385 citations · 2k across the 117 of their papers we have counts for
28 papers · 1 filter
Feasible Flow Matching for Graph Reconstruction via Within-Sampling Primal-Dual Guidance
Haoming Chen, Nicolas Zilberstein, Santiago Paternain +1
Graph reconstruction from partial observations often comes with structural side information, such as degree bounds, triangle counts, or an edge-density band. Prior-Informed Flow Ma…
Learning Normalized Energy Models for Linear Inverse Problems
Nicolas Zilberstein, Santiago Segarra, Eero Simoncelli +1
Generative diffusion models can provide powerful prior probability models for inverse problems in imaging, but existing implementations suffer from two key limitations: the p…
Prior-Informed Flow Matching for Graph Reconstruction
Harvey Chen, Nicolas Zilberstein, Santiago Segarra
We introduce \textit{Prior-Informed Flow Matching (PIFM)}, a conditional flow model for graph reconstruction. Reconstructing graphs from partial observations remains a key challeng…
Deep Unfolding: Recent Developments, Theory, and Design Guidelines
Nir Shlezinger, Santiago Segarra, Yi Zhang +4
Optimization methods play a central role in signal processing, serving as the mathematical foundation for inference, estimation, and control. While classical iterative optimization…
From Moments to Models: Graphon-Mixture Learning for Mixup and Contrastive Learning
Ali Azizpour, Reza Ramezanpour, Santiago Segarra
Real-world graph datasets often arise from mixtures of populations, where graphs are generated by multiple distinct underlying distributions. In this work, we propose a unified fra…
Adaptive Node Feature Selection For Graph Neural Networks
Madeline Navarro, Ali Azizpour, Santiago Segarra
We propose an adaptive node feature selection approach for graph neural networks (GNNs) that identifies and removes unnecessary features during training. The ability to measure how…
GraSSRep: Graph-Based Self-Supervised Learning for Repeat Detection in Metagenomic Assembly
Ali Azizpour, Advait Balaji, Todd J. Treangen +1
Repetitive DNA (repeats) poses significant challenges for accurate and efficient genome assembly and sequence alignment. This is particularly true for metagenomic data, where genom…
Recovering Missing Node Features with Local Structure-based Embeddings
Victor M. Tenorio, Madeline Navarro, Santiago Segarra +1
Node features bolster graph-based learning when exploited jointly with network structure. However, a lack of nodal attributes is prevalent in graph data. We present a framework to…
Hypergraphs with Edge-Dependent Vertex Weights: Spectral Clustering based on the 1-Laplacian
Yu Zhu, Boning Li, Santiago Segarra
We propose a flexible framework for defining the 1-Laplacian of a hypergraph that incorporates edge-dependent vertex weights. These weights are able to reflect varying importance o…
Learning to Transmit with Provable Guarantees in Wireless Federated Learning
Boning Li, Jake Perazzone, Ananthram Swami +1
We propose a novel data-driven approach to allocate transmit power for federated learning (FL) over interference-limited wireless networks. The proposed method is useful in challen…
Beyond Hawkes: Neural Multi-event Forecasting on Spatio-temporal Point Processes
Negar Erfanian, Santiago Segarra, Maarten de Hoop
Predicting discrete events in time and space has many scientific applications, such as predicting hazardous earthquakes and outbreaks of infectious diseases. History-dependent spat…
GraphMAD: Graph Mixup for Data Augmentation using Data-Driven Convex Clustering
Madeline Navarro, Santiago Segarra
We develop a novel data-driven nonlinear mixup mechanism for graph data augmentation and present different mixup functions for sample pairs and their labels. Mixup is a data augmen…
Hypergraphs with Edge-Dependent Vertex Weights: p-Laplacians and Spectral Clustering
Yu Zhu, Santiago Segarra
We study p-Laplacians and spectral clustering for a recently proposed hypergraph model that incorporates edge-dependent vertex weights (EDVW). These weights can reflect different i…
Power Allocation for Wireless Federated Learning using Graph Neural Networks
Boning Li, Ananthram Swami, Santiago Segarra
We propose a data-driven approach for power allocation in the context of federated learning (FL) over interference-limited wireless networks. The power policy is designed to maximi…
Label Propagation across Graphs: Node Classification using Graph Neural Tangent Kernels
Artun Bayer, Arindam Chowdhury, Santiago Segarra
Graph neural networks (GNNs) have achieved superior performance on node classification tasks in the last few years. Commonly, this is framed in a transductive semi-supervised learn…
Unrolling Particles: Unsupervised Learning of Sampling Distributions
Fernando Gama, Nicolas Zilberstein, Richard G. Baraniuk +1
Particle filtering is used to compute good nonlinear estimates of complex systems. It samples trajectories from a chosen distribution and computes the estimate as a weighted averag…
Robust Hierarchical Clustering for Directed Networks: An Axiomatic Approach
Gunnar Carlsson, Facundo Mémoli, Santiago Segarra
We provide a complete taxonomic characterization of robust hierarchical clustering methods for directed networks following an axiomatic approach. We begin by introducing three prac…
An Impossibility Theorem for Node Embedding
T. Mitchell Roddenberry, Yu Zhu, Santiago Segarra
With the increasing popularity of graph-based methods for dimensionality reduction and representation learning, node embedding functions have become important objects of study in t…
Free Energy Node Embedding via Generalized Skip-gram with Negative Sampling
Yu Zhu, Ananthram Swami, Santiago Segarra
A widely established set of unsupervised node embedding methods can be interpreted as consisting of two distinctive steps: i) the definition of a similarity matrix based on the gra…
GIST: Distributed Training for Large-Scale Graph Convolutional Networks
Cameron R. Wolfe, Jingkang Yang, Arindam Chowdhury +4
The graph convolutional network (GCN) is a go-to solution for machine learning on graphs, but its training is notoriously difficult to scale both in terms of graph size and the num…
Principled Simplicial Neural Networks for Trajectory Prediction
T. Mitchell Roddenberry, Nicholas Glaze, Santiago Segarra
We consider the construction of neural network architectures for data on simplicial complexes. In studying maps on the chain complex of a simplicial complex, we define three desira…
Graph-based Semi-Supervised & Active Learning for Edge Flows
Junteng Jia, Michael T. Schaub, Santiago Segarra +1
We present a graph-based semi-supervised learning (SSL) method for learning edge flows defined on a graph. Specifically, given flow measurements on a subset of edges, we want to pr…
Blind identification of stochastic block models from dynamical observations
Michael T. Schaub, Santiago Segarra, John N. Tsitsiklis
We consider a blind identification problem in which we aim to recover a statistical model of a network without knowledge of the network's edges, but based solely on nodal observati…
Excisive Hierarchical Clustering Methods for Network Data
Gunnar Carlsson, Facundo Mémoli, Alejandro Ribeiro +1
We introduce two practical properties of hierarchical clustering methods for (possibly asymmetric) network data: excisiveness and linear scale preservation. The latter enforces imp…