Gianmaria Silvello

Gianmaria Silvello

Auto-generated profile, based on publicly available information

Gianmaria Silvello

University of Padova

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 September 2022 in Data Mining and Knowledge Discovery
Verified
Journal Article
Open access
PDF file
AFAlessandro Fabris
Alessandro Fabris
SMStefano Messina
Stefano Messina
GSGianmaria Silvello
Gianmaria Silvello
GSGian Antonio Susto
Gian Antonio Susto
Data-driven algorithms are studied and deployed in diverse domains to support critical decisions, directly impacting people’s well-being. As a result, a growing community of researchers has been investigating the equity of existing algorithms and proposing novel ones, advancing the understanding of risks and opportunities of automated decision-making for historically disadvantaged populations. Progress in fair machine learning and equitable algorithm design hinges on data, which can be appropriately used only if adequately documented. Unfortunately, the algorithmic fairness community, as a whole, suffers from a collective data documentation debt caused by a lack of information on specific resources (opacity) and scatteredness of available information (sparsity). In this work, we target this data documentation debt by surveying over two hundred datasets employed in algorithmic fairness research, and producing standardized and searchable documentation for each of them. Moreover we rigorously identify the three most popular fairness datasets, namely Adult, COMPAS, and German Credit, for which we compile in-depth documentation. This unifying documentation effort supports multiple contributions. Firstly, we summarize the merits and limitations of Adult, COMPAS, and German Credit, adding to and unifying recent scholarship, calling into question their suitability as general-purpose fairness benchmarks. Secondly, we document hundreds of available alternatives, annotating their domain and supported fairness tasks, along with additional properties of interest for fairness practitioners and researchers, including their format, cardinality, and the sensitive attributes they encode. We summarize this information, zooming in on the tasks, domains, and roles of these resources. Finally, we analyze these datasets from the perspective of five important data curation topics: anonymization, consent, inclusivity, labeling of sensitive attributes, and transparency. We discuss different approaches and levels of attention to these topics, making them tangible, and distill them into a set of best practices for the curation of novel resources.

19 September 2017 in Journal of the Association for Information Science and Technology
Verified
Journal Article
Closed access
PDF file
GSGianmaria Silvello
Gianmaria Silvello

22 July 2022 in npj Digital Medicine
Verified
Journal Article
Open access
PDF file
NMNiccolo Marini
Niccolo Marini
SMStefano Marchesin
Stefano Marchesin
SOSebastian Otálora
Sebastian Otálora
MWMarek Wodzinski
Marek Wodzinski
ACAlessandro Caputo
Alessandro Caputo
Manfredo AtzoriManfredo Atzori
Manfredo Atzori
The digitalization of clinical workflows and the increasing performance of deep learning algorithms are paving the way towards new methods for tackling cancer diagnosis. However, the availability of medical specialists to annotate digitized images and free-text diagnostic reports does not scale with the need for large datasets required to train robust computer-aided diagnosis methods that can target the high variability of clinical cases and data produced. This work proposes and evaluates an approach to eliminate the need for manual annotations to train computer-aided diagnosis tools in digital pathology. The approach includes two components, to automatically extract semantically meaningful concepts from diagnostic reports and use them as weak labels to train convolutional neural networks (CNNs) for histopathology diagnosis. The approach is trained (through 10-fold cross-validation) on 3’769 clinical images and reports, provided by two hospitals and tested on over 11’000 images from private and publicly available datasets. The CNN, trained with automatically generated labels, is compared with the same architecture trained with manual labels. Results show that combining text analysis and end-to-end deep neural networks allows building computer-aided diagnosis tools that reach solid performance (micro-accuracy = 0.908 at image-level) based only on existing clinical data without the need for manual annotations.

7 July 2016
Verified
Conference Paper
Open access
PDF file
NFNicola Ferro
Nicola Ferro
GSGianmaria Silvello
Gianmaria Silvello
Topic variance has a greater effect on performances than system variance but it cannot be controlled by system developers who can only try to cope with it. On the other hand, system variance is important on its own, since it is what system developers may affect directly by changing system components and it determines the differences among systems. In this paper, we face the problem of studying system variance in order to better understand how much system components contribute to overall performances. To this end, we propose a methodology based on General Linear Mixed Model (GLMM) to develop statistical models able to isolate system variance, component effects as well as their interaction by relying on a Grid of Points (GoP) containing all the combinations of analysed components. We apply the proposed methodology to the analysis of TREC Ad-hoc data in order to show how it works and discuss some interesting outcomes of this new kind of analysis. Finally, we extend the analysis to different evaluation measures, showing how they impact on the sources of variance.

28 May 2016 in International Journal on Digital Libraries
Verified
Journal Article
Closed access
PDF file
GSGianmaria Silvello
Gianmaria Silvello
GBGeorgeta Bordea
Georgeta Bordea
NFNicola Ferro
Nicola Ferro
PBPaul Buitelaar
Paul Buitelaar
TBToine Bogers
Toine Bogers

1 December 2021 in Quantitative Science Studies
Verified
Journal Article
Open access
PDF file
PBPeter Buneman
Peter Buneman
DDDennis Dosso
Dennis Dosso
MLMatteo Lissandrini
Matteo Lissandrini
GSGianmaria Silvello
Gianmaria Silvello
The citation graph is a computational artifact that is widely used to represent the domain of published literature. It represents connections between published works, such as citations and authorship. Among other things, the graph supports the computation of bibliometric measures such as h-indexes and impact factors. There is now an increasing demand that we should treat the publication of data in the same way that we treat conventional publications. In particular, we should cite data for the same reasons that we cite other publications. In this paper we discuss what is needed for the citation graph to represent data citation. We identify two challenges: to model the evolution of credit appropriately (through references) over time and to model data citation not only to a data set treated as a single object but also to parts of it. We describe an extension of the current citation graph model that addresses these challenges. It is built on two central concepts: citable units and reference subsumption. We discuss how this extension would enable data citation to be represented within the citation graph and how it allows for improvements in current practices for bibliometric computations, both for scientific publications and for data.