Tabular Data Augmentation for Machine Learning: Progress and Prospects of Embracing Generative AI
Machine learning (ML) on tabular data is ubiquitous, yet obtaining abundant high-quality
tabular data for model training remains a significant obstacle. Numerous works have …
tabular data for model training remains a significant obstacle. Numerous works have …
[HTML][HTML] Feasibility Study of Edge Computing Empowered by Artificial Intelligence—A Quantitative Analysis Based on Large Models
Y Chen, C Wu, R Sui, J Zhang - Big Data and Cognitive Computing, 2024 - mdpi.com
The advancement of artificial intelligence (AI) demands significant data and computational
resources that have an adverse impact on the environment. To address this issue, a novel …
resources that have an adverse impact on the environment. To address this issue, a novel …
NegativePrompt: Leveraging Psychology for Large Language Models Enhancement via Negative Emotional Stimuli
Large Language Models (LLMs) have become integral to a wide spectrum of applications,
ranging from traditional computing tasks to advanced artificial intelligence (AI) applications …
ranging from traditional computing tasks to advanced artificial intelligence (AI) applications …
Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives
Humans use multiple senses to comprehend the environment. Vision and language are two
of the most vital senses since they allow us to easily communicate our thoughts and …
of the most vital senses since they allow us to easily communicate our thoughts and …
LLMs vs Established Text Augmentation Techniques for Classification: When do the Benefits Outweight the Costs?
The generative large language models (LLMs) are increasingly being used for data
augmentation tasks, where text samples are LLM-paraphrased and then used for classifier …
augmentation tasks, where text samples are LLM-paraphrased and then used for classifier …
Stochastic Adversarial Networks for Multi-Domain Text Classification
Adversarial training has been instrumental in advancing multi-domain text classification
(MDTC). Traditionally, MDTC methods employ a shared-private paradigm, with a shared …
(MDTC). Traditionally, MDTC methods employ a shared-private paradigm, with a shared …
A Survey of Data Synthesis Approaches
HY Chang, PY Chen, TH Chou, CS Kao, HY Yu… - arXiv preprint arXiv …, 2024 - arxiv.org
This paper provides a detailed survey of synthetic data techniques. We first discuss the
expected goals of using synthetic data in data augmentation, which can be divided into four …
expected goals of using synthetic data in data augmentation, which can be divided into four …
You Only Need Half: Boosting Data Augmentation by Using Partial Content
J Hu, Y Wu - arXiv preprint arXiv:2405.02830, 2024 - arxiv.org
We propose a novel data augmentation method termed You Only Need hAlf (YONA), which
simplifies the augmentation process. YONA bisects an image, substitutes one half with …
simplifies the augmentation process. YONA bisects an image, substitutes one half with …
Margin Discrepancy-based Adversarial Training for Multi-Domain Text Classification
Y Wu - arXiv preprint arXiv:2403.00888, 2024 - arxiv.org
Multi-domain text classification (MDTC) endeavors to harness available resources from
correlated domains to enhance the classification accuracy of the target domain. Presently …
correlated domains to enhance the classification accuracy of the target domain. Presently …
Vision Transformer-based Adversarial Domain Adaptation
Y Li, Y Wu - arXiv preprint arXiv:2404.15817, 2024 - arxiv.org
Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source
domain to an unlabeled target domain. The most recent UDA methods always resort to …
domain to an unlabeled target domain. The most recent UDA methods always resort to …