PAC-reasoning in relational domains
arXiv preprint arXiv:1803.05768, 2018•arxiv.org
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.
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.
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.
arxiv.org