Thomas Gebhart

According to our database, Thomas Gebhart authored at least 12 papers between 2017 and 2023.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2023

Extending Transductive Knowledge Graph Embedding Models for Inductive Logical Relational Inference.

Thomas Gebhart, John Cobb

CoRR, 2023

A Mathematical Framework for Citation Disruption.

Thomas Gebhart, Russell J. Funk

CoRR, 2023

Knowledge Sheaves: A Sheaf-Theoretic Framework for Knowledge Graph Embedding.

Thomas Gebhart, Jakob Hansen, Paul Schrater

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

Graph Convolutional Networks from the Perspective of Sheaves and the Neural Tangent Kernel.

Thomas Gebhart

Proceedings of the Topological, 2022

2021

A Unified Paths Perspective for Pruning at Initialization.

Thomas Gebhart, Udit Saxena, Paul Schrater

CoRR, 2021

Go with the Flow? A Large-Scale Analysis of Health Care Delivery Networks in the United States Using Hodge Theory.

Thomas Gebhart, Xiaojun Fu, Russell J. Funk

Proceedings of the 2021 IEEE International Conference on Big Data (Big Data), 2021

2020

Sheaf Neural Networks.

Jakob Hansen, Thomas Gebhart

CoRR, 2020

The Emergence of Higher-Order Structure in Scientific and Technological Knowledge Networks.

Thomas Gebhart, Russell J. Funk

CoRR, 2020

2019

Adversarial Examples Target Topological Holes in Deep Networks.

Thomas Gebhart, Paul Schrater

CoRR, 2019

Characterizing the Shape of Activation Space in Deep Neural Networks.

Thomas Gebhart, Paul Schrater, Alan Hylton

Proceedings of the 18th IEEE International Conference On Machine Learning And Applications, 2019

Path Homologies of Deep Feedforward Networks.

Samir Chowdhury, Thomas Gebhart, Steve Huntsman, Matvey Yutin

Proceedings of the 18th IEEE International Conference On Machine Learning And Applications, 2019

2017

Adversary Detection in Neural Networks via Persistent Homology.

Thomas Gebhart, Paul Schrater

CoRR, 2017