← Search

Fanshuang Kong

2 accepted papers

2024

On Unsupervised Domain Adaptation: Pseudo Label Guided Mixup for Adversarial Prompt Tuning

AAAI 2024technical

To date, a backbone of methods for unsupervised domain adaptation (UDA) involves learning label-discriminative features via a label classifier and domain-invariant features through a domain discriminator in an adversarial scheme. However, these methods lack explicit control for aligning the source d…

2022

DropMix: A Textual Data Augmentation Combining Dropout with Mixup

EMNLP 2022main

Overfitting is a notorious problem when there is insufficient data to train deep neural networks in machine learning tasks. Data augmentation regularization methods such as Dropout, Mixup, and their enhanced variants are effective and prevalent, and achieve promising performance to overcome overfitt…

Cited by 12SourcePDFScholar