Kicking off our upcoming workshop at NeurIPS 2024, we're excited to announce the NeurReps Global Speaker Series!
Designed to foster a truly global community, the NeurReps Speaker Series is a rotating, biweekly, hybrid seminar series. By hosting and live-streaming talks from various international institutions, we aim to increase geographic diversity and broaden our worldwide network of researchers. Talks will be made publicly available on our website and various streaming services, ensuring widespread access to these valuable insights.
Join us as we build momentum towards the 3rd edition of the NeurReps Workshop at NeurIPS 2024, exploring the fascinating convergence of mathematical structures in neural systems and advancing our understanding of information processing in brains and machines.
ABSTRACT
This talk examines recent progress in the expressive power of geometric deep learning architectures, a prominent research direction motivated by fundamental limitations of traditional graph neural networks through two research projects. The session opens with a 5-minute introduction by Haggai Maron on his lab's research in geometric deep learning, followed by two 35-minute presentations: Guy Bar-Shalom will present his work on improving graph neural network expressivity via graph products (ICML 2024, NeurIPS 2024 and NeurIPS workshop Best Paper). Then, Yam Eitan and Yoav Gelberg will discuss their research on expressive power in topological deep learning (ICLR 2025 Oral).
Haggai Maron is an Assistant Professor and the Robert J. Shillman Fellow at the Faculty of Electrical and Computer Engineering at the Technion and a senior research scientist at NVIDIA Research at NVIDIA's lab in Tel Aviv. His primary research interest is in machine learning, with a focus on deep learning for structured data. Specifically, he studies how to apply deep learning techniques to sets, graphs, point clouds, surfaces, weight spaces and other mathematical objects that have an inherent symmetry structure
Guy is a Ph.D. Student in the Computer Science Department at the Technion under the joint supervision of Haggai Maron and Ran El-Yaniv . His research focuses on deep learning, with a specific interest in Graph Neural Networks and uncertainty estimation. He has interned as a research scientist at Google-Verlily and Meta.
Yam is a 2nd year PhD student in Haggai Maron's lab working on graph neural networks, geometric deep learning, and generative AI.
Yoav is a PhD student at the University of Oxford, co-advised by Yarin Gal, Michael Bronstein, and Haggai Maron. His research focuses on the symmetry and structure of neural network parameter spaces, with the goal of performing meta-learning tasks over model weights. He holds an undergraduate degree in mathematics from the Technion, where he was a Rothschild scholar. Before joining Oxford, Yoav conducted research on expander graphs at the Weizmann Institute, developed fair learning algorithms at Fairgen, and taught math and programming at the ARDC. His PhD is funded by the EPSRC through the AIMS CDT program.
Acknowledgements The present talk has been made possible thanks to the help of Guy Bar-Shalom (Technion) who served as a speaker and volunteer for locally hosting and recording the seminar.