Ng, A. Y., Zheng, A. X., and Jordan, M. Stable algorithms for link analysis. In Proceedings of the Twenty-fourth Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Sept. 2001.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....At each step, with probability ffl, the Rafiei and Mendelzon algorithm jumps to a page of the collection chosen uniformly at random, and with probability 1 Gamma ffl it performs a SALSA step. This algorithm is essentially the same as the Randomized HITS algorithm considered later by Ng et al. [19]. 2.4 The PHITS Algorithm Cohn and Chang [8] propose a statistical hubs and authorities algorithm, which they call the PHITS Algorithm. They propose a probabilistic model in which a citation c of a document d is caused by a latent factor or topic , z. It is postulated that there are ....

....secondary (i.e. non principal) eigenvectors (or their positive and negative components) being related to secondary (or opposing) communities of web pages. The use of secondary eigenvectors for discovering communities, or for improving the quality of the ranking has been investigated further in [13, 1, 19]. We now present a few simple examples which we feel illustrate the opinion that such secondary eigenvectors sometimes are, but sometimes are not, indicative of secondary communities. In short, there is no simple result either way, regarding these secondary eigenvectors. For the following, we ....

[Article contains additional citation context not shown here]

A. Y. Ng, A. X. Zheng, and M. I. Jordan. Stable algorithms for link analysis. In Proceedings of the 24th International Conference on Research and Development in Information Retrieval (SIGIR 2001.

....[11] consider improvements on the HITS algorithm by using textual information to weight the importance of nodes and links. Rafiei and Mendelzon [42, 38] consider a variation of the HITS algorithm that uses random jumps, similar to SALSA. The same algorithm is also considered by Ng Zheng and Jordan [39, 40], termed Randomized HITS. Extensions of the HITS algorithm that use multiple eigenvectors were proposed by Ng, Zheng and Jordan [40] and Achlioptas et al. 3] Tomlin [51] proposes a generalization of the PAGERANK algorithm that computes flow values for the edges of the Web graph, and a ....

....[42, 38] consider a variation of the HITS algorithm that uses random jumps, similar to SALSA. The same algorithm is also considered by Ng Zheng and Jordan [39, 40] termed Randomized HITS. Extensions of the HITS algorithm that use multiple eigenvectors were proposed by Ng, Zheng and Jordan [40], and Achlioptas et al. 3] Tomlin [51] proposes a generalization of the PAGERANK algorithm that computes flow values for the edges of the Web graph, and a TrafficRank value for each page. There exists also a large body of work that deals with personalization of the PAGERANK algorithm [41, 23, ....

[Article contains additional citation context not shown here]

A. Y. Ng, A. X. Zheng, and M. I. Jordan. Stable algorithms for link analysis. In Proceedings of the 24th International Conference on Research and Development in Information Retrieval (SIGIR 2001.

....web pages. Independently, Brin and Page proposed the PageRank algorithm [5] which become an integral component of the successful Google search engine [9] These two algorithms spawned the research field of link analysis ranking, and they were followed by a substantial amount of research work [4, 3, 13, 16, 2, 1, 15]. Most of link analysis ranking algorithms start with a set of web pages, interconnected with hypertext links. Given the underlying graph, the algorithms extract the principal eigenvector (s) of a matrix associated with the graph, and rank the pages according to the value of each page in this ....

....by good hubs. In PAGERANK good authorities are pointed to by good authorities. The HITS and PAGERANK algorithms were followed by a substantial number of variations and enhancements. Most of the subsequent work follows a similar algebraic approach, manipulating some matrix related to the web graph [4, 3, 13, 16, 2, 1, 15]. Recently, there were some interesting attempts in applying statistical, and machine learning tools for computing authority weights [4, 6, 11] 3. DYNAMICAL SYSTEMS A dynamical system describes a weight propagation scheme on the nodes of a graph. We construct the Base Set as described by ....

[Article contains additional citation context not shown here]

A. Y. Ng, A. X. Zheng, and M. I. Jordan. Stable algorithms for link analysis. In Proceedings of the 24th International Conference on Research and Development in Information Retrieval (SIGIR 2001.

