Author image not provided
 Franco Scarselli

Authors:
Add personal information
  Affiliation history
Bibliometrics: publication history
Average citations per article11.85
Citation Count320
Publication count27
Publication years1998-2016
Available for download7
Average downloads per article1,237.86
Downloads (cumulative)8,665
Downloads (12 Months)199
Downloads (6 Weeks)26
SEARCH
ROLE
Arrow RightAuthor only


AUTHOR'S COLLEAGUES
See all colleagues of this author

SUBJECT AREAS
See all subject areas




BOOKMARK & SHARE


27 results found Export Results: bibtexendnoteacmrefcsv

Result 1 – 20 of 27
Result page: 1 2

Sort by:

1
November 2016 AI*IA 2016: Proceedings of the XV International Conference of the Italian Association for Artificial Intelligence on Advances in Artificial Intelligence - Volume 10037
Publisher: Springer-Verlag
Bibliometrics:
Citation Count: 0

Traditional supervised approaches realize an inductive learning process: A model is learnt from labeled examples, in order to predict the labels of unseen examples. On the other hand, transductive learning is less ambitious. It can be thought as a procedure to learn the labels on a training set, while, simultaneously, ...
Keywords: Inductive learning, Feedforward neural networks, Transductive learning

2
March 2011 Machine Learning: Volume 82 Issue 3, March 2011
Publisher: Kluwer Academic Publishers
Bibliometrics:
Citation Count: 2

In the last decade, connectionist models have been proposed that can process structured information directly. These methods, which are based on the use of graphs for the representation of the data and the relationships within the data, are particularly suitable for handling relational learning tasks. In this paper, two recently ...
Keywords: Graph neural networks, Mutagenesis, Relational learning, Relational neural networks, Biodegradability

3
September 2010 ICANN'10: Proceedings of the 20th international conference on Artificial neural networks: Part II
Publisher: Springer-Verlag
Bibliometrics:
Citation Count: 1

In this paper, we will apply, to the task of detecting web spam, a combination of the best of its breed algorithms for processing graph domain input data, namely, probability mapping graph self organizing maps and graph neural networks. The two connectionist models are organized into a layered architecture, consisting ...
Keywords: web spam detection, graph neural network, probability mapping GraphSOM

4
September 2010 ICANN'10: Proceedings of the 20th international conference on Artificial neural networks: Part III
Publisher: Springer-Verlag
Bibliometrics:
Citation Count: 0

In this paper, we will apply a recently proposed connectionist model, namely, the Graph Neural Network, for processing the graph formed by considering each sentence in a document as a node and the relationship between two sentences as an edge. Using commonly accepted evaluation protocols, the ROGUE toolkit, the technique ...
Keywords: sentence extraction, graph neural network, text summarization, textrank

5
December 2009 INEX'09: Proceedings of the Focused retrieval and evaluation, and 8th international conference on Initiative for the evaluation of XML retrieval
Publisher: Springer-Verlag
Bibliometrics:
Citation Count: 1

This paper introduces a novel approach for processing a general class of structured information, viz., a graph of graphs structure, in which each node of the graph can be described by another graph, and each node in this graph, in turn, can be described by yet another graph, up to ...

6
December 2009 Neurocomputing: Volume 73 Issue 1-3, December, 2009
Publisher: Elsevier Science Publishers B. V.
Bibliometrics:
Citation Count: 0


7
October 2009
Bibliometrics:
Citation Count: 0

This research book presents some of the most recent advances in neural information processing models including both theoretical concepts and practical applications. The contributions include: Advances in neural information processing paradigms - Self organizing structures - Unsupervised and supervised learning of graph domains - Neural grammar networks - Model complexity ...

8
January 2009 IEEE Transactions on Neural Networks: Volume 20 Issue 1, January 2009
Publisher: IEEE Press
Bibliometrics:
Citation Count: 21

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 ...
Keywords: recursive neural networks, Graphical domains, graph processing, graph neural networks (GNNs), graphical domains

9
January 2009 IEEE Transactions on Neural Networks: Volume 20 Issue 1, January 2009
Publisher: IEEE Press
Bibliometrics:
Citation Count: 16

In this paper, we will consider the approximation properties of a recently introduced neural network model called graph neural network (GNN), which can be used to process-structured data inputs, e.g., acyclic graphs, cyclic graphs, and directed or undirected graphs. This class of neural networks implements a function τ( G, n ...
Keywords: graph neural networks (GNNs), universal approximators, approximation theory, graphical domains, Approximation theory

10
January 2007 IJCAI'07: Proceedings of the 20th international joint conference on Artifical intelligence
Publisher: Morgan Kaufmann Publishers Inc.
Bibliometrics:
Citation Count: 0

Term weighting systems are of crucial importance in Information Extraction and Information Retrieval applications. Common approaches to term weighting are based either on statistical or on natural language analysis. In this paper, we present a new algorithm that capitalizes from the advantages of both the strategies by adopting a machine ...

