Adlib: A Self-Tuning Index for Dynamic Peer-to-Peer Systems

Ganesan, Prasanna; Sun, Qixiang; García-Molina, Héctor

doi:10.1109/icde.2005.19

Cited by 13 publications

(12 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each peer stores and maintains inverted indices matched with the documents that it is responsible for. On the other hand, the partition by keyword approach [22,[40][41][42] divides an inverted index on the basis of a keyword. The keywords that appear in the documents are divided among peers.…”

Section: Index Partitionmentioning

confidence: 99%

“…In the local index, each peer has a local view. It maintains a local inverted index of the contents it stores [40][41] . On the other hand, the global index keeps the complete inverted list of the contents stored on neighbors or whole peers.…”

Section: Index Organizationmentioning

confidence: 99%

“…The partition by document approach [22,[40][41][42] divides an inverted index on the basis of a document. The documents (or files) are divided among peers.…”

Section: Index Partitionmentioning

confidence: 99%

See 2 more Smart Citations

Tree-Based Index Overlay in Hybrid Peer-to-Peer Systems

Kang

Choi

Jung

et al. 2010

J. Comput. Sci. Technol.

View full text Add to dashboard Cite

Hybrid Peer-to-Peer (P2P) systems that construct overlay networks structured among superpeers have great potential in that they can give the benefits such as scalability, search speed and network traffic, taking advantages of superpeer-based and the structured P2P systems. In this article, we enhance keyword search in hybrid P2P systems by constructing a tree-based index overlay among directory nodes that maintain indices, according to the load and popularity of a keyword. The mathematical analysis shows that the keyword search based on semi-structured P2P overlay can improve the search performance, reducing the message traffic and maintenance costs.

show abstract

Section: Index Partitionmentioning

confidence: 99%

Section: Index Organizationmentioning

confidence: 99%

See 1 more Smart Citation

Tree-Based Index Overlay in Hybrid Peer-to-Peer Systems

Kang

Choi

Jung

et al. 2010

J. Comput. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Even with this simplification already good performance benefits can be obtained, but again at the price of index incompleteness. The Adlib approach [8] establishes a two-tier structure, where a first tier divides the documents into independent, equal-sized partitions, so-called domains. Within each domain, nodes build a distributed index over the content stored which then is offered in the second tier for querying.…”

Section: Related Workmentioning

confidence: 99%

DHTs over Peer Clusters for Distributed Information Retrieval

Papapetrou

Siberski

Balke

et al. 2007

21st International Conference on Advanced Networking and Applications (AINA '07)

View full text Add to dashboard Cite

Distributed Hash Tables (DHTs) are very efficient for querying based on key lookups, if only a small number of keys has to be registered by each individual peer. However, building huge term indexes, as required for IR-style keyword search, are impractical with plain DHTs. Due to the large sizes of document term vocabularies, joining peers cause huge amounts of key inserts, and subsequently large numbers of index maintenance messages. Thus, the key to exploiting DHTs for distributed information retrieval is to reduce index maintenance. We show that this can be achieved by combining DHTs with peer clustering. Peers are first clustered into communities, each of the communities having a representative super-peer. Then all occurrences of a term in a community are published to the global DHT in a batch by the representative super-peer. Our evaluation shows that this reduces index maintenance cost by an order of magnitude, while still keeping a complete and correct term index for query processing.

show abstract

“…The Adlib approach [32] follows a different direction for reducing network cost. It establishes a two-tier structure, where a first tier divides the documents into independent, equal-sized partitions, called domains.…”

Section: P2p Information Retrievalmentioning

confidence: 99%

PCIR: Combining DHTs and peer clusters for efficient full-text P2P indexing

Papapetrou¹,

Siberski²,

Nejdl³

2010

Computer Networks

View full text Add to dashboard Cite

Distributed hash tables (DHTs) are very efficient for querying based on key lookups. However, building huge term indexes, as required for IR-style keyword search, poses a scalability challenge for plain DHTs. Due to the large sizes of document term vocabularies, peers joining the network cause huge amounts of key inserts and, consequently, a large number of index maintenance messages. Thus, the key to exploiting DHTs for distributed information retrieval is to reduce index maintenance costs. Various approaches in this direction have been pursued, including the use of hybrid infrastructures, or changing the granularity of the inverted index to peer level. We show that indexing costs can be significantly reduced further by letting peers form groups in a self-organized fashion. Instead of each individual peer submitting index information separately, all peers of a group cooperate to publish the index updates to the DHT in batches. Our evaluation shows that this approach reduces index maintenance cost by an order of magnitude, while still keeping a complete and correct term index for query processing.

show abstract

Adlib: A Self-Tuning Index for Dynamic Peer-to-Peer Systems

Cited by 13 publications

References 2 publications

Tree-Based Index Overlay in Hybrid Peer-to-Peer Systems

Tree-Based Index Overlay in Hybrid Peer-to-Peer Systems

DHTs over Peer Clusters for Distributed Information Retrieval

PCIR: Combining DHTs and peer clusters for efficient full-text P2P indexing

Contact Info

Product

Resources

About