The rise of Artificial Intelligence (AI) recently empowered researchers to investigate hard mathematical problems which eluded traditional approaches for decades. Yet, the use of AI in Universal Algebra (UA)-one of the fields laying the foundations of modern mathematics-is still completely unexplored. This work proposes the first use of AI to investigate UA's conjectures with an equivalent equational and topological characterization. While topological representations would enable the analysis of such properties using graph neural networks, the limited transparency and brittle explainability of these models hinder their straightforward use to empirically validate existing conjectures or to formulate new ones. To bridge these gaps, we propose a general algorithm generating AI-ready datasets based on UA's conjectures, and introduce a novel neural layer to build fully interpretable graph networks. The results of our experiments demonstrate that interpretable graph networks: (i) enhance interpretability without sacrificing task accuracy, (ii) strongly generalize when predicting universal algebra's properties, (iii) generate simple explanations that empirically validate existing conjectures, and (iv) identify subgraphs suggesting the formulation of novel conjectures.

Interpretable Graph Networks Formulate Universal Algebra Conjectures / Giannini, F.; Fioravanti, S.; Keskin, O.; Lupidi, A. M.; Magister, L. C.; Lio, P.; Barbiero, P.. - 36:(2023). (Intervento presentato al convegno 37th Conference on Neural Information Processing Systems, NeurIPS 2023 tenutosi a Ernest N. Morial Convention Center, usa).

Interpretable Graph Networks Formulate Universal Algebra Conjectures

Lio P.;
2023

Abstract

The rise of Artificial Intelligence (AI) recently empowered researchers to investigate hard mathematical problems which eluded traditional approaches for decades. Yet, the use of AI in Universal Algebra (UA)-one of the fields laying the foundations of modern mathematics-is still completely unexplored. This work proposes the first use of AI to investigate UA's conjectures with an equivalent equational and topological characterization. While topological representations would enable the analysis of such properties using graph neural networks, the limited transparency and brittle explainability of these models hinder their straightforward use to empirically validate existing conjectures or to formulate new ones. To bridge these gaps, we propose a general algorithm generating AI-ready datasets based on UA's conjectures, and introduce a novel neural layer to build fully interpretable graph networks. The results of our experiments demonstrate that interpretable graph networks: (i) enhance interpretability without sacrificing task accuracy, (ii) strongly generalize when predicting universal algebra's properties, (iii) generate simple explanations that empirically validate existing conjectures, and (iv) identify subgraphs suggesting the formulation of novel conjectures.
2023
37th Conference on Neural Information Processing Systems, NeurIPS 2023
Algebra; Multilayer neural networks; Topology
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Interpretable Graph Networks Formulate Universal Algebra Conjectures / Giannini, F.; Fioravanti, S.; Keskin, O.; Lupidi, A. M.; Magister, L. C.; Lio, P.; Barbiero, P.. - 36:(2023). (Intervento presentato al convegno 37th Conference on Neural Information Processing Systems, NeurIPS 2023 tenutosi a Ernest N. Morial Convention Center, usa).
File allegati a questo prodotto
File Dimensione Formato  
Giannini_Interpretable_2023.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 910.38 kB
Formato Adobe PDF
910.38 kB Adobe PDF   Contatta l'autore

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1725229
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact