On the exact learnability of graph parameters: the case of partition functions
From MaRDI portal
Abstract: We study the exact learnability of real valued graph parameters which are known to be representable as partition functions which count the number of weighted homomorphisms into a graph with vertex weights and edge weights . M. Freedman, L. Lov'asz and A. Schrijver have given a characterization of these graph parameters in terms of the -connection matrices of . Our model of learnability is based on D. Angluin's model of exact learning using membership and equivalence queries. Given such a graph parameter , the learner can ask for the values of for graphs of their choice, and they can formulate hypotheses in terms of the connection matrices of . The teacher can accept the hypothesis as correct, or provide a counterexample consisting of a graph. Our main result shows that in this scenario, a very large class of partition functions, the rigid partition functions, can be learned in time polynomial in the size of and the size of the largest counterexample in the Blum-Shub-Smale model of computation over the reals with unit cost.
Recommendations
This page was built for publication: On the exact learnability of graph parameters: the case of partition functions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4608626)