Hyperbolic deep neural networks: A survey
Recently, hyperbolic deep neural networks (HDNNs) have been gaining momentum as the
deep representations in the hyperbolic space provide high fidelity embeddings with few …
deep representations in the hyperbolic space provide high fidelity embeddings with few …
Riemannian score-based generative modelling
Score-based generative models (SGMs) are a powerful class of generative models that
exhibit remarkable empirical performance. Score-based generative modelling (SGM) …
exhibit remarkable empirical performance. Score-based generative modelling (SGM) …
[HTML][HTML] Learning meaningful representations of protein sequences
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 …
subsequently extract information from them. Machine learning promises to automatically …
Normalizing flows on tori and spheres
DJ Rezende, G Papamakarios… - International …, 2020 - proceedings.mlr.press
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 …
dimensions. So far, most of the literature has concentrated on learning flows on Euclidean …
Constant curvature graph convolutional networks
G Bachmann, G Bécigneul… - … conference on machine …, 2020 - proceedings.mlr.press
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 …
eg hyperbolic or spherical that provide specific inductive biases useful for certain real-world …
Towards transferable targeted attack
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 …
black-box attacks are feasible in real-world applications. Previous works mostly study the …
Riemannian continuous normalizing flows
Normalizing flows have shown great promise for modelling flexible probability distributions
in a computationally tractable way. However, whilst data is often naturally described on …
in a computationally tractable way. However, whilst data is often naturally described on …
Hyperbolic variational graph neural network for modeling dynamic graphs
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 …
applications. In this paper, we summarize the limitations of the prior works in three folds …
Self-supervised continual graph learning in adaptive riemannian spaces
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 …
the graph data with different tasks come sequentially. Despite the success of prior works, it …
Data augmentation in high dimensional low sample size setting using a geometry-based variational autoencoder
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 …
the High Dimensional Low Sample Size (HDLSS) setting using a geometry-based …