Recent success of deep learning is largely attributed to the sheer amount of data used for
training deep neural networks. Despite the unprecedented success, the massive data …

Most machine learning algorithms are configured by a set of hyperparameters whose values
must be carefully chosen and which often considerably impact performance. To avoid a time …

Self-supervised learning on graph-structured data has drawn recent interest for learning
generalizable, transferable and robust representations from unlabeled graphs. Among …

Abstract Machine learning algorithms have been used widely in various applications and
areas. To fit a machine learning model into different problems, its hyper-parameters must be …

The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …

Shallow neural networks process the features directly, while deep networks extract features
automatically along with the training. Both models suffer from overfitting or poor …

Automatic differentiation (autodiff) has revolutionized machine learning. Itallows to express
complex computations by composing elementary ones in creativeways and removes the …

Deep learning (DL) techniques have obtained remarkable achievements on various tasks,
such as image recognition, object detection, and language modeling. However, building a …

A core capability of intelligent systems is the ability to quickly learn new tasks by drawing on
prior experience. Gradient (or optimization) based meta-learning has recently emerged as …

Recent interest in complex and computationally expensive machine learning models with
many hyperparameters, such as automated machine learning (AutoML) frameworks and …