Self-Interpretable Time Series Prediction with Counterfactual Explanations

Authors: Jingquan Yan, Hao Wang

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

Reproducibility Variable Result LLM Response
Research Type Experimental In this section, we evaluate our Coun TS and existing methods on two synthetic and three real-world datasets. For each dataset, we evaluate different methods in terms of three metrics: (1) prediction accuracy, (2) counterfactual accuracy, and (3) counterfactual change ratio, with the last one as the most important metric.
Researcher Affiliation Academia 1Department of Computer Science, Rutgers University. Correspondence to: Jingquan Yan <jy766@rutgers.edu>.
Pseudocode Yes Algorithm 1 Generating Counterfactual Explanations
Open Source Code Yes Code will be available at https://github.com/Wang-MLLab/self-interpretable-time-series.
Open Datasets Yes We evaluate our model on three real-world medical datasets: Sleep Heart Health Study (SHHS) (Quan et al., 1997), Multi-ethnic Study of Atherosclerosis (MESA) (Zhang et al., 2018a), and Study of Osteoporotic Fractures (SOF) (Cummings et al., 1990)
Dataset Splits No In the cross-dataset setting, 'We use all source datasets (e.g., SHHS and MESA) and 10% of the target dataset (e.g., SOF) as the training set and use the remaining 90% of the target dataset as the test set.' While this provides training and test split information, it does not explicitly state a validation split percentage.
Hardware Specification No The paper does not provide specific hardware details such as CPU/GPU models, memory, or cloud computing instance types used for experiments.
Software Dependencies No All methods above are implemented with Py Torch (Paszke et al., 2019). - While PyTorch is mentioned and cited, a specific version number is not provided (e.g., 'PyTorch 1.9'), which is required for reproducibility.
Experiment Setup No The paper mentions λ as a hyperparameter for balancing terms in the objective function but does not provide its specific value or other typical experimental setup details such as learning rate, batch size, or optimizer settings in the main text.