Awesome-Temporal-Point-Process

A temporal point process is a model that simultaneously predict item and time in tasks like recommendation system.

Papers

• Fast and Flexible Temporal Point Processes with Triangular Maps(NeurIPS 2020) [Code]
• Intensity-Free Learning of Temporal Point Processes(ICLR 2020) [Code]
• Fully Neural Network based Model for General Temporal Point Processes(NeurIPS 2019) [Code]
• Neural Jump Stochastic Differential Equations(NeurIPS 2019) [Code]
• Deep Reinforcement Learning of Marked Temporal Point Processes(NeurIPS 2018) [Code]
• Learning temporal point processes via reinforcement learning(NeurIPS 2018) [Code]
• Improving Maximum Likelihood Estimation of Temporal Point Process via Discriminative and Adversarial Learning(IJCAI 2018)
• JUMP: A Joint Predictor for User Click and Dwell Time(IJCAI 2018)
• Learning Conditional Generative Models for Temporal Point Processes(AAAI 2018)
• The Neural Hawkes Process(NeurIPS 2017) [Code]
• Wasserstein Learning of Deep Generative Point Process Models(NeurIPS 2017) [Code]
• Cascade Dynamics Modeling with Attention-based Recurrent Neural Network(IJCAI 2017)
• Modeling the intensity function of point process via recurrent neural networks. (AAAI 2017) [Unofficial Pytorch]
• Recurrent Marked Temporal Point Processes: Embedding Event History to Vector(DDK 2016) [Code] [Unofficial Tensorflow] [Unofficial Pytorch]

Survey

• Recent Advance in Temporal Point Process: from Machine Learning Perspective (2019)

Framework

• A general framework for learning spatio-temporal point processes via reinforcement learning. [Code]

Utils

• A Spatio-temporal point process simulator. [Code]
• PtPack: The C++ Multivariate Temporal Point Process Package. [Code]
• PoPPy: A Point Process Toolbox Based on PyTorch. [Code]

Dataset

Others

• MIT lecture [Url]
• PaperWithCode-point-processes [Url]