Temporal Domain Generalization via Learning Instance-level Evolving Patterns

Authors: Yujie Jin, Zhibang Yang, Xu Chu, Liantao Ma

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on multiple classification and regression benchmarks demonstrate the effectiveness of the proposed CTOT framework.
Researcher Affiliation Academia Yujie Jin1,2 , Zhibang Yang2 , Xu Chu1,2,3 and Liantao Ma4 1School of Computer Science, Peking University, Beijing, China 2Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China 3Center on Frontiers of Computing Studies, Peking University, Beijing, China 4National Engineering Research Center of Software Engineering, Peking University, Beijing, China {jinyujie, chu xu, malt}@pku.edu.cn, yangzb@stu.pku.edu.cn
Pseudocode Yes The pseudo code of the overall CTOT is provided in Appendix A.2.
Open Source Code Yes The code and appendix are both available on https://github.com/JinYujie99/CTOT.
Open Datasets Yes Following existing works [Nasery et al., 2021; Bai et al., 2023], we conduct experiments on the following five classification datasets: Rotated Moons (2-Moons), Rotated MNIST (Rot-MNIST), Online News Popularity (ONP), Shuttle, and Electrical Demand (Elec2); and the following two regression datasets: House prices dataset (House), Appliances energy prediction dataset (Appliance).
Dataset Splits Yes For tuning hyperparameters, we consider data from the last source domain (DT ) as the validation set.
Hardware Specification No The paper does not provide specific hardware details such as GPU/CPU models or memory amounts.
Software Dependencies No The paper does not provide specific software dependencies with version numbers.
Experiment Setup Yes For tuning hyperparameters, we consider data from the last source domain (DT ) as the validation set. We control the number of generated instances to be close to the number of instances in a single source domain. For each method, the experiments are repeated 5 times with different random seeds, and we report the mean results and standard deviation. More details are given in Appendix B.3 and B.4.