Research

My broad research interests are in geometric and topological representation learning. During my PhD, my research focused on topological data analysis (TDA) and deep learning applications for graph structured data. Currently, my research interests also include AI assurance methods and model interpretability using tools from geometry and topology.

Papers and Preprints

Preprint

NervePool: A Simplicial Pooling Layer

Sarah McGuire, Elizabeth Munch, Matthew Hirn

arXiv preprint, 2023

Published version

Preprint

Do Neural Networks Trained with Topological Features Learn Different Internal Representations?

Sarah McGuire, Shane Jackson, Tegan Emerson, Henry Kvinge

Symmetry and Geometry in Neural Representations (NeurReps) Workshop at NeurIPS 2022

Published version

arXiv

Code

Taxonomy of Benchmarks in Graph Representation Learning

Renming Liu, Semih Cantürk, Frederik Wenkel, Sarah McGuire, Xinyi Wang, Anna Little, Leslie O’Bray, Michael Perlmutter, Bastian Rieck, Matthew Hirn, Guy Wolf, Ladislav Rampášek

Learning on Graphs Conference (LoG), 2022

arXiv

Towards a Taxonomy of Graph Learning Datasets

Renming Liu, Semih Cantürk, Frederik Wenkel, Dylan Sandfelder, Devin Kreuzer, Anna Little, Sarah McGuire, Leslie O’Bray, Michael Perlmutter, Bastian Rieck, Matthew Hirn, Guy Wolf, Ladislav Rampášek

Data-Centric AI workshop at NeurIPS, 2021

Page updated

Google Sites

Report abuse