collaborators

5 papers

cs.HC2026

Trade-offs in Financial AI: Explainability in a Trilemma with Accuracy and Compliance

Patricia Marcella Evite, Ekaterina Svetlova, Doina Bucur

As Artificial Intelligence (AI) becomes increasingly embedded in financial decision-making, the opacity of complex models presents significant challenges for professionals and regu…

cs.LG2024

gFlora: a topology-aware method to discover functional co-response groups in soil microbial communities

Nan Chen, Merlijn Schram, Doina Bucur

We aim to learn the functional co-response group: a group of taxa whose co-response effect (the representative characteristic of the group showing the total topological abundance o…

cs.SI2024

Learning the mechanisms of network growth

Lourens Touwen, Doina Bucur, Remco van der Hofstad +2

We propose a novel model-selection method for dynamic networks. Our approach involves training a classifier on a large body of synthetic network data. The data is generated by simu…

cs.LG2024

Understanding Sparse Neural Networks from their Topology via Multipartite Graph Representations

Elia Cunegatti, Matteo Farina, Doina Bucur +1

Pruning-at-Initialization (PaI) algorithms provide Sparse Neural Networks (SNNs) which are computationally more efficient than their dense counterparts, and try to avoid performanc…

physics.soc-ph2024

Parallels in the symbolism of star constellations

Doina Bucur

We answer the question whether, when forming constellations in the night sky, people in astronomical cultures around the world and through time consistently imagined and assigned t…