waghmaregovind / joint_tpp

Modeling Inter-Dependence Between Time and Mark in Multivariate Temporal Point Processes, CIKM 22

Modeling Inter-Dependence Between Time and Mark in Multivariate Temporal Point Processes

This repository includes PyTorch implementation of the paper "Modeling Inter-Dependence Between Time and Mark in Multivariate Temporal Point Processes", CIKM 2022.

Datasets

• Real-world datasets are available at: data/real
• Synthetic Hawkes datasets: Refer to synth_data_gen.ipynb for Hawkes process data generation.

Acknowledgements

• We build on top of ifl-tpp source code. dpp package is copied and modified to support joint modeling of time and mark. Thanks to Oleksandr Shchur for the awesome codebase.

• and neuralTPPs are used to generate synthetic Hawkes process data.

Citation

@inproceedings{10.1145/3511808.3557399,
author = {Waghmare, Govind and Debnath, Ankur and Asthana, Siddhartha and Malhotra, Aakarsh},
title = {Modeling Inter-Dependence Between Time and Mark in Multivariate Temporal Point Processes},
year = {2022},
isbn = {9781450392365},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3511808.3557399},
doi = {10.1145/3511808.3557399},
booktitle = {Proceedings of the 31st ACM International Conference on Information & Knowledge Management},
pages = {1986–1995},
numpages = {10},
keywords = {multivariate temporal point processes, probabilistic modeling},
location = {Atlanta, GA, USA},
series = {CIKM '22}
}