Satisfiability modulo theory meets inductive logic programming

Nijesh Upreti; Vaishak Belle

Satisfiability modulo theory meets inductive logic programming

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Inductive Logic Programming (ILP) is a powerful framework that bridges logic programming and machine learning. Despite its strengths, traditional ILP systems are generally limited to reasoning over discrete-valued predicates, often expressed through Horn clauses. This paper explores an enhanced approach to ILP by leveraging Satisfiability Modulo Theories (SMT), which offers richer representational capabilities, especially for continuous and hybrid domains. We propose a more expressive foundation for inductive declarative programming and outline how SMT solvers can extend ILP's reach.

Original language	English
Title of host publication	Proceedings of the 5th International Joint Conference on Learning & Reasoning
Publisher	Springer
Pages	1-20
Number of pages	20
Publication status	Accepted/In press - 11 Aug 2025
Event	5th International Joint Conference on Learning & Reasoning - Guilford, United Kingdom Duration: 11 Sept 2025 → 14 Sept 2025 Conference number: 5 https://ijclr2025.pages.surrey.ac.uk/index.html

Publication series

Name	Lecture Notes in Artificial Intelligence
Publisher	Springer
ISSN (Print)	2945-9133
ISSN (Electronic)	2945-9141

Conference

Conference	5th International Joint Conference on Learning & Reasoning
Country/Territory	United Kingdom
City	Guilford
Period	11/09/25 → 14/09/25
Internet address	https://ijclr2025.pages.surrey.ac.uk/index.html

Keywords / Materials (for Non-textual outputs)

inductive logic programming
satisfiability modulo theories
hybrid reasoning
declarative programming
continuous and discrete variables
constraint logic programming

Access to Document

UpretiBelleIJCLR2025SatisfiabilityModuloTheoryAccepted author manuscript, 486 KBLicence: Creative Commons: Attribution (CC-BY)

https://arxiv.org/abs/2512.12918Licence: Creative Commons: Attribution (CC-BY)

Cite this

@inproceedings{0acc120046c848c18ac890fc70fa21eb,

title = "Satisfiability modulo theory meets inductive logic programming",

abstract = "Inductive Logic Programming (ILP) is a powerful framework that bridges logic programming and machine learning. Despite its strengths, traditional ILP systems are generally limited to reasoning over discrete-valued predicates, often expressed through Horn clauses. This paper explores an enhanced approach to ILP by leveraging Satisfiability Modulo Theories (SMT), which offers richer representational capabilities, especially for continuous and hybrid domains. We propose a more expressive foundation for inductive declarative programming and outline how SMT solvers can extend ILP's reach.",

keywords = "inductive logic programming, satisfiability modulo theories, hybrid reasoning, declarative programming, continuous and discrete variables, constraint logic programming",

author = "Nijesh Upreti and Vaishak Belle",

year = "2025",

month = aug,

day = "11",

language = "English",

series = "Lecture Notes in Artificial Intelligence",

publisher = "Springer",

pages = "1--20",

booktitle = "Proceedings of the 5th International Joint Conference on Learning \& Reasoning",

address = "United Kingdom",

note = "5th International Joint Conference on Learning \& Reasoning ; Conference date: 11-09-2025 Through 14-09-2025",

url = "https://ijclr2025.pages.surrey.ac.uk/index.html",

}

TY - GEN

T1 - Satisfiability modulo theory meets inductive logic programming

AU - Upreti, Nijesh

AU - Belle, Vaishak

N1 - Conference code: 5

PY - 2025/8/11

Y1 - 2025/8/11

N2 - Inductive Logic Programming (ILP) is a powerful framework that bridges logic programming and machine learning. Despite its strengths, traditional ILP systems are generally limited to reasoning over discrete-valued predicates, often expressed through Horn clauses. This paper explores an enhanced approach to ILP by leveraging Satisfiability Modulo Theories (SMT), which offers richer representational capabilities, especially for continuous and hybrid domains. We propose a more expressive foundation for inductive declarative programming and outline how SMT solvers can extend ILP's reach.

AB - Inductive Logic Programming (ILP) is a powerful framework that bridges logic programming and machine learning. Despite its strengths, traditional ILP systems are generally limited to reasoning over discrete-valued predicates, often expressed through Horn clauses. This paper explores an enhanced approach to ILP by leveraging Satisfiability Modulo Theories (SMT), which offers richer representational capabilities, especially for continuous and hybrid domains. We propose a more expressive foundation for inductive declarative programming and outline how SMT solvers can extend ILP's reach.

KW - inductive logic programming

KW - satisfiability modulo theories

KW - hybrid reasoning

KW - declarative programming

KW - continuous and discrete variables

KW - constraint logic programming

M3 - Conference contribution

T3 - Lecture Notes in Artificial Intelligence

SP - 1

EP - 20

BT - Proceedings of the 5th International Joint Conference on Learning & Reasoning

PB - Springer

T2 - 5th International Joint Conference on Learning & Reasoning

Y2 - 11 September 2025 through 14 September 2025

ER -

Satisfiability modulo theory meets inductive logic programming

Abstract

Publication series

Conference

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Cite this