The pursuit of optimal neural network architectures is foundational to the progression of
Neural Architecture Search (NAS). However, the existing NAS methods suffer from the …

Differential privacy (DP), as a promising privacy-preserving model, has attracted great
interest from researchers in recent years. At present, research on the combination of deep …

Neural Architecture Search (NAS) has emerged as one of the effective methods to design
the optimal neural network architecture automatically. Although neural architectures have …

Continual learning refers to the capability of a machine learning model to learn and adapt to
new information, without compromising its performance on previously learned tasks …

Abstract Transformer-based Large Models (TLM), such as generative pre-trained models
(GPT), have become increasingly popular for practical applications through Deep Learning …

A classifier with the ability to handle continuous streams of opinion information on the
Internet should have good lifelong learning ability. However, deep neural networks face the …

This study presents an adaptive online learning method for text classification under
distribution shifts. We formulate a typical neural network-based text classification model as …

Information retrieval (IR) refers to obtaining relevant information from a repository, such as a
database or the internet, based on a user's query. The rise of deep learning has led to the …

This study investigated the intricate dynamics of the stability-plasticity trade-off within large
language models (LLMs) as applied to healthcare chatbot systems, specifically focusing on …