12 papers
Fair Feature Importance Scores via Feature Occlusion and Permutation
Camille Little, Madeline Navarro, Santiago Segarra +1
As machine learning models increasingly impact society, their opaque nature poses challenges to trust and accountability, particularly in fairness contexts. Understanding how indiv…
Stationarity and Spectral Characterization of Random Signals on Simplicial Complexes
Madeline Navarro, Andrei Buciulea, Santiago Segarra +1
It is increasingly common for data to possess intricate structure, necessitating new models and analytical tools. Graphs, a prominent type of structure, can encode the relationship…
Learning Time-Varying Turn-Taking Behavior in Group Conversations
Madeline Navarro, Lisa O'Bryan, Santiago Segarra
We propose a flexible probabilistic model for predicting turn-taking patterns in group conversations based solely on individual characteristics and past speaking behavior. Many mod…
Estimating Fair Graphs from Graph-Stationary Data
Madeline Navarro, Andrei Buciulea, Samuel Rey +2
We estimate fair graphs from graph-stationary nodal observations such that connections are not biased with respect to sensitive attributes. Edges in real-world graphs often exhibit…
Adaptive Graph Coarsening for Efficient GNN Training
Rostyslav Olshevskyi, Madeline Navarro, Santiago Segarra
We propose an adaptive graph coarsening method to jointly learn graph neural network (GNN) parameters and merge nodes via K-means clustering during training. As real-world graphs g…
Adapting to Heterophilic Graph Data with Structure-Guided Neighbor Discovery
Victor M. Tenorio, Madeline Navarro, Samuel Rey +2
Graph Neural Networks (GNNs) often struggle with heterophilic data, where connected nodes may have dissimilar labels, as they typically assume homophily and rely on local message p…
Structure-Guided Input Graph for GNNs facing Heterophily
Victor M. Tenorio, Madeline Navarro, Samuel Rey +2
Graph Neural Networks (GNNs) have emerged as a promising tool to handle data exhibiting an irregular structure. However, most GNN architectures perform well on homophilic datasets,…
ML-SPEAK: A Theory-Guided Machine Learning Method for Studying and Predicting Conversational Turn-taking Patterns
Lisa R. O'Bryan, Madeline Navarro, Juan Segundo Hevia +1
Predicting team dynamics from personality traits remains a fundamental challenge for the psychological sciences and team-based organizations. Understanding how team composition gen…
Low-Rank Tensors for Multi-Dimensional Markov Models
Madeline Navarro, Sergio Rozada, Antonio G. Marques +1
This work presents a low-rank tensor model for multi-dimensional Markov chains. A common approach to simplify the dynamical behavior of a Markov chain is to impose low-rankness on…
Online Network Inference from Graph-Stationary Signals with Hidden Nodes
Andrei Buciulea, Madeline Navarro, Samuel Rey +2
Graph learning is the fundamental task of estimating unknown graph connectivity from available data. Typical approaches assume that not only is all information available simultaneo…
Redesigning graph filter-based GNNs to relax the homophily assumption
Samuel Rey, Madeline Navarro, Victor M. Tenorio +2
Graph neural networks (GNNs) have become a workhorse approach for learning from data defined over irregular domains, typically by implicitly assuming that the data structure is rep…
Fair CoVariance Neural Networks
Andrea Cavallo, Madeline Navarro, Santiago Segarra +1
Covariance-based data processing is widespread across signal processing and machine learning applications due to its ability to model data interconnectivities and dependencies. How…