Learning with Temporal Point Processes

In this workshop, we take a broad perspective in learning with temporal point process and address a wide range of challenges including but not limited to

• Mathematical modeling of real life phenomena using temporal point process
• Machine learning methods for inference of temporal point process.
• Control of temporal point process
• Reinforcement learning of temporal point process
• Causal learning of temporal point process
• Inference of temporal point process with intermittent observations
• Emerging applications of temporal point process e.g. epidemic modeling, deep generative models, etc.

In recent years, there has been an increasing number of machine learning models, inference methods and control algorithms using temporal point processes. They have been particularly popular for understanding, predicting, and enhancing the functioning of social and information systems, where they have achieved unprecedented performance. This workshop aims to introduce temporal point processes to the machine learning community at large. In this workshop, we aim to popularize temporal point processes within the machine learning community at large. It will bring together experts from a diverse, multi-disciplinary set of backgrounds. One of the main goals of this workshop is to help the community understand the role of temporal point process on the development of human-centered machine learning models and algorithms accounting for the feedback loop between algorithmic and human decisions, which are inherently asynchronous events.

We take a broad perspective to learning with temporal point process and address a wide range of themes including, but not limited to predictive models, efficient inference methods, deep learning, control and reinforcement learning, generative models, causal learning, incomplete and missing data We also encourage the submission of emerging real-world applications of TPPs.

Important dates:

• Submission deadline: September 15, 23:59 AOE
• Author notification: September 30

Submissions in the form of extended abstracts must be at most 4 pages long (not including references and an unlimited number of pages for supplemental material, which reviewers are not required to take into account) and adhere to the NeurIPS format. We accept submissions of work recently published or currently under review. Submissions should be anonymized as described in the submission instructions and should be submitted through:

The workshop will not have formal proceedings, but authors of accepted abstracts can choose to have either a link to an arxiv version of their paper or a pdf published on the workshop webpage.

Link to the papers would be updated shortly.

• Mixtures of Heterogeneous Poisson Processes for the Assessment of e-Social Activity in Mental Health-- Pablo Bonilla-Escribano, David Ramírez and Antonio Artés-Rodríguez
• Fused Gromov-Wasserstein Alignment for Hawkes Processes-- Dixin Luo, Hongteng Xu and Lawrence Carin
• The Graph Hawkes Network for Reasoning on Temporal Knowledge Graphs-- Zhen Han, Jindong Jiang, Yuyi Wang, Yunpu Ma and Volker Tresp
• Insider Threat Detection via Hierarchical Neural Temporal Point Processes-- Shuhan Yuan, Panpan Zheng, Xintao Wu and Qinghua Li
• A sleep-wake detection algorithm for memory-constrained wearable devices: Change Point Decoder-- Ayse Cakmak, Giulia Da Poian, Adam Willats, Amit Shah, Viola Vaccarino, Donald Bliwise, Christopher Rozell and Gari Clifford
• Learning to Crawl-- Utkarsh Upadhyay, Robert Busa-Fekete, Wojciech Kotlowski, David Pal and Balazs Szorenyi
• Deep Point Process Destructors-- David Inouye
• Topics are not Marks: Modeling Text-based Cascades using Multi-network Hawkes Process-- Jayesh Choudhari, Anirban Dasgupta, Indrajit Bhattacharya and Srikanta Bedathur
• Intermittent Demand Forecasting with Deep Renewal Processes-- Ali Caner Türkmen, Yuyang Wang and Tim Januschowski
• Temporal Logic Point Processes-- Shuang Li, Lu Wang, Ruizhi Zhang, Nan Du and Le Song
• Mutually-Exciting Temporal Point Process Methods to Model Clinical Event Dynamics-- Thomas Taylor
• Meta Learning with Relational Information for Short Sequences-- Yujia Xie, Haoming Jiang, Feng Liu, Tuo Zhao and Hongyuan Zha
• Stance Classification using Discriminative Modeling of Text in Hawkes Process-- Rohan Tondulkar, Srijith P. K. and Michal Lukasik
• Point Process Flows-- Nazanin Mehrasa, Ruizhi Deng, Jiawei He, Bo Chang, Thibaut Durand, Mohamed Osama Ahmed, Marcus Brubaker and Greg Mori
• Multivariate coupling estimation between continuous signals and point processes-- Shervin Safavi, Nikos K. Logothetis and Michel Besserve
• You May Not Need Order in Time Series Forecasting-- Yunkai Zhang, Qiao Jiang, Shurui Li, Xiaoyong Jin, Xueying Ma and Xifeng Yan
• Learning Temporal Point Processes using Neural Stochastic Differential Equations with Bayesian Jumps-- Kazi Islam and Christian Shelton
• Better Approximate Inference for Partial Likelihood Models with a Latent Structure-- Amrith Setlur and Barnabas Poczos

• Junchi Yan
• Antonio Vergari
• Bidisha Samanta
• Behzad Tabibian
• Shuang Li
• Marian-Andrei Rizoiu
• Utkarsh Upadhyay
• Karishma Sharma
• Ali Zarezade
• Yingxiang Yang
• Xinran He

• Manuel Gomez Rodriguez (Max Planck Institute for Software Systems)
• Le Song (Georgia Institute of Technology)
• Isabel Valera (Max Planck Institute for Intelligent Systems)
• Yan Liu (University of Southern California)
• Abir De (Max Planck Institute for Software Systems)
• Hongyuan Zha (Georgia Institute of Technology)