Scalable summary based retrieval in P2P networks

Abstract

Much of the present P2P-IR literature is focused on distributed indexing structures. Within this paper, we present an approach based on the replication of peer data summaries via rumor spreading and multicast in a structured overlay.We will describe Rumorama, a P2P framework for similarity queries inspired by GlOSS and CORI and their P2P-adaptation, PlanetP. Rumorama achieves a hierarchization of PlanetP-like summary-based P2P-IR networks. In a Rumorama network, each peer views the network as a small PlanetP network with connections to peers that see other small PlanetP networks. One important aspect is that each peer can choose the size of the PlanetP network it wants to see according to its local processing power and bandwidth. Even in this adaptive environment, Rumorama manages to process a query such that the summary of each peer is considered exactly once in a network without churn. However, the actual number of peers to be contacted for a query is a small fraction of the total number of peers in the network.Within this article, we present the Rumorama base protocol, as well as experiments demonstrating the scalability and viability of the approach under churn.

Clustering-Based Source Selection for Efficient Image Retrieval in Peer-to-Peer Networks

“…A broad state of the art of P2P-IR is given in [8] and [7]. In this paper we are looking for an approach that permits efficient indexing of documents without expensive replication of full indexing data.…”

“…The query performance is determined by the quality of the summary and the peer selection method. Successful uses of summaries have been described for text data [4,2] and image data [7]. Within this paper we present further improvements.…”

“…One focus of research is therefore the search on stored data in a P2P network. Current research is spanning diverse areas such as efficient exact search (via distributed hash tables [11,10]), similarity search on text and multimedia data [12,7], and semantic networks expressed via RDF [9]. The topic of this paper is similarity search for Information Retrieval (IR) and in particular Content Based Image Retrieval (CBIR), a technique that allows searching images by their visual content.…”

Aspects of Adaptivity in P2P Information Retrieval

“…Obviously this scheme is not scalable as the number of peers to keep track of grows O(N ). We have presented a scalable version of PlanetP, Rumorama [16] whose properties will be discussed below but whose details are out of scope here.…”

“…For a couple of years, the focus lay on exact search in P2P networks, however, there is a growing interest in similarity search, i.e. information retrieval (IR) in P2P networks [25,18,16].…”