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

Networks are finite metric spaces, with distances defined by the shortest paths between
nodes. However, this is not the only form of network geometry: two others are the geometry …

Graph convolutional neural networks (GCNs) embed nodes in a graph into Euclidean space,
which has been shown to incur a large distortion when embedding real-world graphs with …

There has been a surge of recent interest in graph representation learning (GRL). GRL
methods have generally fallen into three main categories, based on the availability of …

Learning from graph-structured data is an important task in machine learning and artificial
intelligence, for which Graph Neural Networks (GNNs) have shown great promise. Motivated …

Abstract Representation learning has become an invaluable approach for learning from
symbolic data such as text and graphs. However, state-of-the-art embedding methods …

We are concerned with the discovery of hierarchical relationships from large-scale
unstructured similarity scores. For this purpose, we study different models of hyperbolic …

Hyperbolic embeddings offer excellent quality with few dimensions when embedding
hierarchical data structures. We give a combinatorial construction that embeds trees into …

Abstract Similarity-based Hierarchical Clustering (HC) is a classical unsupervised machine
learning algorithm that has traditionally been solved with heuristic algorithms like Average …

Hyperbolic neural networks have shown great potential for modeling complex data.
However, existing hyperbolic networks are not completely hyperbolic, as they encode …