In recent years, deep learning (DL) has been widely studied using various methods across
the globe, especially with respect to training methods and network structures, proving highly …

Abstract Knowledge extraction through machine learning techniques has been successfully
applied in a large number of application domains. However, apart from the required …

Sensors in cyber-physical systems often capture interconnected processes and thus emit
correlated time series (CTS), the forecasting of which enables important applications. The …

In multiobjective evolutionary neural architecture search (NAS), existing predictor-based
methods commonly suffer from the rank disorder issue that a candidate high-performance …

Sensors in cyber-physical systems often capture interconnected processes and thus emit
correlated time series (CTS), the forecasting of which enables important applications …

Heterogeneous graphs are commonly used to describe networked data with multiple types
of nodes and edges. Heterogeneous Graph Neural Networks (HGNNs) are powerful tools for …

We study self-supervised video representation learning, which is a challenging task due to
1) sufficient labels for supervision; 2) unstructured and noisy visual information. Existing …

Time-consuming performance evaluation is the bottleneck of traditional Neural Architecture
Search (NAS) methods. Predictor-based NAS can speed up performance evaluation by …

Neural architecture search (NAS) is a popular method that can automatically design deep
neural network structures. However, designing a neural network using NAS is …

Abstract Predictor-based Neural Architecture Search (NAS) continues to be an important
topic because it aims to mitigate the time-consuming search procedure of traditional NAS …