11 published by ACM
November 2006 ACM Transactions on Internet Technology (TOIT): Volume 6 Issue 4, November 2006
Publisher: ACM
Bibliometrics:
Citation Count: 6
Downloads (6 Weeks): 1,   Downloads (12 Months): 8,   Downloads (Overall): 905

Full text available: PDFPDF
In this article, we present a new approach to page ranking. The page rank of a collection of Web pages can be represented in a parameterized model, and the user requirements can be represented by a set of constraints. For a particular parameterization, namely, a linear combination of the page ...
Keywords: Interface personalization, PageRank, Web page scoring systems, search engines

12
May 2006 Proceedings of the 2006 conference on ECAI 2006: 17th European Conference on Artificial Intelligence August 29 -- September 1, 2006, Riva del Garda, Italy
Publisher: IOS Press
Bibliometrics:
Citation Count: 1

Term weighting is a crucial task in many Information Retrieval applications. Common approaches are based either on statistical or on natural language analysis. In this paper, we present a new algorithm that capitalizes from the advantages of both the strategies. In the proposed method, the weights are computed by a ...

13
May 2006 Proceedings of the 2006 conference on ECAI 2006: 17th European Conference on Artificial Intelligence August 29 -- September 1, 2006, Riva del Garda, Italy
Publisher: IOS Press
Bibliometrics:
Citation Count: 3

Graph Neural Networks (GNNs) are a recently proposed connectionist model that extends previous neural methods to structured domains. GNNs can be applied on datasets that contain very general types of graphs and, under mild hypotheses, they have been proven to be universal approximators on graphical domains. Whereas most of the ...

14
October 2005 Neural Networks - Special issue on neural networks and kernel methods for structured domains: Volume 18 Issue 8, October 2005
Publisher: Elsevier Science Ltd.
Bibliometrics:
Citation Count: 12

In this paper, we introduce a new recursive neural network model able to process directed acyclic graphs with labelled edges. The model uses a state transition function which considers the edge labels and is independent both from the number and the order of the children of each node. The computational ...

15
September 2005 WI '05: Proceedings of the 2005 IEEE/WIC/ACM International Conference on Web Intelligence
Publisher: IEEE Computer Society
Bibliometrics:
Citation Count: 9
Downloads (6 Weeks): 2,   Downloads (12 Months): 12,   Downloads (Overall): 12

Full text available: PDFPDF
An artificial neural network model, capable of processing general types of graph structured data, has recently been proposed. This paper applies the new model to the computation of customised page ranks problem in the World Wide Web. The class of customised page ranks that can be implemented in this way ...

16
September 2005 Pattern Recognition Letters - Special issue: Artificial neural networks in pattern recognition: Volume 26 Issue 12, September 2005
Publisher: Elsevier Science Inc.
Bibliometrics:
Citation Count: 8

Localizing faces in images is a difficult task, and represents the first step towards the solution of the face recognition problem. Moreover, devising an effective face detection method can provide some suggestions to solve similar object and pattern detection problems. This paper presents a novel approach to the solution of ...
Keywords: Face recognition, Localization of faces, Recursive neural networks

17 published by ACM
May 2005 WWW '05: Special interest tracks and posters of the 14th international conference on World Wide Web
Publisher: ACM
Bibliometrics:
Citation Count: 2
Downloads (6 Weeks): 1,   Downloads (12 Months): 10,   Downloads (Overall): 474

Full text available: PDFPDF
Recent developments in the area of neural networks provided new models which are capable of processing general types of graph structures. Neural networks are well-known for their generalization capabilities. This paper explores the idea of applying a novel neural network model to a web graph to compute an adaptive ranking ...
Keywords: adaptive page rank, graph processing, neural networks

18
March 2005 APWeb'05: Proceedings of the 7th Asia-Pacific web conference on Web Technologies Research and Development
Publisher: Springer-Verlag
Bibliometrics:
Citation Count: 0

In this paper, we will provide an overview of some of the more recent developments in web graph processing using the classic Google page rank equation as popularized by Brins and Page [1], and its modifications, to handle page rank and personalized page rank determinations. It is shown that one ...

19 published by ACM
February 2005 ACM Transactions on Internet Technology (TOIT): Volume 5 Issue 1, February 2005
Publisher: ACM
Bibliometrics:
Citation Count: 108
Downloads (6 Weeks): 12,   Downloads (12 Months): 132,   Downloads (Overall): 5,413

Full text available: PDFPDF
Although the interest of a Web page is strictly related to its content and to the subjective readers' cultural background, a measure of the page authority can be provided that only depends on the topological structure of the Web. PageRank is a noticeable way to attach a score to Web ...
Keywords: Information retrieval, PageRank, search engines, searching the Web, Markov chains, Web page scoring

20 published by ACM
May 2004 WWW Alt. '04: Proceedings of the 13th international World Wide Web conference on Alternate track papers & posters
Publisher: ACM
Bibliometrics:
Citation Count: 2
Downloads (6 Weeks): 1,   Downloads (12 Months): 15,   Downloads (Overall): 246

Full text available: PDFPDF
This paper presents an algorithm to bound the bandwidth of a Web crawler. The crawler collects statistics on the transfer rate of each server to predict the expected bandwidth use for future downloads. The prediction allows us to activate the optimal number of fetcher threads in order to exploit the ...
Keywords: bandwidth optimization, parallel web crawlers



The ACM Digital Library is published by the Association for Computing Machinery. Copyright © 2018 ACM, Inc.
Terms of Usage   Privacy Policy   Code of Ethics   Contact Us