Conditional Synchronization in Multi-Agent Graph-based Knowledge System

摘要

Graph transformations provide a well established method for the formal description of modifications of graph-based systems. On the other side such systems can be regarded as multi-agent ones providing a feasible mean for maintaining and manipulating large scale data. This paper deals with the problem of information exchange among agents maintaining different graph-based systems. Graph formalism applied for representing a knowledge maintained by agents is used at the same time to perform graph transformations modeling a knowledge exchange. The consistency of knowledge represented by set of agents is ensured by execution of some graph transformations rules by two agents in a parallel way. We sugest that complex operations (sequences of graph transformations) should be introduced instead of the formalism basing on simple unconditional operations. The approach presented in this paper is accompanied by examples concerning the problem of personal data distributed over different places (and maintained by different agents) and transmitted in such an environment~1.