This paper describes a vector space equalization scheme for a concept-based collaborative information retrieval system. Authors previously proposed a peer-to-peer information exchange system that aims at smooth knowledge and information management to activate organizations and communities. One problem with the system arises when information is retrieved from another's personal repository since the framework's retrieval criteria are strongly personalized. This paper presents a vector space quealization scheme, the automated relevance feedback scheme, that compensates the differences in the vector spaces of the personal repositories.