Divide and augment: Supervised domain adaptation via sample-wise feature fusion

Z Chen, B Pu, L Zhao, J He, P Liang - Information Fusion, 2025 - Elsevier
The training of deep models relies on appropriate regularization from a copious amount of
labeled data. And yet, obtaining a large and well-annotated dataset is costly. Thus …

Source-Free Domain Adaptation for Question Answering with Masked Self-training

MJ Yin, B Wang, Y Dong, C Ling - Transactions of the Association for …, 2024 - direct.mit.edu
Previous unsupervised domain adaptation (UDA) methods for question answering (QA)
require access to source domain data while fine-tuning the model for the target domain …

Unsupervised domain adaptation via style-aware self-intermediate Domain

L Wang, M Wang, D Zhang, H Fu - arxiv preprint arxiv:2209.01870, 2022 - arxiv.org
Unsupervised domain adaptation (UDA) has attracted considerable attention, which
transfers knowledge from a label-rich source domain to a related but unlabeled target …

Improving representation learning on graph-structural data for classification, generation, and recommendation

T Luo - 2024 - dr.ntu.edu.sg
This thesis explores innovative approaches in graph representation learning and its
applications using deep learning models, making significant contributions across several …