Zobrazeno 1 - 10
of 1 540
pro vyhledávání: '"Levie, P"'
We analyze the universality and generalization of graph neural networks (GNNs) on attributed graphs, i.e., with node attributes. To this end, we propose pseudometrics over the space of all attributed graphs that describe the fine-grained expressivity
Externí odkaz:
http://arxiv.org/abs/2411.05464
Autor:
Zilberg, Daniel, Levie, Ron
We propose PieClam (Prior Inclusive Exclusive Cluster Affiliation Model): a probabilistic graph model for representing any graph as overlapping generalized communities. Our method can be interpreted as a graph autoencoder: nodes are embedded into a c
Externí odkaz:
http://arxiv.org/abs/2409.11618
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 generalization. In this paper, we focus on an extension of shift equiva
Externí odkaz:
http://arxiv.org/abs/2406.01249
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 the node's neighbors, which necessitates a memory complexity of the ord
Externí odkaz:
http://arxiv.org/abs/2405.20724
We study the generalization capabilities of Message Passing Neural Networks (MPNNs), a prevalent class of Graph Neural Networks (GNN). We derive generalization bounds specifically for MPNNs with normalized sum aggregation and mean aggregation. Our an
Externí odkaz:
http://arxiv.org/abs/2404.03473
Autor:
Morris, Christopher, Frasca, Fabrizio, Dym, Nadav, Maron, Haggai, Ceylan, İsmail İlkan, Levie, Ron, Lim, Derek, Bronstein, Michael, Grohe, Martin, Jegelka, Stefanie
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 disciplines, from life to social and engineering sciences. Despite their pra
Externí odkaz:
http://arxiv.org/abs/2402.02287
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 Prediction Challenge. In this short overview paper, we briefly describe the pa
Externí odkaz:
http://arxiv.org/abs/2310.07658
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 translation equivariance of Euclidean convolution neural networks (CNNs)
Externí odkaz:
http://arxiv.org/abs/2308.10436
Numerous recent works have analyzed the expressive power of message-passing graph neural networks (MPNNs), primarily utilizing combinatorial techniques such as the $1$-dimensional Weisfeiler-Leman test ($1$-WL) for the graph isomorphism problem. Howe
Externí odkaz:
http://arxiv.org/abs/2306.03698
Autor:
Levie, Ron
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 function that takes a graph and a signal on the graph (a graph-signal) an
Externí odkaz:
http://arxiv.org/abs/2305.15987