Meta-Interpretive Learning as Metarule Specialisation
This work addresses the need for automated inductive bias specification in MIL, reducing manual effort for researchers and practitioners in machine learning, though it is incremental as it builds on existing MIL frameworks.
The paper tackles the problem of manually defining metarules in Meta-Interpretive Learning (MIL) by showing that second-order metarules can be learned automatically through MIL itself, using a new operator called TOIL. The result is that automatically derived metarules maintain predictive accuracy and training times, as demonstrated in experiments with the Louise system.
In Meta-Interpretive Learning (MIL) the metarules, second-order datalog clauses acting as inductive bias, are manually defined by the user. In this work we show that second-order metarules for MIL can be learned by MIL. We define a generality ordering of metarules by $θ$-subsumption and show that user-defined \emph{sort metarules} are derivable by specialisation of the most-general \emph{matrix metarules} in a language class; and that these matrix metarules are in turn derivable by specialisation of third-order \emph{punch metarules} with variables quantified over the set of atoms and for which only an upper bound on their number of literals need be user-defined. We show that the cardinality of a metarule language is polynomial in the number of literals in punch metarules. We re-frame MIL as metarule specialisation by resolution. We modify the MIL metarule specialisation operator to return new metarules rather than first-order clauses and prove the correctness of the new operator. We implement the new operator as TOIL, a sub-system of the MIL system Louise. Our experiments show that as user-defined sort metarules are progressively replaced by sort metarules learned by TOIL, Louise's predictive accuracy and training times are maintained. We conclude that automatically derived metarules can replace user-defined metarules.