7 papers
Monotone and Separable Set Functions: Characterizations and Neural Models
Soutrik Sarangi, Yonatan Sverdlov, Nadav Dym +1
Motivated by applications for set containment problems, we consider the following fundamental problem: can we design set-to-vector functions so that the natural partial order on se…
When and How to Canonize: A Generalization Perspective
Yonatan Sverdlov, Benjamin Friedman, Snir Hordan +1
While invariant architectures are standard for processing symmetric data, there is growing interest in achieving invariance by applying group averaging or canonization to non-invar…
FSW-GNN: A Bi-Lipschitz WL-Equivalent Graph Neural Network
Yonatan Sverdlov, Yair Davidson, Nadav Dym +1
Famously, the ability of Message Passing Neural Networks (MPNN) to distinguish between graphs is limited to graphs separable by the Weisfeiler-Lemann (WL) graph isomorphism test, a…
Short-Range Oversquashing
Yaaqov Mishayev, Yonatan Sverdlov, Tal Amir +1
Message Passing Neural Networks (MPNNs) are widely used for learning on graphs, but their ability to process long-range information is limited by the phenomenon of oversquashing. T…
Toward bilipshiz geometric models
Yonatan Sverdlov, Eitan Rosen, Nadav Dym
Many neural networks for point clouds are, by design, invariant to the symmetries of this datatype: permutations and rigid motions. The purpose of this paper is to examine whether…
Revisiting Multi-Permutation Equivariance through the Lens of Irreducible Representations
Yonatan Sverdlov, Ido Springer, Nadav Dym
This paper explores the characterization of equivariant linear layers for representations of permutations and related groups. Unlike traditional approaches, which address these pro…