98 citations · 622 across the 36 of their papers we have counts for
27 papers · 1 filter
Homomorphism Expressivity of Spectral Invariant Graph Neural Networks
Jingchu Gai, Yiheng Du, Bohang Zhang +2
Graph spectra are an important class of structural features on graphs that have shown promising results in enhancing Graph Neural Networks (GNNs). Despite their widespread practica…
On the Reconstruction of Training Data from Group Invariant Networks
Ran Elbaz, Gilad Yehudai, Meirav Galun +1
Reconstructing training data from trained neural networks is an active area of research with significant implications for privacy and explainability. Recent advances have demonstra…
Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models
Theo Putterman, Derek Lim, Yoav Gelberg +2
Low-rank adaptations (LoRAs) have revolutionized the finetuning of large foundation models, enabling efficient adaptation even with limited computational resources. The resulting p…
On the Expressive Power of Spectral Invariant Graph Neural Networks
Bohang Zhang, Lingxiao Zhao, Haggai Maron
Incorporating spectral information to enhance Graph Neural Networks (GNNs) has shown promising results but raises a fundamental challenge due to the inherent ambiguity of eigenvect…
The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof
Derek Lim, Theo Moe Putterman, Robin Walters +2
Many algorithms and observed phenomena in deep learning appear to be affected by parameter symmetries -- transformations of neural network parameters that do not change the underly…
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…
Graph Metanetworks for Processing Diverse Neural Architectures
Derek Lim, Haggai Maron, Marc T. Law +2
Neural networks efficiently encode learned information within their parameters. Consequently, many tasks can be unified by treating neural networks themselves as input data. When d…
Expressive Sign Equivariant Networks for Spectral Geometric Learning
Derek Lim, Joshua Robinson, Stefanie Jegelka +1
Recent work has shown the utility of developing machine learning models that respect the structure and symmetries of eigenvectors. These works promote sign invariance, since for an…
Hierarchical Graph Neural Network with Cross-Attention for Cross-Device User Matching
Ali Taghibakhshi, Mingyuan Ma, Ashwath Aithal +3
Cross-device user matching is a critical problem in numerous domains, including advertising, recommender systems, and cybersecurity. It involves identifying and linking different d…
Equivariant Polynomials for Graph Neural Networks
Omri Puny, Derek Lim, Bobak T. Kiani +2
Graph Neural Networks (GNN) are inherently limited in their expressive power. Recent seminal works (Xu et al., 2019; Morris et al., 2019b) introduced the Weisfeiler-Lehman (WL) hie…
Generalized Laplacian Positional Encoding for Graph Representation Learning
Sohir Maskey, Ali Parviz, Maximilian Thiessen +3
Graph neural networks (GNNs) are the primary tool for processing graph-structured data. Unfortunately, the most commonly used GNNs, called Message Passing Neural Networks (MPNNs) s…
Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries
Fabrizio Frasca, Beatrice Bevilacqua, Michael M. Bronstein +1
Subgraph GNNs are a recent class of expressive Graph Neural Networks (GNNs) which model graphs as collections of subgraphs. So far, the design space of possible Subgraph GNN archit…
A Simple and Universal Rotation Equivariant Point-cloud Network
Ben Finkelshtein, Chaim Baskin, Haggai Maron +1
Equivariance to permutations and rigid motions is an important inductive bias for various 3D learning problems. Recently it has been shown that the equivariant Tensor Field Network…
Sign and Basis Invariant Networks for Spectral Graph Representation Learning
Derek Lim, Joshua Robinson, Lingxiao Zhao +4
We introduce SignNet and BasisNet -- new neural architectures that are invariant to two key symmetries displayed by eigenvectors: (i) sign flips, since if is an eigenvector the…
Federated Learning with Heterogeneous Architectures using Graph HyperNetworks
Or Litany, Haggai Maron, David Acuna +3
Standard Federated Learning (FL) techniques are limited to clients with identical network architectures. This restricts potential use-cases like cross-platform training or inter-or…
Weisfeiler and Leman go Machine Learning: The Story so far
Christopher Morris, Yaron Lipman, Haggai Maron +5
In recent years, algorithms and neural architectures based on the Weisfeiler--Leman algorithm, a well-known heuristic for the graph isomorphism problem, have emerged as a powerful…
Equivariant Subgraph Aggregation Networks
Beatrice Bevilacqua, Fabrizio Frasca, Derek Lim +5
Message-passing neural networks (MPNNs) are the leading architecture for deep learning on graph-structured data, in large part due to their simplicity and scalability. Unfortunatel…
On the Universality of Rotation Equivariant Point Cloud Networks
Nadav Dym, Haggai Maron
Learning functions on point clouds has applications in many fields, including computer vision, computer graphics, physics, and chemistry. Recently, there has been a growing interes…
From Local Structures to Size Generalization in Graph Neural Networks
Gilad Yehudai, Ethan Fetaya, Eli Meirom +2
Graph neural networks (GNNs) can process graphs of different sizes, but their ability to generalize across sizes, specifically from small to large graphs, is still not well underst…
Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks
Eli A. Meirom, Haggai Maron, Shie Mannor +1
We consider the problem of controlling a partially-observed dynamic process on a graph by a limited number of interventions. This problem naturally arises in contexts such as sched…
Learning Algebraic Multigrid Using Graph Neural Networks
Ilay Luz, Meirav Galun, Haggai Maron +2
Efficient numerical solvers for sparse linear systems are crucial in science and engineering. One of the fastest methods for solving large-scale sparse linear systems is algebraic…
Set2Graph: Learning Graphs From Sets
Hadar Serviansky, Nimrod Segol, Jonathan Shlomi +4
Many problems in machine learning can be cast as learning functions from sets to graphs, or more generally to hypergraphs; in short, Set2Graph functions. Examples include clusterin…
On Learning Sets of Symmetric Elements
Haggai Maron, Or Litany, Gal Chechik +1
Learning from unordered sets is a fundamental learning setup, recently attracting increasing attention. Research in this area has focused on the case where elements of the set are…
Controlling Neural Level Sets
Matan Atzmon, Niv Haim, Lior Yariv +3
The level sets of neural networks represent fundamental properties such as decision boundaries of classifiers and are used to model non-linear manifold data such as curves and surf…