New algorithms for neutrinos and fake-news

The IceCube Lab -2012 Credit: Sven Lidstrom, IceCube/NSF
The IceCube Lab -2012 Credit: Sven Lidstrom, IceCube/NSF

Institutional Communication Service

21 January 2019

Do neutrinos, the elementary particles, have something in common with fake news on social media? The peculiar and positive answer comes from a group of researchers at USI Institute of Computational Science, and it shows how both their behaviour can be represented using the same data structure. Such structure is based on a non-Euclidean geometry and can be studied through a new class of algorithms: the Graph Convolutional Neural Networks (GCNN).

Such algorithms are highly complex mathematical models, and the research work carried out by Federico Monti, member of Prof. Michael Bronstein group, earned him the award for the best scientific contribution assigned by ICMLA, the most important international conference in the field.

Monti, in collaboration with other colleagues from New York University, Berkeley and Imperial College, had the opportunity to collaborate with the Lawrence Berkley National Laboratory on data acquired by the IceCube Neutrino Observatory at the South Pole. - Thanks to 60 sensors positioned at a depth of more than two kilometres in the Antarctic ice, the powerful polar observatory studies the behaviour of neutrinos with the aim of opening new research scenarios regarding the birth and development of the universe.

According to Federico Monti: “It is extremely difficult to effectively process the data collected by the IceCube detectors with traditional Deep Learning Algorithms (which are useful to process data defined on regular grids such as images, videos or audio messagges). The main obstacle lies in the irregularity of the network of sensors positioned in the observatory, presenting different levels of density in different regions of the ice. The new GCNN algorithms are ideal for this purpose, as they are designed to address irregular structures such as graphs or surfaces”.

From the South Pole to social network, the same data structure can also be found in the dynamics in which fake news spread on the internet: the spin-off Fabula Al, founded at USI by Prof. Bronstein, Federico Monti, and Dr. Davide Eynard is working at an innovative analysis systems, which could, in the near future prevent the dissemination of fake news online.


The ICMLA award:
Fabula AI: