Abstract While Graph Neural Networks (GNNs) have been successfully leveraged for
learning on graph-structured data across domains, several potential pitfalls have been …

The notion of curvature on graphs has recently gained traction in the networks community,
with the Ollivier–Ricci curvature (ORC) in particular being used for several tasks in network …

Unsupervised node clustering (or community detection) is a classical graph learning task. In
this paper, we study algorithms, which exploit the geometry of the graph to identify densely …

Recently, there has been a surge of interest in representation learning in hyperbolic spaces,
driven by their ability to represent hierarchical data with significantly fewer dimensions than …

A wide variety of machine learning tasks such as knowledge base completion, ontology
alignment, and multi-label classification can benefit from incorporating into learning …

We study stochastic projection-free methods for constrained optimization of smooth functions
on Riemannian manifolds, ie, with additional constraints beyond the parameter domain …

A major factor contributing to the success of modern representation learning is the ease of
performing various vector operations. Recently, objects with geometric structures (eg …

Graph representation learning has been widely studied and demonstrated effectiveness in
various graph tasks. Most existing works embed graph data in the Euclidean space, while …

Structural and Positional Encodings can significantly improve the performance of Graph
Neural Networks in downstream tasks. Recent literature has begun to systematically …

A key challenge in Machine Learning (ML) is the identification of geometric structure in high-
dimensional data. Most algorithms assume that data lives in a high-dimensional vector …