Out-of-distribution Representation Learning for Time Series Classification

Authors: Wang Lu, Jindong Wang, Xinwei Sun, Yiqiang Chen, Xing Xie

ICLR 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments are conducted on seven datasets with different OOD settings across gesture recognition, speech commands recognition, wearable stress and affect detection, and sensor-based human activity recognition. Qualitative and quantitative results demonstrate that DIVERSIFY significantly outperforms other baselines and effectively characterizes the latent distributions.
Researcher Affiliation Collaboration Wang Lu1 , Jindong Wang2 , Xinwei Sun3, Yiqiang Chen1, Xing Xie2 1Institute of Comput. Tech., CAS 2Microsoft Research Asia 3Fudan University
Pseudocode No The paper describes the steps of the DIVERSIFY algorithm in narrative text and figures, but it does not include a clearly labeled pseudocode or algorithm block.
Open Source Code Yes Code is available at https://github.com/microsoft/robustlearn.
Open Datasets Yes Extensive experiments are conducted on seven datasets with different OOD settings across gesture recognition, speech commands recognition, wearable stress and affect detection, and sensor-based human activity recognition... EMG for gestures Data Set (Lobov et al., 2018)... Speech Commands dataset (Warden, 2018)... Wearable Stress and Affect Detection (WESAD) (Schmidt et al., 2018)... DSADS (Barshan & Y uksek, 2014), USC-HAD (Zhang & Sawchuk, 2012), UCI-HAR (Anguita et al., 2012), and PAMAP (Reiss & Stricker, 2012).
Dataset Splits Yes We conduct the training-domain-validation strategy and the training data are split by 8 : 2 for training and validation.
Hardware Specification No The paper does not explicitly describe the hardware used to run its experiments, such as specific GPU or CPU models, or cloud computing specifications.
Software Dependencies No The paper mentions 'Py Torch (Paszke et al., 2019)' but does not provide a specific version number for PyTorch or any other software dependencies crucial for replication.
Experiment Setup Yes The maximum training epoch is set to 150. The Adam optimizer with weight decay 5 10 4 is used. The learning rate for GILE is 10 4. The learning rate for the rest methods is 10 2 or 10 3. (For Speech Commands with Match Box Net3-1-64, we also try the learning rate, 10 4.) We tune hyperparameters for each method. Detailed data pre-processing, architecture, and hyperparameters are in Appendix C.5 and D.