11 papers
Size Transferability of Graph Transformers with Convolutional Positional Encodings
Javier Porras-Valenzuela, Zhiyang Wang, Xiaotao Shang +2
Transformers have achieved remarkable success across domains, motivating the rise of Graph Transformers (GTs) as attention-based architectures for graph-structured data. A key desi…
RKHS Representation of Algebraic Convolutional Filters with Integral Operators
Alejandro Parada-Mayorga, Alejandro Ribeiro, Juan Bazerque
Integral operators play a central role in signal processing, underpinning classical convolution, and filtering on continuous network models such as graphons. While these operators…
Learning Policy Representations for Steerable Behavior Synthesis
Beiming Li, Sergio Rozada, Alejandro Ribeiro
Given a Markov decision process (MDP), we seek to learn representations for a range of policies to facilitate behavior steering at test time. As policies of an MDP are uniquely det…
Decentralized Learning Strategies for Estimation Error Minimization with Graph Neural Networks
Xingran Chen, Navid NaderiAlizadeh, Alejandro Ribeiro +1
We address real-time sampling and estimation of autoregressive Markovian sources in dynamic yet structurally similar multi-hop wireless networks. Each node caches samples from othe…
Transferable Graphical MARL for Real-Time Estimation in Dynamic Wireless Networks
Xingran Chen, Navid NaderiAlizadeh, Alejandro Ribeiro +1
We study real-time sampling and estimation of autoregressive Markovian sources in decentralized and dynamic multi-hop networks that share similar structures. Nodes cache neighborin…
Learning Optimal Power Flow with Pointwise Constraints
Damian Owerko, Anna Scaglione, Alejandro Ribeiro
Training learning parameterizations to solve optimal power flow (OPF) with pointwise constraints is proposed. In this novel training approach, a learning parameterization is substi…