Recently, hyperbolic deep neural networks (HDNNs) have been gaining momentum as the
deep representations in the hyperbolic space provide high fidelity embeddings with few …

Score-based generative models (SGMs) are a powerful class of generative models that
exhibit remarkable empirical performance. Score-based generative modelling (SGM) …

How we choose to represent our data has a fundamental impact on our ability to
subsequently extract information from them. Machine learning promises to automatically …

Normalizing flows are a powerful tool for building expressive distributions in high
dimensions. So far, most of the literature has concentrated on learning flows on Euclidean …

Interest has been rising lately towards methods representing data in non-Euclidean spaces,
eg hyperbolic or spherical that provide specific inductive biases useful for certain real-world …

An intriguing property of adversarial examples is their transferability, which suggests that
black-box attacks are feasible in real-world applications. Previous works mostly study the …

Normalizing flows have shown great promise for modelling flexible probability distributions
in a computationally tractable way. However, whilst data is often naturally described on …

Learning representations for graphs plays a critical role in a wide spectrum of downstream
applications. In this paper, we summarize the limitations of the prior works in three folds …

Continual graph learning routinely finds its role in a variety of real-world applications where
the graph data with different tasks come sequentially. Despite the success of prior works, it …

In this paper, we propose a new method to perform data augmentation in a reliable way in
the High Dimensional Low Sample Size (HDLSS) setting using a geometry-based …