Affinity P2P: A self-organizing content-based locality-aware collaborative peer-to-peer network

Tirado, Juan M.; Higuero, Daniel; Isaila, Florin; Carretero, Jesús; Iamnitchi, Adriana

doi:10.1016/j.comnet.2010.04.016

Cited by 28 publications

(18 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These metrics have been widely used in distributed systems where the user has a partial vision of the network [22,5] and also in graph-based solutions [16,3]. The main reason for their utilization is that they are computationally light and summarize relevant features users may have in common.…”

Section: Proposed Approachmentioning

confidence: 99%

Cheap and Cheerful: Trading Speed and Quality for Scalable Social-Recommenders

Kermarrec¹,

Taı̈ani²,

Tirado³

2015

Distributed Applications and Interoperable Systems

Self Cite

View full text Add to dashboard Cite

Abstract. Recommending appropriate content and users is a critical feature of on-line social networks. Computing accurate recommendations on very large datasets can however be particularly costly in terms of resources, even on modern parallel and distributed infrastructures. As a result, modern recommenders must generally trade-off quality and computational cost to reach a practical solution. This trade-off has however so far been largely left unexplored by the research community, making it difficult for practitioners to reach informed design decisions. In this paper, we investigate to which extent the additional computing costs of advanced recommendation techniques based on supervised classifiers can be balanced by the gains they bring in terms of quality. In particular, we compare these recommenders against their unsupervised counterparts, which offer lightweight and highly scalable alternatives. We propose a thorough evaluation comparing 11 classifiers against 7 lightweight recommenders on a real Twitter dataset. Additionally, we explore data grouping as a method to reduce computational costs in a distributed setting while improving recommendation quality. We demonstrate how classifiers trained using data grouping can reduce their computing time by 6 while improving recommendations up to 22% when compared with lightweight solutions.

show abstract

Section: Proposed Approachmentioning

confidence: 99%

Cheap and Cheerful: Trading Speed and Quality for Scalable Social-Recommenders

Kermarrec¹,

Taı̈ani²,

Tirado³

2015

Distributed Applications and Interoperable Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…Designing highly scalable and privacy-preserving recommenders is hard, and one promising approach consists in exploiting fully decentralised mechanisms such as gossip [21,5], or DHTs [29]. These decentralised recommenders, however, have so far used a mostly homogeneous design.…”

Section: Introductionmentioning

confidence: 99%

Similitude: Decentralised Adaptation in Large-Scale P2P Recommenders

Frey

Kermarrec

Maddock

et al. 2015

Distributed Applications and Interoperable Systems

View full text Add to dashboard Cite

Abstract. Decentralised recommenders have been proposed to deliver privacy-preserving, personalised and highly scalable on-line recommendations. Current implementations tend, however, to rely on a hard-wired similarity metric that cannot adapt. This constitutes a strong limitation in the face of evolving needs. In this paper, we propose a framework to develop dynamically adaptive decentralised recommendation systems. Our proposal supports a decentralised form of adaptation, in which individual nodes can independently select, and update their own recommendation algorithm, while still collectively contributing to the overall system's mission.

show abstract

“…Compared to cluster-based replication approaches, our approach has two distinct characteristics. First, instead of keeping data copies at cluster data servers [21,[23][24] or nodes in the same cluster [22,25] , these data are replicated onto neighbor nodes and shortcut nodes, so that they become widely available and the impact of different network partitions on the service quality is reduced. Second, unlike the cluster-based replication method that replicates data on demand [21] or according to the popularity [22][23] , the proposed approach enables each node to take into account nodes' location to improve the replication flexibility and reduce the cost caused by a large number of replicas' creation and maintenance.…”

Section: Related Workmentioning

confidence: 99%

“…There are several work proposed to cope with node failure and keep high data availability by using the clustering-based replication technology [21][22][23][24][25] . The main idea of this strategy is to place multiple object replicas on the nodes (servers) in the same cluster to reduce the distances between accessing sites and data (file) and maximize the availability of the data (file) in the network.…”

Section: Related Workmentioning

confidence: 99%

Fault Tolerance and Recovery for Group Communication Services in Distributed Networks

Wang

Zhou

Liu

et al. 2012

J. Comput. Sci. Technol.

View full text Add to dashboard Cite

Group communication services (GCSs) are becoming increasingly important as a wide field of promising applications has emerged to serve millions of users distributed across the world. However, it is challenging to make the service fault tolerance and scalable to fulfill the voluminous demand of users in a distributed network (DN). While many reliable group communication protocols have been dedicated to addressing such a challenge so as to accommodate the changes in the network, they are often costly or require complicated strategies to handle the service interruptions caused by node departures or link failures, which hinders the service practicability. In this paper, we present two schemes to address the challenges. The first one is a location-aware replication scheme called NS, which makes replicas in a dispersed fashion that enables the services on nodes to gain immunity of failures with different patterns (e.g., network partition and single point failure) while keeping replication overhead low. The second one is a novel failure recovery scheme that exploits the independence between service recovery and structure recovery in time domain to achieve quick failure recovery. Our simulation results indicate that the two proposed schemes outperform the existing schemes and simple alternative schemes in service success rate, recovery latency, and communication cost.

show abstract

Affinity P2P: A self-organizing content-based locality-aware collaborative peer-to-peer network

Cited by 28 publications

References 20 publications

Cheap and Cheerful: Trading Speed and Quality for Scalable Social-Recommenders

Cheap and Cheerful: Trading Speed and Quality for Scalable Social-Recommenders

Similitude: Decentralised Adaptation in Large-Scale P2P Recommenders

Fault Tolerance and Recovery for Group Communication Services in Distributed Networks

Contact Info

Product

Resources

About