Transformer Hawkes Process

Authors: Simiao Zuo, Haoming Jiang, Zichong Li, Tuo Zhao, Hongyuan Zha

ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Numerical experiments on various datasets show that THP outperforms existing models in terms of both likelihood and event prediction accuracy by a notable margin.
Researcher Affiliation Academia 1Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, USA; 2School of the Gifted Young, University of Science and Technology of China, Hefei, China; 3Computational Science and Engineering, Georgia Institute of Technology, Atlanta, USA; 4School of Data Science, Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China; 5Currently on leave from Georgia Institute of Technology.
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes Our code is available at https://github.com/ Simiao Zuo/Transformer-Hawkes-Process.
Open Datasets Yes Retweets (Zhao et al., 2015): The Retweets dataset contains sequences of tweets... Meme Track (Leskovec & Krevl, 2014): This dataset contains mentions of 42 thousand different memes... Financial Transactions (Du et al., 2016): This financial dataset contains transaction records... Electrical Medical Records (Johnson et al., 2016): MIMICII medical dataset collects patients visit to a hospital... Stack Overflow (Leskovec & Krevl, 2014): Stack Overflow is a question-answering website... 911-Calls4: The 911-Calls dataset contains emergency phone call records. 4The dataset is available on www.kaggle.com/ mchirico/montcoalert. Earthquake5: This dataset contains time and location of earthquakes in China... 5The dataset is provided by China Earthquake Data Center. (http://data.earthquake.cn)
Dataset Splits No The paper mentions 'train-dev-test splitting ratio' in Figure 6, and 'held-out test sets are constructed by randomly sampling some events', but does not provide specific percentages or counts for training, validation, and test splits in the main text. Details about training are deferred to the appendix.
Hardware Specification No The paper does not provide specific hardware details (like exact GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper mentions using 'ADAM (Kingma & Ba, 2014)' as an optimization algorithm, but does not specify version numbers for any software dependencies or libraries.
Experiment Setup No The paper states 'Details about training are deferred to the appendix' and describes the loss function used, but does not provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs) or detailed system-level training settings in the main text.