this paper was supported in part by the National Competence Center in Research on Mobile Information and Communication Systems (NCCR-MICS), a center supported by the Swiss National Science Foundation under grant number 5005-67322 and by SNSF grant 2100064994, "Peer-to-Peer Information Systems." messages. From the responses it (randomly) selects certain peers to which direct network links are established

In peer-to-peer data integration, each peer exports data in terms of its own schema, and data interoperation is achieved by means of mappings among the peer schemas. Peers are autonomous systems and mappings are dynamically created and changed. One of the challenges in these systems is answering queries posed to one peer taking into account the mappings. Obviously, query answering strongly depends on the semantics of the overall system. In this paper, we compare the commonly adopted approach of interpreting peerto-peer systems using a first-order semantics, with an alternative approach based on epistemic logic. We consider several central properties of peer-to-peer systems: modularity, generality, and decidability. We argue that the approach based on epistemic logic is superior with respect to all the above properties. In particular, we show that, in systems in which peers have decidable schemas and conjunctive mappings, but are arbitrarily interconnected, the first-order approach may lead to undecidability of query answering, while the epistemic approach always preserves decidability. This is a fundamental property, since the actual interconnections among peers are not under the control of any actor in the system. 1.

This paper studies the problem of updates in decentralised and self-organising P2P systems in which peers have low online probabilities and only local knowledge. The update strategy we propose for this environment is based on a hybrid push/pull rumor spreading algorithm and provides a fully decentralised, efficient and robust communication scheme which offers probabilistic guarantees rather than ensuring strict consistency. We describe a generic analytical model to investigate the utility of our hybrid update propagation scheme from the perspective of communication overhead.

Collection selection has been a research issue for years. Typically, in related work, precomputed statistics are employed in order to estimate the expected result quality of each collection, and subsequently the collections are ranked accordingly. Our thesis is that this simple approach is insufficient for several applications in which the collections typically overlap. This is the case, for example, for the collections built by autonomous peers crawling the web. We argue for the extension of existing quality measures using estimators of mutual overlap among collections and present experiments in which this combination outperforms CORI, a popular approach based on quality estimation. We outline our prototype implementation of a P2P web search engine, coined MINERVA 1, that allows handling large amounts of data in a distributed and self-organizing manner. We conduct experiments which show that taking overlap into account during collection selection can drastically decrease the number of collections that have to be contacted in order to reach a satisfactory level of recall, which is a great step toward the feasibility of distributed web search.

Building distributed content--based publish/subscribe systems has remained a challenge. Existing solutions typically use a relatively small set of trusted computers as brokers, which may lead to scalability concerns for large Internet--scale workloads. Moreover, since each broker maintains state for a large number of users, it may be di#cult to tolerate faults at each broker. In this paper we propose an approach to building content--based publish/subscribe systems on top of distributed hash table (DHT) systems. DHT systems have been e#ectively used for scalable and fault--tolerant resource lookup in large peer--to--peer networks.

Abstract. In this paper, we study the problem of data integration in P2P systems. Differently from the traditional setting, data integration in these systems is not based on the existence of a global view. Instead, each peer exports data in terms of its own schema, and information integration is achieved by establishing mappings among the various peer schemas. We present a framework that captures this general architecture, and then we discuss the problem of characterizing the semantics of such framework. We show that the usual approach of resorting to a first-order logic intepretation of P2P mappings, leads both to a poor modeling of the whole system, and to undecidability of query answering, even for mappings of a restricted form. This motivates the need of a new semantics for P2P system. We then present a novel proposal, based on epistemic logic, and show that not only it adequately models the interactions among peers, but it also supports decidable query answering. In particular, for the restricted form of mapping mentioned above, query answering is polynomial with respect to the size of data stored in the peers. 1

this paper shows that unbalanced trees do not harm as long as communication is considered as the critical cost and the access structures are constructed properly. Besides proving this result we propose the necessary distributed, randomized algorithms that allow to construct the P-Grid in a self-organized manner such that the tree structure dynamically adapts to the data distribution and the aforementioned result is applicable

Structured peer-to-peer (P2P) systems are considered as the next generation application backbone on the Internet. An important problem of these systems is load balancing in the presence of non-uniform data distributions. In this paper we propose a completely decentralized mechanism that in parallel addresses a local and a global load balancing problem: (1) balancing the storage load uniformly among peers participating in the network and (2) uniformly replicating different data items in the network while optimally exploiting existing storage capacity. Our approach is based on the P-Grid P2P system which is our variant of a structured P2P network. Problem (1) is solved by directly adapting the search structure to the data distribution. This may result in an unbalanced search structure, but we will show that the expected search cost in P-Grid in number of messages remains logarithmic under all circumstances.

Abstract: We consider the problem of collaborative Web search and query routing strategies in a peer-to-peer (P2P) environment. In our architecture every peer has a full-fledged search engine with a (thematically focused) crawler and a local index whose contents may be tailored to the user’s specific interest profile. Peers are autonomous and post meta-information about their bookmarks and index lists to a global directory, which is efficiently implemented in a decentralized manner using Chordstyle distributed hash tables. A query posed by one peer is first evaluated locally; if the result is unsatisfactory the query is forwarded to selected peers. These peers are chosen based on a benefit/cost measure where benefit reflects the thematic similarity of peers ’ interest profiles, derived from bookmarks, and cost captures estimated peer load and response time. The meta-information that is needed for making these query routing decisions is efficiently looked up in the global directory; it can also be cached and proactively disseminated for higher availability and reduced network load. 1

Decentralized peer-to-peer (P2P) applications are characterized by the absence of a central authority or infrastructure that coordinates the behavior of entities in the system. These entities, called peers, interact directly with each other and make local autonomous decisions in order to achieve their individual goals. In the absence of a single authority that maintains all the data and handles all the queries, peers themselves are responsible for seeking, storing, and sharing information efficiently. Placing a large amount of information on every peer or broadcasting a request to every peer greatly reduces the performance and efficiency of the system. Hence, it is essential that decentralized applications employ efficient storage mechanisms and reliable search mechanisms. Further, an open decentralized system that does not regulate the joining of peers can be subject to grave risks. In particular, malicious peers may be encouraged to resort to a variety of attacks, including sending spurious information, posing as other peers, etc. It is important for each peer in the system to defend against such attacks. This survey discusses these two essential issues that characterize P2P decentralized applications: storage and discovery mechanisms, and trust management. It identifies and defines key properties for each of these and also summarizes the efforts of the P2P community in addressing these properties by categorizing and discussing relevant technologies and approaches.