Characterization of Inclusion Neighbourhood in Terms of the Essential Graph: Uper Neighbours
نویسنده
چکیده
The topic of the contribution is to characterize the inclusion neighbourhood of a given equivalence class of Bayesian networks in terms of the respective essential graph in such a way that it can be used eeciently in a method of local search for maximization of a quality criterion. One can distinguish two kinds of inclusion neighbours: upper and lower ones. A previous paper 15] gave a characterization of upper inclusion neighbourhood , and this contribution gives a characterization of lower inclusion neighbourhood. It is shown here that each inclusion neighbour is uniquely described by a pair ((a; b]; C) where a; b] is an unordered pair of distinct nodes and C N n fa; bg a disjoint set of nodes in the essential graph. The second basic result is that, for given a; b], the collection of those sets C which correspond to lower inclusion neighbours has a special form. More speciically, given an unordered pair a; b] of nodes which is not an edge in the essential graph, the respective collection of sets C is the union of (at most) two tufts of sets. The least and maximal sets of these two tufts, which determine them, can also be read from the essential graph. Some of the approaches to learning Bayesian networks use the method of max-imization of a quality criterion, named also 'quality measure' 3] and 'score metric' 4]. Quality criterion is a function, designed by a statistician, which ascribes a real number to data and a network. This number evaluates how the statistical model determined by the network is suitable to explain the occurence
منابع مشابه
Characterization of inclusion neighbourhood in terms of the essential graph
The question of efficient characterization of inclusion neighbourhood is crucial in some methods for learning (equivalence classes of) Bayesian networks. In this paper, neighbouring equivalence classes of a given equivalence class of Bayesian networks are characterized efficiently in terms of the respective essential graph. One can distinguish two kinds of inclusion neighbours: upper and lower ...
متن کامل2 Characterization of inclusion neighbourhood 3 in terms of the essential graph q 4
10 The question of efficient characterization of inclusion neighbourhood is crucial in some 11 methods for learning (equivalence classes of) Bayesian networks. In this paper, neighbouring 12 equivalence classes of a given equivalence class of Bayesian networks are characterized effi13 ciently in terms of the respective essential graph. One can distinguish two kinds of inclusion 14 neighbours: u...
متن کاملCharacterization of Inclusion Neighbourhood in Terms of the Essential Graph: Upper Neighbours ? 1 Motivation 1.1 Learning Bayesian Networks
The problem of eecient characterization of inclusion neighbourhood is crucial for some methods of learning (equivalence classes of) Bayesian networks. In this paper, neighbouring equivalence classes of a given equivalence class of Bayesian networks are characterized eeciently by means of the respective essential graph. The characterization reveals hidded internal structure of the inclusion neig...
متن کاملThe Neighbourhood Polynomial of some Nanostructures
The neighbourhood polynomial G , is generating function for the number of faces of each cardinality in the neighbourhood complex of a graph. In other word $N(G,x)=sum_{Uin N(G)} x^{|U|}$, where N(G) is neighbourhood complex of a graph, whose vertices are the vertices of the graph and faces are subsets of vertices that have a common neighbour. In this paper we compute this polynomial for some na...
متن کاملA Magnetic Procedure for the Stability Number
A magnet is a pair u, v of adjacent vertices such that the proper neighbours of u are completely linked to the proper neighbours of v. It has been shown that one can reduce the graph by removing one of the vertices of a magnet together with all edges linking the other one to its proper neighbours without changing the stability number. We characterize a class of graphs such that by repeated use ...
متن کامل