{"type":"ScholarlyArticle","title":"Grounding Methods for Neural-Symbolic AI","authors":[{"name":"Rodrigo Castellano Ontiveros","slug":"rodrigo-castellano-ontiveros","given":"Rodrigo","family":"Castellano Ontiveros","affiliation":""},{"name":"Francesco Giannini","slug":"francesco-giannini","given":"Francesco","family":"Giannini","affiliation":""},{"name":"Marco Gori","slug":"marco-gori","given":"Marco","family":"Gori","affiliation":""},{"name":"Giuseppe Marra","slug":"giuseppe-marra","given":"Giuseppe","family":"Marra","affiliation":""},{"name":"Michelangelo Diligenti","slug":"michelangelo-diligenti","given":"Michelangelo","family":"Diligenti","affiliation":""}],"abstract":"A large class of Neural-Symbolic (NeSy) methods employs a machine learner to process the input entities, while relying on a reasoner based on First-Order Logic to represent and process more complex relationships among the entities. A fundamental role for these methods is played by the process of logic grounding, which determines the relevant substitutions for the logic rules using a (sub)set of entities.\r\nSome NeSy methods use an exhaustive derivation of all possible substitutions, preserving the full expressive power of the logic knowledge, but leading to a combinatorial explosion of the number of ground formulas to consider and, therefore, strongly limiting their scalability. Other methods rely on heuristic-based selective derivations, which are generally more computationally efficient, but lack a justification and provide no guarantees of preserving the information provided to and returned by the reasoner. \r\nTaking inspiration from multi-hop symbolic reasoning, this paper proposes a parametrized family of grounding methods generalizing classic Backward Chaining. Different selections within this family allow to obtain commonly employed grounding methods as special cases, and to control the trade-off between expressiveness and scalability of the reasoner.\r\nThe experimental results show that the selection of the grounding criterion is often as important as the NeSy method itself.","doi":"10.24963/ijcai.2025/535","url":"https://ijcai.org/proceedings/2025/535","pdf":"https://ijcai.org/proceedings/2025/0535.pdf","markdown":"https://ijcai.org/proceedings/2025/535.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/535","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Machine Learning","track":"Main Track","number":535,"pages":{"first":4806,"last":4814},"keywords":["Machine Learning: ML: Neuro-symbolic methods/Abductive Learning","Knowledge Representation and Reasoning: KRR: Learning and reasoning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}