Domain Adaptation with Invariant Representation Learning: What Transformations to Learn?

Authors: Petar Stojanov, Zijian Li, Mingming Gong, Ruichu Cai, Jaime Carbonell, Kun Zhang

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate the efficacy of our method via synthetic and real-world data experiments.
Researcher Affiliation Academia 1 Carnegie Mellon University 2 School of Computer Science, Guangdong University of Technology 3 School of Mathematics and Statistics, University of Melbourne 4 Broad Institute of MIT and Harvard
Pseudocode No The paper describes the method verbally and with a diagram (Figure 3), but does not include any structured pseudocode or algorithm blocks.
Open Source Code Yes The code is available at: https://github.com/DMIRLAB-Group/DSAN.
Open Datasets Yes To evaluate our method on real datasets, we consider three datasets and respective tasks from various domains of applications: cross-domain Wi-Fi localization, Amazon product reviews and image classification.
Dataset Splits No No explicit dataset split percentages or sample counts for training, validation, or test sets are provided in the main text. Details are referred to supplementary materials.
Hardware Specification No No specific hardware details such as GPU/CPU models, memory, or computing infrastructure are mentioned in the paper.
Software Dependencies No No specific software dependencies with version numbers (e.g., Python version, library versions like PyTorch, TensorFlow, etc.) are mentioned in the paper.
Experiment Setup No For detailed descriptions of the experimental design, hyperparameter tuning and neural network architectures, as well as ablation studies, we refer the interested reader to the supplementary materials.