Expressive power of invariant and equivariant graph neural networks
Various classes of Graph Neural Networks (GNN) have been proposed and shown to be
successful in a wide range of applications with graph structured data. In this paper, we …
successful in a wide range of applications with graph structured data. In this paper, we …
Settling the sharp reconstruction thresholds of random graph matching
This paper studies the problem of recovering the hidden vertex correspondence between
two edge-correlated random graphs. We focus on the Gaussian model where the two graphs …
two edge-correlated random graphs. We focus on the Gaussian model where the two graphs …
Revised note on learning quadratic assignment with graph neural networks
Inverse problems correspond to a certain type of optimization problems formulated over
appropriate input distributions. Recently, there has been a growing interest in understanding …
appropriate input distributions. Recently, there has been a growing interest in understanding …
[PDF][PDF] A note on learning algorithms for quadratic assignment with graph neural networks
Many inverse problems are formulated as optimization problems over certain appropriate
input distributions. Recently, there has been a growing interest in understanding the …
input distributions. Recently, there has been a growing interest in understanding the …
Exact matching of random graphs with constant correlation
C Mao, M Rudelson, K Tikhomirov - Probability Theory and Related Fields, 2023 - Springer
This paper deals with the problem of graph matching or network alignment for Erdős–Rényi
graphs, which can be viewed as a noisy average-case version of the graph isomorphism …
graphs, which can be viewed as a noisy average-case version of the graph isomorphism …
Matching recovery threshold for correlated random graphs
Matching recovery threshold for correlated random graphs Page 1 The Annals of Statistics
2023, Vol. 51, No. 4, 1718–1743 https://doi.org/10.1214/23-AOS2305 © Institute of …
2023, Vol. 51, No. 4, 1718–1743 https://doi.org/10.1214/23-AOS2305 © Institute of …
Seeded graph matching via large neighborhood statistics
We study a noisy graph isomorphism problem, where the goal is to perfectly recover the
vertex correspondence between two edge‐correlated graphs, with an initial seed set of …
vertex correspondence between two edge‐correlated graphs, with an initial seed set of …
The algorithmic phase transition of random graph alignment problem
H Du, S Gong, R Huang - arXiv preprint arXiv:2307.06590, 2023 - arxiv.org
We study the graph alignment problem over two independent Erd\H {o} sR\'enyi graphs on $
n $ vertices, with edge density $ p $ falling into two regimes separated by the critical window …
n $ vertices, with edge density $ p $ falling into two regimes separated by the critical window …
Deep adversarial network alignment
Network alignment, in general, seeks to discover the hidden underlying correspondence
between nodes across two (or more) networks when given their network structure. However …
between nodes across two (or more) networks when given their network structure. However …
Impossibility of partial recovery in the graph alignment problem
L Ganassali, L Massoulié… - Conference on Learning …, 2021 - proceedings.mlr.press
Random graph alignment refers to recovering the underlying vertex correspondence
between two random graphs with correlated edges. This can be viewed as an average-case …
between two random graphs with correlated edges. This can be viewed as an average-case …