Divide and augment: Supervised domain adaptation via sample-wise feature fusion
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 …
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
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 …
require access to source domain data while fine-tuning the model for the target domain …
Unsupervised domain adaptation via style-aware self-intermediate Domain
Unsupervised domain adaptation (UDA) has attracted considerable attention, which
transfers knowledge from a label-rich source domain to a related but unlabeled target …
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 …
applications using deep learning models, making significant contributions across several …