PAC-Reasoning in Relational Domains
This addresses the challenge of ensuring reliability in automated reasoning systems for relational domains, though it appears incremental as it builds on existing inference methods.
The paper tackles the problem of predicting missing facts in relational data using imperfect logical rules, aiming to bound the expected number of incorrect inferences by weakening classical inference relations.
We consider the problem of predicting plausible missing facts in relational data, given a set of imperfect logical rules. In particular, our aim is to provide bounds on the (expected) number of incorrect inferences that are made in this way. Since for classical inference it is in general impossible to bound this number in a non-trivial way, we consider two inference relations that weaken, but remain close in spirit to classical inference.