Graph Neural Networks for Ranking Web Pages

Scarselli, Franco; Yong, Sweah Liang; Gori, Marco; Hagenbuchner, Markus; Tsoi, Ah Chung; Maggini, Marco

doi:10.1109/wi.2005.67

Cited by 96 publications

(54 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Finally, the web page ranking is an interesting problem, since it is important in information retrieval and very few techniques have been proposed for its solution [76]. It is worth mentioning that the GNN model has been already successfully applied on larger applications, which include image classification and object localization in images [77], [78], web page ranking [79], relational learning [80], and XML classification [81].…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

The Graph Neural Network Model

Scarselli

Gori

Tsoi

et al. 2009

IEEE Trans. Neural Netw.

Self Cite

6,239

3,275

View full text Add to dashboard Cite

Many underlying relationships among data in several areas of science and engineering, e.g., computer vision, molecular chemistry, molecular biology, pattern recognition, and data mining, can be represented in terms of graphs. In this paper, we propose a new neural network model, called graph neural network (GNN) model, that extends existing neural network methods for processing the data represented in graph domains. This GNN model, which can directly process most of the practically useful types of graphs, e.g., acyclic, cyclic, directed, and undirected, implements a function tau(G,n) isin IR m that maps a graph G and one of its nodes n into an m-dimensional Euclidean space. A supervised learning algorithm is derived to estimate the parameters of the proposed GNN model. The computational cost of the proposed algorithm is also considered. Some experimental results are shown to validate the proposed learning algorithm, and to demonstrate its generalization capabilities. Disciplines Physical Sciences and Mathematics

show abstract

Section: Resultsmentioning

confidence: 99%

“…Here, we present the results obtained by GNNs on a synthetic data set. More results achieved on a snapshot of the web are available in [79].…”

Section: Web Page Rankingmentioning

confidence: 99%

The Graph Neural Network Model

Scarselli

Gori

Tsoi

et al. 2009

IEEE Trans. Neural Netw.

Self Cite

6,239

3,275

View full text Add to dashboard Cite

show abstract

“…The neural network graph could learn the ranking function via examples, and is capable of generalizing over unseen data [7]. Khodadadian and et al, by using the reinforcement learning concept, proposed RL_Rank algorithm which is a novel connection based algorithm for ranking web pages.…”

Section: Related Workmentioning

confidence: 99%

Presentation of an Extended Version of the PageRank Algorithm to Rank Web Pages Inspired by Ant Colony Algorithm

Setayesh¹,

Harounabadi²,

Rahmani³

2014

IJCA

View full text Add to dashboard Cite

The general search engines represent various results in their lists, which is very time consuming to check. . One way to limit the search engine results is to use ranking pages algorithm in web. One of the most important ranking algorithms of web pages in the internet is known as "PageRank", which works on the web-graph structure.In this article, an extended version of the "PageRank" algorithm taking into consideration the degree of user interest in web pages and the ant colony algorithm is presented. Simulation results indicate that in the recommended algorithm ranks are closer to the real data; they produce more distinguished ranks, and have a less amount of errors.

show abstract

“…9 Graph neural networks, 10 capable of processing cyclic nonpositional graphs directly, were applied e.g. for spam detection, 11 document mining, 12 web page ranking, 13 image localisation 14 and image classification. 15 A different model, the Graph Machines, 16 was developed for QSAR 17 and was recently used for predicting fuel combustion properties.…”

Section: Introductionmentioning

confidence: 99%