Time series forecasting holds significant importance in many real-world dynamic systems
and has been extensively studied. Unlike natural language process (NLP) and computer …

Temporal data, notably time series and spatio-temporal data, are prevalent in real-world
applications. They capture dynamic system measurements and are produced in vast …

The union of Edge Computing (EC) and Artificial Intelligence (AI) has brought forward the
Edge AI concept to provide intelligent solutions close to the end-user environment, for …

Over the past decade, the dominance of deep learning has prevailed across various
domains of artificial intelligence, including natural language processing, computer vision …

Recently, there has been a growing interest in leveraging pre-trained large language
models (LLMs) for various time series applications. However, the semantic space of LLMs …

Energy forecasting is crucial in scheduling and planning future electric load, so as to
improve the reliability and safeness of the power grid. Despite recent developments of …

Explanations in Computer Vision are often desired, but most Deep Neural Networks can
only provide saliency maps with questionable faithfulness. Self-Explaining Neural Networks …

High computation demands and big memory resources are the major implementation
challenges of Convolutional Neural Networks (CNNs) especially for low-power and resource …

In real-world scenarios like traffic and energy, massive time-series data with missing values
and noises are widely observed, even sampled irregularly. While many imputation methods …

Graph attention networks (GATs) are a mainstream graph neural network (GNN) model.
They have better performance in some tasks compared to other GNN models. The challenge …