Skip to main content

Distributed Large-Scale Information Filtering

We study the problem of distributed resource sharing in peer-to-peer networks and focus on the problem of information ltering. In our setting, subscriptions and publications are speci ed using an expressive attribute-value representation that supports both the Boolean and Vector Space models.We use an extension of the distributed hash table Chord to organise the nodes and store user subscriptions, and utilise ecient publication protocols that keep the network trac and latency
low at ltering time. To verify our approach, we evaluate the proposed protocols experimentally using thousands of nodes, millions of user subscriptions, and two di erent real-life corpora. We also study three important facets of the load-balancing problem in such a scenario and present a novel algorithm that manages to distribute the load evenly among the
nodes. Our results show that the designed protocols are scalable and ecient: they achieve expressive information ltering functionality with low message trac and latency.
C. Tryfonopoulos, S. Idreos, M. Koubarakis, P. Raftopoulou, "Distributed Large-Scale Information Filtering ", In LNCS Transactions on Large-Scale Data- and Knowledge-Centered Systems (TLDKS), Springer, 2014
Published at
LNCS Transactions on Large-Scale Data- and Knowledge-Centered Systems, Springer
Related research area
No related research area
Related Organizations
No related organizations