The 32nd International Conference on Inductive Logic Programming (ILP2023) was held in Bari, Italy, 13-15 November 2023, as a component of the 3rd International Joint Conference on Learning & Reasoning, IJCLR 2023.
Elisabetta Gentili, PhD student at the University of Ferrara as part of TAILOR partner CINI, was awarded together with other researchers with the Best Student Paper Award. The paper “Regularization in Probabilistic Inductive Logic Programming” was chosen among the long papers submitted at the conference.
Here you can find the abstract of the paper:
Probabilistic Logic Programming combines uncertainty and logic-based languages. Liftable Probabilistic Logic Programs have been recently proposed to perform inference in a lifted way. LIFTCOVER is an algorithm used to perform parameter and structure learning of liftable probabilistic logic programs. In particular, it performs parameter learning via Expectation Maximization and LBFGS.
In this paper, we present an updated version of LIFTCOVER, called LIFTCOVER+, in which regularization was added to improve the quality of the solutions and LBFGS was replaced by gradient descent. We tested LIFTCOVER+ on the same 12 datasets on which LIFTCOVER was tested and compared the performances in terms of AUC-ROC, AUC-PR, and execution times. Results show that in most cases Expectation Maximization with regularization improves the quality of the solutions.
The article will appear in the conference proceedings, which will be a part of Lecture Notes in Artificial Intelligence (LNAI) series, number 14363, edited by Elena Bellodi, Francesca Alessandra Lisi, Riccardo Zese, titled “Inductive Logic Programming.”