Publications (12)
Neural Injective Functions for Multisets, Measures and Graphs via a Finite Witness Theorem
Tal Amir, Steven J. Gortler, Ilai Avni +2
Injective multiset functions have a key role in the theoretical study of machine learning on multisets and graphs. Yet, there remains a gap between the provably injective multiset…
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…
Fourier Sliced-Wasserstein Embedding for Multisets and Measures
Tal Amir, Nadav Dym
We present the Fourier Sliced-Wasserstein (FSW) embedding - a novel method to embed multisets and measures over into Euclidean space. Our proposed embedding approxim…
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…
Symmetrized Robust Procrustes: Constant-Factor Approximation and Exact Recovery
Tal Amir, Shahar Kovalsky, Nadav Dym
The classical problem is to find a rigid motion (orthogonal transformation and translation) that best aligns two given point-sets in the least-squares sense.…
Weisfeiler Leman for Euclidean Equivariant Machine Learning
Snir Hordan, Tal Amir, Nadav Dym
The -Weisfeiler-Leman (-WL) graph isomorphism test hierarchy is a common method for assessing the expressive power of graph neural networks (GNNs). Recently, GNNs whose expre…