....link is highly recommended and therefore an authority. The authoritativeness of a document is even higher if the documents that link to it are some sort of authorities themselves. HITS and PageRank (or variants of those) are reported to be successful in numerous studies of retrieval quality [18, 3, 1, 25, 5], however when measuring relevance only, without taking quality or authoritativeness into account, HITS and PageRank based methods have not been able to improve retrieval effectiveness for Ad Hoc search tasks [15, 13, 20, 31, 8] Davison [11] shows that the topic locality assumption holds: when ....

A. Y. Ng, A. X. Zheng, and M. I. Jordan. Stable algorithms for link analysis. In Croft et al. [9], pages 258--266.

....companies and researchers try to work out solutions to improve the precision of search engines. One of the representative solutions is to re ranking the retrieved documents by their importance [1] 8] 12] which is calculated by analyzing the link between Web pages. Web link analysis [1] 2] 3] 4][5][6] 7] 8] 13] has been proved to reach higher precision than full text search in practice. According to the type of web link, link analysis approaches can be classified into two categories, explicit link analysis and implicit link analysis . The so called explicit link stands for the ....

....et al. 2] 3] pointed out that text surround hyperlinks in source web pages is helpful to express the content of destination web pages. Moreover, to reduce weight factors of hyperlinks from the same domain, the problem that a single website dominates the computation can be avoided. Ng et al. [5] present ed randomized HITS and subspace HITS algorithms to enhance the stability of the basic HITS. The former imitates a random walk on web pages and defines the authority hub weight as a chance of visiting that page on time step t (t is large enough) The latter uses the first k eigenvectors ....

Andrew Y. Ng et al., Stable algorithms for link analysis, in: Proc. of the 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2001.

....the basic concepts of hubs and authorities. HITS assigns respective scores to hubs and authorities, and computes them in a mutually reinforcing way: an authority must be pointed to by several good hubs while a hub must point to several good authorities. Further improved versions are also developed [15, 5, 10, 21, 6, 11, 23]. The basic thesis of HITS can be characterized as exploring the duality relationship between hubs and authorities in the web link graph. The nal goal is to provide a ranking of webpages based on their hub and authority scores. In this paper we give an in depth analysis of the HITS algorithm. ....

A.Y. Ng, A.X. Zheng, and M.I. Jordan. Stable algorithms for link analysis. Proc. ACM Conf. on Research and Develop. in Info. Retrieval (SIGIR'01), 2001.

....HITS makes the distinction between hubs and authorities and computes them in a mutually reinforcing way. PageRank considers the hyperlink weight normalization and the equilibrium distribution of random surfers as the citation score. There are a number of further extensions and developments [4, 9, 19, 5, 20]. In this paper, we briefly discuss HITS with mutual reinforcement of hubs and authorities. We also emphasize the role of co reference and co citation (Fig.1) which provides the bibliographic rational for hyperlink weight normalization (Fig.2) as a key concept in link analysis. An indepth ....

....of L L and LL , which are the singular value decomposition of L. In practical applications, a modification of HITS [4] by suppressing the contribution from di#erent webpages from same host (site or root in URL) is often adopted. Further developments and applications are discussed in [13, 8, 4, 18, 9, 19, 5, 20] (see 6) 2.1 Co citation and co reference The authority and hub matrices have interesting connections [16] to co citation and co reference in the fields of citation analysis and bibliometrics. Here we discuss the relationships in further details and emphasize the important roles of in degrees ....

[Article contains additional citation context not shown here]

A.Y. Ng, A.X. Zheng, and M.I. Jordan. Stable algorithms for link analysis. Proc. ACM Conf. on Research and Develop. Info. Retrieval (SIGIR), 2001.

....link is highly recommended and therefore an authority. The authoritativeness of a document is even higher if the documents that link to it are some sort of authorities themselves. HITS and PageRank (or variants of those) are reported to be successful in numerous studies of retrieval quality [18, 3, 1, 25, 5], however when measuring relevance only, without taking quality or authoritativeness into account, HITS and PageRank based methods have not been able to improve retrieval effectiveness for Ad Hoc search tasks [15, 13, 20, 31, 8] Davison [11] shows that the topic locality assumption holds: when ....

