Overview

This is the homepage for our ICLR 2022 workshop on ‘Geometrical and Topological Representation Learning’.

Information for participants

The workshop and the associated Geomstats challenge are over—a big thank you to everyone who participated!

Background

Over the past two decades, high-throughput data collection technologies have become commonplace in most fields of science and technology, and with them an ever-increasing amount of big high dimensional data is being generated by virtually every real-world system. While such data systems are highly diverse in nature, the underlying data analysis and exploration task give rise to common challenges at the core of modern representation learning. For example, even though modern real-world data typically have high dimensional ambient measurement spaces, they often exhibit low dimensional intrinsic structures that can be uncovered by geometry-oriented methods, such as the ones encountered in manifold learning, graph signal processing, geometric deep learning, and topological data analysis. As a result, recent years have seen significant interest and progress in geometric and topological approaches to representation learning, which enable tractable exploratory analysis by domain experts who are often not computation-oriented. Our overarching goal in the proposed workshop is to deepen our understanding of the challenges and opportunities in this field, while breaking the barriers between the typically disjoint computational approaches (or communities) that work in this field, with emphasis on the domains of topological data analysis, graph representation learning, and manifold learning, on which we shall subsequently briefly comment.

Call for Papers: Topology, Algebra, and Geometry in the Data Sciences (Special Issue of La Matematica)

This special issue will show-case work which takes concepts or tools from the rich fields of topology, algebra, and geometry and brings them to bear on data science problems. We expect the developed approaches to address a specific challenge and demonstrate utility on at least one interesting dataset. Submitted works should provide novel methodology and insight into interesting real-world datasets but are not required to be evaluated on conventional benchmarking datasets if these do not adequately capture the challenge which the paper seeks to address. Authors that have participated in the Geometrical and Topological Representation Learning Workshop at ICLR are encouraged to submit extended versions of their conference paper, provided there is significant novel extension of the work and the conference paper is appropriately cited and summarized.

See https://www.springer.com/journal/44007/updates/19962244 for more information.