A Dirichlet Mixture Model of Hawkes Processes for Event Sequence Clustering
Authors: Hongteng Xu, Hongyuan Zha
NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on both synthetic and real-world data show that the clustering method based on our model can learn structural triggering patterns hidden in asynchronous event sequences robustly and achieve superior performance on clustering purity and consistency compared to existing methods.Table 1: Clustering Purity on Synthetic Data.Table 2: Clustering Consistency on Real-world Data.In Fig. 3 we visualize the comparison for our method and its main competitor MMHP+DPGMM on the ICU patient flow data. |
| Researcher Affiliation | Academia | Hongteng Xu School of ECE Georgia Institute of Technology hongtengxu313@gmail.comHongyuan Zha College of Computing Georgia Institute of Technology zha@cc.gateh.edu |
| Pseudocode | No | The paper describes a variational Bayesian inference algorithm within a nested EM framework but does not provide pseudocode or an algorithm block in the main text. It states 'Both the details of our algorithm and its computational complexity are given in the supplementary file.' |
| Open Source Code | Yes | The source code can be found at https://github.com/Hongteng Xu/Hawkes-Process-Toolkit. |
| Open Datasets | Yes | The first is the ICU patient flow data used in [43], which is extracted from the MIMIC II data set [32]. This data set contains the transition processes of 30, 308 patients among different kinds of care units.The second is the IPTV data set in [20,22], which contains 7, 100 IPTV users viewing records collected via Shanghai Telecomm Inc. |
| Dataset Splits | No | The paper describes a cross-validation setup where data is 'randomly divided into two folds' (training and testing folds) to measure consistency. However, it does not specify explicit train/validation/test splits with percentages or exact counts for the main model training. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used for running the experiments, such as CPU or GPU models, or memory specifications. |
| Software Dependencies | No | The paper does not specify any software dependencies with version numbers (e.g., programming languages, libraries, frameworks, or solvers). |
| Experiment Setup | No | While the paper describes data generation parameters for synthetic data and discusses inner iteration allocation strategies, it does not provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs, optimizer settings) or other concrete training configurations for the DMHP model. |