5 papers
Art Beyond Semantics: Sheaf-Informed Contrastive Learning for Multi-Relational Representations
Ludovica Schaerf, Antonio Purificato, Piera Riccio +2
Understanding a painting is never a single act. Art historians may analyze the same work through concepts of style, iconography, or historical context, dimensions that are not inte…
Select, Label, Evaluate: Active Testing in NLP
Antonio Purificato, Maria Sofia Bucarelli, Andrea Bacciu +2
Human annotation cost and time remain significant bottlenecks in Natural Language Processing (NLP), with test data annotation being particularly expensive due to the stringent requ…
Directional Sheaf Hypergraph Networks: Unifying Learning on Directed and Undirected Hypergraphs
Emanuele Mule, Stefano Fiorini, Antonio Purificato +3
Hypergraphs provide a natural way to represent higher-order interactions among multiple entities. While undirected hypergraphs have been extensively studied, the case of directed h…
The Majority Vote Paradigm Shift: When Popular Meets Optimal
Antonio Purificato, Maria Sofia Bucarelli, Anil Kumar Nelakanti +3
Reliably labelling data typically requires annotations from multiple human workers. However, humans are far from being perfect. Hence, it is a common practice to aggregate labels g…
One Search Fits All: Pareto-Optimal Eco-Friendly Model Selection
Filippo Betello, Antonio Purificato, Vittoria Vineis +2
The environmental impact of Artificial Intelligence (AI) is emerging as a significant global concern, particularly regarding model training. In this paper, we introduce GREEN (Guid…