Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies
if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the
same subfield and year (this is the minimum needed to enter the top 1%, not the average
within it), or reaches the top citation threshold in at least one of its specific research
topics.
The Graph Neural Network Model
20085.1k citationsFranco Scarselli, M. Gori et al.IEEE Transactions on Neural Networksprofile →
A new model for learning in graph domains
20061.0k citationsMarco Gori, Gabriele Monfardini et al.profile →
On the Complexity of Neural Network Classifiers: A Comparison Between Shallow and Deep Architectures
Countries citing papers authored by Franco Scarselli
Since
Specialization
Citations
This map shows the geographic impact of Franco Scarselli's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Franco Scarselli with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Franco Scarselli more than expected).
Fields of papers citing papers by Franco Scarselli
This network shows the impact of papers produced by Franco Scarselli. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Franco Scarselli. The network helps show where Franco Scarselli may publish in the future.
Co-authorship network of co-authors of Franco Scarselli
This figure shows the co-authorship network connecting the top 25 collaborators of Franco Scarselli.
A scholar is included among the top collaborators of Franco Scarselli based on the total number of
citations received by their joint publications. Widths of edges
represent the number of papers authors have co-authored together.
Node borders
signify the number of papers an author published with Franco Scarselli. Franco Scarselli is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Rossi, Alberto, Simone Bonechi, Paolo Andreini, et al.. (2020). Graph Neural Networks for the Prediction of Protein-Protein Interfaces.. Use Siena air (University of Siena). 127–132.13 indexed citations
Bianchini, Monica & Franco Scarselli. (2014). On the complexity of shallow and deep neural network classifiers. Use Siena air (University of Siena). 371–376.22 indexed citations
Scarselli, Franco, M. Gori, Ah Chung Tsoi, Markus Hagenbuchner, & Gabriele Monfardini. (2008). Computational Capabilities of Graph Neural Networks. IEEE Transactions on Neural Networks. 20(1). 81–102.133 indexed citations
12.
Angelini, Giovanni, et al.. (2007). An adaptive context-based algorithm for term weighting: application to single-word question answering. International Joint Conference on Artificial Intelligence. 29(3). 2748–2753.1 indexed citations
13.
Pucci, Augusto, Marco Gori, Markus Hagenbuchner, Franco Scarselli, & Ah Chung Tsoi. (2006). Investigation into the application of graph neural networks to large-scale recommender systems. Systems Science. 32(4). 17–26.4 indexed citations
14.
Monfardini, Gabriele, et al.. (2006). Two connectionist models for graph processing: An experimental comparison on relational data. Lirias (KU Leuven). 211–220.8 indexed citations
15.
Monfardini, Gabriele, et al.. (2006). Graph Neural Networks for Object Localization. Use Siena air (University of Siena). 665–669.6 indexed citations
Bianchini, Monica, Marco Gori, & Franco Scarselli. (2004). PageRank and Web communities. Use Siena air (University of Siena). 365–371.4 indexed citations
18.
Tsoi, Ah Chung, et al.. (2003). A Simple Focused Crawler.. Use Siena air (University of Siena).9 indexed citations
19.
Bianchini, Monica, et al.. (2003). Face Spotting in Color Images using Recursive Neural Networks. Use Siena air (University of Siena). 76–81.14 indexed citations
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive
bibliographic database. While OpenAlex provides broad and valuable coverage of the global
research landscape, it—like all bibliographic datasets—has inherent limitations. These include
incomplete records, variations in author disambiguation, differences in journal indexing, and
delays in data updates. As a result, some metrics and network relationships displayed in
Rankless may not fully capture the entirety of a scholar's output or impact.