15 citations · 56 across the 12 of their papers we have counts for
14 papers
Neural Link Prediction with Walk Pooling
Liming Pan, Cheng Shi, Ivan Dokmanić
Graph neural networks achieve high accuracy in link prediction by jointly leveraging graph topology and node attributes. Topology, however, is represented indirectly; state-of-the-…
Universal Joint Approximation of Manifolds and Densities by Simple Injective Flows
Michael Puthawala, Matti Lassas, Ivan Dokmanić +1
We study approximation of probability measures supported on -dimensional manifolds embedded in by injective flows -- neural networks composed of invertible flows…
Universal Approximation Under Constraints is Possible with Transformers
Anastasis Kratsios, Behnoosh Zamanlooy, Tianlin Liu +1
Many practical problems need the output of a machine learning model to satisfy a set of constraints, . Nevertheless, there is no known guarantee that classical neural network ar…
Truly shift-equivariant convolutional neural networks with adaptive polyphase upsampling
Anadi Chaman, Ivan Dokmanić
Convolutional neural networks lack shift equivariance due to the presence of downsampling layers. In image classification, adaptive polyphase downsampling (APS-D) was recently prop…
Trumpets: Injective Flows for Inference and Inverse Problems
Konik Kothari, AmirEhsan Khorashadizadeh, Maarten de Hoop +1
We propose injective generative models called Trumpets that generalize invertible normalizing flows. The proposed generators progressively increase dimension from a low-dimensional…
Localizing Unsynchronized Sensors with Unknown Sources
Dalia El Badawy, Viktor Larsson, Marc Pollefeys +1
We propose a method for sensor array self-localization using a set of sources at unknown locations. The sources produce signals whose times of arrival are registered at the sensors…