70 citations · 110 across the 33 of their papers we have counts for
39 papers
Specific Algorithmic Interpretability of Neural Networks: A Case Study on Textures
Yanglin Zhang, Anneke von Seeger, Gilad Lerman +1
We develop a principled framework for constructing neural networks whose specific parameter realizations admit an explicit algorithmic interpretation. Existing algorithm-inspired a…
Out-of-Distribution Inverse Design of Elastic Networks with Differentiable Graph Neural Network Molecular Dynamics
Sergey A. Shteingolts, Salman N. Salman, Ron Levie +1
Machine-learning-based inverse design can accelerate the discovery of materials with targeted properties, but conventional structure--property models often require large training d…
Beyond Oversquashing: Understanding Signal Propagation in GNNs Via Observables
Eden Nagar, Ya-Wei Eileen Lin, Ron Levie
Graph Neural Networks (GNNs) perform computations on graphs by routing the signal between graph regions using a graph shift operator or a message passing scheme. Often, the propaga…
Graph Learning Should Move Beyond Restrictive Views of Spectral and Message-Passing GNNs
Antonis Vasileiou, Juan Cervino, Pascal Frossard +7
Graph neural networks (GNNs) are commonly divided into message-passing neural networks (MPNNs) and spectral GNNs, reflecting two largely separate research traditions in machine lea…
A Graphop Analysis of Graph Neural Networks on Sparse Graphs: Generalization and Universal Approximation
Ofek Amran, Tom Gilat, Ron Levie
Generalization and approximation capabilities of message passing graph neural networks (MPNNs) are often studied by defining a compact metric on a space of input graphs under which…
Neural Networks With Dense Weights Are Not Universal Approximators
Levi Rauchwerger, Stefanie Jegelka, Ron Levie
We investigate the approximation capabilities of dense neural networks. While universal approximation theorems establish that sufficiently large architectures can approximate arbit…
Equivariant Machine Learning on Graphs with Nonlinear Spectral Filters
Ya-Wei Eileen Lin, Ronen Talmon, Ron Levie
Equivariant machine learning is an approach for designing deep learning models that respect the symmetries of the problem, with the aim of reducing model complexity and improving g…
Learning on Large Graphs using Intersecting Communities
Ben Finkelshtein, İsmail İlkan Ceylan, Michael Bronstein +1
Message Passing Neural Networks (MPNNs) are a staple of graph machine learning. MPNNs iteratively update each node's representation in an input graph by aggregating messages from t…
Generalization Bounds for Message Passing Networks on Mixture of Graphons
Sohir Maskey, Gitta Kutyniok, Ron Levie
We study the generalization capabilities of Message Passing Neural Networks (MPNNs), a prevalent class of Graph Neural Networks (GNN). We derive generalization bounds specifically…
Future Directions in the Theory of Graph Machine Learning
Christopher Morris, Fabrizio Frasca, Nadav Dym +7
Machine learning on graphs, especially using graph neural networks (GNNs), has seen a surge in interest due to the wide availability of graph data across a broad spectrum of discip…
The First Pathloss Radio Map Prediction Challenge
Çağkan Yapar, Fabian Jaensch, Ron Levie +2
To foster research and facilitate fair comparisons among recently proposed pathloss radio map prediction methods, we have launched the ICASSP 2023 First Pathloss Radio Map Predicti…
Approximately Equivariant Graph Networks
Ningyuan Huang, Ron Levie, Soledad Villar
Graph neural networks (GNNs) are commonly described as being permutation equivariant with respect to node relabeling in the graph. This symmetry of GNNs is often compared to the tr…
Fine-grained Expressivity of Graph Neural Networks
Jan Böker, Ron Levie, Ningyuan Huang +2
Numerous recent works have analyzed the expressive power of message-passing graph neural networks (MPNNs), primarily utilizing combinatorial techniques such as the -dimensional…
A graphon-signal analysis of graph neural networks
Ron Levie
We present an approach for analyzing message passing graph neural networks (MPNNs) based on an extension of graphon analysis to a so called graphon-signal analysis. A MPNN is a fun…
Dataset of Pathloss and ToA Radio Maps With Localization Application
Çağkan Yapar, Ron Levie, Gitta Kutyniok +1
In this article, we present a collection of radio map datasets in dense urban setting, which we generated and made publicly available. The datasets include simulated pathloss/recei…
On the Effective Usage of Priors in RSS-based Localization
Çağkan Yapar, Fabian Jaensch, Ron Levie +1
In this paper, we study the localization problem in dense urban settings. In such environments, Global Navigation Satellite Systems fail to provide good accuracy due to low likelih…
Unveiling the Sampling Density in Non-Uniform Geometric Graphs
Raffaele Paolino, Aleksandar Bojchevski, Stephan Günnemann +2
A powerful framework for studying graphs is to consider them as geometric graphs: nodes are randomly sampled from an underlying metric space, and any pair of nodes is connected if…
Explaining Image Classifiers with Multiscale Directional Image Representation
Stefan Kolek, Robert Windesheim, Hector Andrade Loarca +2
Image classifiers are known to be difficult to interpret and therefore require explanation methods to understand their decisions. We present ShearletX, a novel mask explanation met…
Memorization-Dilation: Modeling Neural Collapse Under Label Noise
Duc Anh Nguyen, Ron Levie, Julian Lienen +2
The notion of neural collapse refers to several emergent phenomena that have been empirically observed across various canonical classification problems. During the terminal phase o…
LocUNet: Fast Urban Positioning Using Radio Maps and Deep Learning
Çağkan Yapar, Ron Levie, Gitta Kutyniok +1
This paper deals with the problem of localization in a cellular network in a dense urban scenario. Global Navigation Satellite Systems (GNSS) typically perform poorly in urban envi…
Generalization Analysis of Message Passing Neural Networks on Large Random Graphs
Sohir Maskey, Ron Levie, Yunseok Lee +1
Message passing neural networks (MPNN) have seen a steep rise in popularity since their introduction as generalizations of convolutional neural networks to graph-structured data, a…
A Rate-Distortion Framework for Explaining Black-box Model Decisions
Stefan Kolek, Duc Anh Nguyen, Ron Levie +2
We present the Rate-Distortion Explanation (RDE) framework, a mathematically well-founded method for explaining black-box model decisions. The framework is based on perturbations o…
Cartoon Explanations of Image Classifiers
Stefan Kolek, Duc Anh Nguyen, Ron Levie +2
We present CartoonX (Cartoon Explanation), a novel model-agnostic explanation method tailored towards image classifiers and based on the rate-distortion explanation (RDE) framework…
Transferability of Graph Neural Networks: an Extended Graphon Approach
Sohir Maskey, Ron Levie, Gitta Kutyniok
We study spectral graph convolutional neural networks (GCNNs), where filters are defined as continuous functions of the graph shift operator (GSO) through functional calculus. A sp…