A. Y. Ng, A. X. Zheng, and M. I. Jordan. Stable algorithms for link analysis. In Croft et al. [9], pages 258--266.

....Letting denote the stationary distribution of P , the fundamental question in sensitivity analysis is how to express Gamma in terms of E; typically: jj Gamma jj jjEjj for a condition number , for standard norms such as the L 1 , Euclidean, or infinity norms. Ng, Zheng, and Jordan [12, 13] compared the stability of PageRank and HITS [8] under massive changes to a graph derived from the Cora citation database [10] Borodin et al. 1] present a set of criteria for comparing link analysis algorithms. Interestingly, they study a variant of monotonicity in the context of hubs and ....

A. Y. Ng, A. X. Zheng, and M. I. Jordan. Stable algorithms for link analysis. Proc. 24th International Conference on Research and Development in Information Retrieval (SIGIR), 2001.

No context found.

Ng, A. Y., Zheng, A. X., and Jordan, M. Stable algorithms for link analysis. In Proceedings of the Twenty-fourth Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Sept. 2001.

No context found.

A. Y. Ng, A. X. Zheng, and M. I. Jordan, Stable algorithms for link analysis, Proc. 24th SIGIR 2001.

No context found.

A. Y. Ng, A. X. Zheng, and M. I. Jordan, Stable algorithms for link analysis, Proc. 24th SIGIR 2001.

No context found.

A. Y. Ng, A. X. Zheng, and M. I. Jordan. Stable algorithms for link analysis. In Proc. 24th Annual Intl. ACM SIGIR Conference. ACM, 2001.

No context found.

A. Y. Ng, A. X. Zheng, and M. I. Jordan. Stable algorithms for link analysis. In Proc. 24th Annual Intl. ACM SIGIR Conference. ACM, 2001.

No context found.

A. Y. Ng, A. X. Zheng, and M. I. Jordan. Stable algorithms for link analysis. In Proc. 24th Annual Intl. ACM SIGIR Conference. ACM, 2001.

No context found.

A. Y. Ng, A. X. Zheng, and M. I. Jordan. Stable algorithms for link analysis. In Proc. 24th Annual Intl. ACM SIGIR Conference. ACM, 2001.

No context found.

A. Y. Ng, A. X. Zheng, and M. I. Jordan. Stable algorithms for link analysis. In Proc. 24th Annual Intl. ACM SIGIR Conference. ACM, 2001.

No context found.

Andrew Y. Ng, Alice X. Zheng, and Michael I. Jordan. Stable algorithms for link analysis. In Proceedings of the 24th Annual International ACM SIGIR Conference. ACM, 2001.

No context found.

A. Y. Ng, A. X. Zheng, and M. I. Jordan. Stable algorithms for link analysis. In Proc. 24th Annual Intl. ACM SIGIR Conference, 2001.

No context found.

Andrew Y. Ng, Alice X. Zheng, and Michael I. Jordan. Stable algorithms for link analysis. In Proceedings of the 24th annual international ACM SIGIR conference on Research and development in information retrieval, pages 258--266. ACM Press, 2001.

No context found.

A. Ng, A. Zheng, and M. Jordan. Stable algorithms for link analysis. In Proc. of the 24th Annual SIGIR Conf. on Research and Development in Information Retrieval, 2001.

No context found.

A. Y. Ng, A. X. Zheng, and M. I. Jordan. Stable algorithms for link analysis. In Proc. 24th Annual Intl. ACM SIGIR Conference. ACM, 2001.

No context found.

A. Ng, A. Zheng, and M. Jordan. Stable algorithms for link analysis. In Proc. ACM SIGIR, 2001.

No context found.

Andrew Y. Ng, Alice X. Zheng, and Michael I. Jordan. Stable algorithms for link analysis. In Proceedings of the 24th Annual International ACM SIGIR Conference. ACM, 2001.

No context found.

A. NG, A. Zheng, and M. Jordan, "Stable algorithms for link analysis," in Proceedings of SIGIR'01, 2001.

First 50 documents

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC