z)
• A PAC-Bayesian Perspective on the Interpolating Information Criterion [54.548058449535155]
  We show how a PAC-Bayes bound is obtained for a general class of models, characterizing factors which influence performance in the interpolating regime. We quantify how the test error for overparameterized models achieving effectively zero training error depends on the quality of the implicit regularization imposed by e.g. the combination of model, parameter-initialization scheme.
  arXiv  Detail & Related papers  (2023-11-13T01:48:08Z)
• Modeling Time-Series and Spatial Data for Recommendations and Other Applications [1.713291434132985]
  We address the problems that may arise due to the poor quality of CTES data being fed into a recommender system. To improve the quality of the CTES data, we address a fundamental problem of overcoming missing events in temporal sequences. We extend their abilities to design solutions for large-scale CTES retrieval and human activity prediction.
  arXiv  Detail & Related papers  (2022-12-25T09:34:15Z)
• Exploring Generative Neural Temporal Point Process [37.1875644118684]
  generative models such as denoising diffusion and score matching models have achieved great progress in image generating tasks. We try to fill the gap by designing a unified textbfgenerative framework for textbfneural textbftemporal textbfpoint textbfprocess.
  arXiv  Detail & Related papers  (2022-08-03T06:56:28Z)
• Integration of neural network and fuzzy logic decision making compared with bilayered neural network in the simulation of daily dew point temperature [0.8808021343665321]
  dew point temperature (DPT) is simulated using the data-driven approach. Various input patterns, namely T min, T max, and T mean, are utilized for training the architecture.
  arXiv  Detail & Related papers  (2022-02-23T14:25:13Z)
• Mixed Effects Neural ODE: A Variational Approximation for Analyzing the Dynamics of Panel Data [50.23363975709122]
  We propose a probabilistic model called ME-NODE to incorporate (fixed + random) mixed effects for analyzing panel data. We show that our model can be derived using smooth approximations of SDEs provided by the Wong-Zakai theorem. We then derive Evidence Based Lower Bounds for ME-NODE, and develop (efficient) training algorithms.
  arXiv  Detail & Related papers  (2022-02-18T22:41:51Z)
• Leveraging the structure of dynamical systems for data-driven modeling [111.45324708884813]
  We consider the impact of the training set and its structure on the quality of the long-term prediction. We show how an informed design of the training set, based on invariants of the system and the structure of the underlying attractor, significantly improves the resulting models.
  arXiv  Detail & Related papers  (2021-12-15T20:09:20Z)
• Pre-Trained Models: Past, Present and Future [126.21572378910746]
  Large-scale pre-trained models (PTMs) have recently achieved great success and become a milestone in the field of artificial intelligence (AI) By storing knowledge into huge parameters and fine-tuning on specific tasks, the rich knowledge implicitly encoded in huge parameters can benefit a variety of downstream tasks. It is now the consensus of the AI community to adopt PTMs as backbone for downstream tasks rather than learning models from scratch.
  arXiv  Detail & Related papers  (2021-06-14T02:40:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.