Fast Distributed PageRank Computation

Sarma, Anish Das; Molla, Anisur Rahaman; Pandurangan, Gopal; Upfal, Eli

doi:10.1007/978-3-642-35668-1_2

Cited by 66 publications

(56 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this paper [6],over the last decade, Page Rank has gained importance in a wide range of applications and domains, ever since it first proved to be effective in determining node importance in large graphs (and was a pioneering idea behind Google's search engine). In distributed computing alone, Page Rank vector, or more generally random walk based quantities have been used for several different applications ranging from determining important nodes, load balancing, search, and identifying connectivity structures.…”

Section: Literature Surveymentioning

confidence: 99%

Friends Wall: A Semantic-based Friend Recommendation System for Social Networks

Agarwal¹,

Singh²,

Bhujbal³

et al. 2017

International Journal of Advanced Research in Computer and Comm

View full text Add to dashboard Cite

Present social networking services suggest friends to users based on their social activities, which may not be the most suitable to react a users taste on friend choice in real life. In this project, we present Friendswall, a semanticbased friend recommendation system for social networks, which present friends to users based on their life styles instead of social activities. By taking benefit of sensor-rich Smartphones, Friendswall discovers life styles of users, measures the resemblance of life styles between users, and suggest friends to users if their life styles have high resemblance. Inspired by text mining, in this project we design a users daily life as life documents, from which his/her life styles are taken out by using the Naive Byes algorithm. We further aim a similarity metric to measure the resemblance of life styles between users, and estimate users impact in terms of life styles with a friend-matching graph. Upon acquiring a request, FriendsWall returns a list of people with maximum resemblance scores to the query user. At last, FriendsWall incorporate a feedback mechanism to further amend the recommendation accuracy. This project will build FriendsWall and evaluate its performance on both small-scale experiments and large-scale model.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Friends Wall: A Semantic-based Friend Recommendation System for Social Networks

Agarwal¹,

Singh²,

Bhujbal³

et al. 2017

International Journal of Advanced Research in Computer and Comm

View full text Add to dashboard Cite

show abstract

“…Alternatively, PowerIteration [27] or using iterative approximations [14,30], which explicitly simulate the dissemination of probability mass by repeatedly applying the transition process to an initial distribution π 0 until a convergence criterion is satisfied. Recent advances on PPR computation include top-k and approximate personalized PageRank algorithms [2,4,14,17,21,23,41] and parallelized implementations on MapReduce or Pregel based systems [3,32,36,38]. The FastRWR algorithm [41], for example partitions the graph into subgraphs and indexes partial intermediary solutions.…”

Section: Obtaining Pagerank and Personalized Pagerank Scoresmentioning

confidence: 99%

Reducing seed noise in personalized PageRank

Huang

Candan

et al. 2016

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

Network based recommendation systems leverage the topology of the underlying graph and the current user context to rank objects in the database. Random-walk based techniques, such as PageRank, encode the structure of the graph in the form of a transition matrix of a stochastic process from which the significances of the nodes in the graph are inferred. Personalized PageRank (PPR) techniques complement this with a seed node set which serves as the personalization context. In this paper, we note (and experimentally show) that PPR algorithms that do not differentiate among the seed nodes may not properly rank nodes in situations where the seed set is incomplete and/or noisy. To tackle this problem, we propose alternative robust personalized PageRank (RPR) strategies, which are insensitive to noise in the set of seed nodes and in which the rankings are not overly biased towards the seed nodes. In particular, we show that novel teleportation discounting and seed-set maximal PPR techniques help eliminate harmful bias of individual seed nodes and provide effective seed differentiation to lead to more accurate rankings. We also show that the proposed techniques lead to efficient implementations, where existing approximation algorithms and/or parallel implementations for computing the PPR scores can be easily leveraged. Moreover, the proposed formulations are reuse-promoting in the sense that, it is possible to divide the work relative to individual seed nodes and cache the intermediary results obtained during the computation, and especially in systems with large query throughputs, it may be possible to cluster queries based on the partial overlaps between the seed sets and reduce the overall robust PPR computation costs. Experiment results show that the proposed techniques are efficient and highly effective in improving recommendations and eliminating unwanted bias due to imperfections in the seed set.

show abstract

“…A distributed Monte Carlo-based approach to the PageRank computation was presented by Das Sarma et al (2013). The work emphasized the suitability of random-walk based Monte Carlo methods for scalable distributed PageRank computation (especially in contrast to power iteration, which is hard to perform in a distributed context and is sensitive to the volume of communication involved).…”

Section: Kudělka Et Almentioning

confidence: 99%

Local dependency in networks

Kudźlka

Zehnalova

Horák

et al. 2015

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

Many real world data and processes have a network structure and can usefully be represented as graphs. Network analysis focuses on the relations among the nodes exploring the properties of each network. We introduce a method for measuring the strength of the relationship between two nodes of a network and for their ranking. This method is applicable to all kinds of networks, including directed and weighted networks. The approach extracts dependency relations among the network's nodes from the structure in local surroundings of individual nodes. For the tasks we deal with in this article, the key technical parameter is locality. Since only the surroundings of the examined nodes are used in computations, there is no need to analyze the entire network. This allows the application of our approach in the area of large-scale networks. We present several experiments using small networks as well as large-scale artificial and real world networks. The results of the experiments show high effectiveness due to the locality of our approach and also high quality node ranking comparable to PageRank.

show abstract

Fast Distributed PageRank Computation

Cited by 66 publications

References 18 publications

Friends Wall: A Semantic-based Friend Recommendation System for Social Networks

Friends Wall: A Semantic-based Friend Recommendation System for Social Networks

Reducing seed noise in personalized PageRank

Local dependency in networks

Contact Info

Product

Resources

About