Domain-Indexing Variational Bayes: Interpretable Domain Index for Domain Adaptation

Authors: Zihao Xu, Guang-Yuan Hao, Hao He, Hao Wang

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

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical results on both synthetic and real data verify that our model can produce interpretable domain indices which enable us to achieve superior performance compared to state-of-the-art domain adaptation methods. In this section, we compare VDI with existing DA methods on both synthetic and real-world datasets.
Researcher Affiliation Academia 1Rutgers University, 2Hong Kong University of Science and Technology, 3Massachusetts Institute of Technology
Pseudocode No The paper does not contain any sections or figures explicitly labeled "Pseudocode" or "Algorithm".
Open Source Code Yes Code is available at https://github.com/Wang-ML-Lab/VDI.
Open Datasets Yes Circle (Wang et al., 2020) is a synthetic dataset with 30 domains for binary classification. DG-15 and DG-16 (Xu et al., 2022). TPT-48 (Xu et al., 2022) is a real-world regression dataset... Comp Cars (Yang et al., 2015) is a car image dataset...
Dataset Splits No The paper mentions using source and target domains but does not explicitly state train/validation/test dataset splits with specific percentages or counts needed for reproduction.
Hardware Specification No The paper does not specify any particular hardware (e.g., CPU, GPU models, or cloud computing instances) used for running the experiments.
Software Dependencies No The paper does not specify software dependencies with version numbers (e.g., 'Python 3.x', 'PyTorch 1.x').
Experiment Setup Yes For experiments on all 4 datasets, we set the dimension of global domain indices to 2. For Circle, DG-15, DG-60, the dimension of local domain indices is 4, while for TPT-48 and Comp Cars, the dimension of local domain indices is 8. Our model is trained with 20 to 70 warmup steps, learning rates ranging from 1 10 5 to 1 10 4, and λd ranging from 0.1 to 1.