Neural inductive logic programming

• Grant number: 22/02937-9
• Support Opportunities: Research Grants - Initial Project
• Start date: February 01, 2023
• End date: January 31, 2028
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Denis Deratani Mauá
• Grantee: Denis Deratani Mauá
• Host Institution: Instituto de Matemática e Estatística (IME). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Associated researchers: Renato Lui Geh
• Associated scholarship(s): 25/01335-3 - Neural Probabilistic Sentential Decision Diagrams, BP.MS; 24/15216-3 - Neurosymbolic Question Answering, BP.IC; 24/14144-9 - Parametric Learning for Tractable Probabilistic Programming, BP.IC

Abstract

Deep learning techniques have shown impressive results in low-level cognitive task such as image and speech recognition as well as in high-level cognitive tasks such as question answering and stochastic planning.Yet, developing effective deep learning solutions is notoriously challenging as they require massive amounts of data and compute (often beyond limited budgets of typical users), are very sensitive to domain shifts, and produce undesirable output that undermine end-user trust in the system. Good old-fashioned AI techniques based on knowledge representation and symbol manipulation are data efficient, generalizable, and produce mostly verifiable behavior; however they scale poorly, require costly knowledge acquisition procedures and have difficulty in coping with noise and uncertainty that are ubiquitous in real settings.Neurosymbolic approaches have recently re-emerged as a means to take the best of both approaches and deliver systems that are expressive and scalable, yet interpretable, generalizable, data efficient and trustworthy.This document describes a five-year research proposal to study the further development of neurosymbolic approaches based on logic programming, procedural probabilistic programming and combinations of both.Ultimately, this research seeks to advance the state-of-the-art of learning-based agents that go beyond the dominant view of learning as an optimization task in a continuous space guided by input-output examples.To this end, we shall extend current neursymbolic logic programming systems with more expressive constructs and more efficient learning techniques, and evaluate them in challenging cognitive tasks such as text-based question answering. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

SILVEIRA, IGOR CATANEO; BARBOSA, ANDRE; DA COSTA, DANIEL SILVA LOPES; MAUA, DENIS DERATANI. Investigating Universal Adversarial Attacks Against Transformers-Based Automatic Essay Scoring Systems. INTELLIGENT SYSTEMS, BRACIS 2024, PT II, v. 15413, p. 15-pg., 2025-01-01. (19/07665-4, 22/02937-9)

MAUA, DENIS DERATANI; COZMAN, FABIO GAGLIARDI. Specifying Credal Sets With Probabilistic Answer Set Programming. NEURIPS WORKSHOPS, 2020, v. 215, p. 12-pg., 2023-01-01. (19/07665-4, 22/02937-9)

NASCIMENTO ROCHA, VICTOR HUGO; SILVEIRA, IGOR CATANEO; PIROZELLI, PAULO; MAUA, DENIS DERATANI; COZMAN, FABIO GAGLIARDI. Assessing Good, Bad and Ugly Arguments Generated by ChatGPT: a New Dataset, its Methodology and Associated Tasks. PROGRESS IN ARTIFICIAL INTELLIGENCE, EPIA 2023, PT I, v. 14115, p. 13-pg., 2023-01-01. (19/07665-4, 22/02937-9, 19/26762-0)