報告人：Cesare Alippi 教授
Neural Graph Processing: an embedding-based approach
Many fields, like physics, neuroscience, chemistry, and sociology, investigate phenomena by processing multivariate measurements advantageously represented as a sequence of attributed graphs. Graphs come in different forms, with variable attributes, topology, and ordering, making it difficult to perform a mathematical analysis in the graph space. Within this framework, we are interested in processing graph datastreams to solve applications e.g., detect structural changes in the graph sequence, a situation associated with time variance, faults, anomalies or events of interest as well as design sophisticated processing like those requested by predictors.
On the change detection front, theoretic results show that, under mild hypotheses, the confidence level of an event detected in the graph domain can be associated with another confidence level in an embedding space; this enables the identification of events in the graph domain by investigating embedded data. The opposite holds. However, evaluation of distances between graphs and identification of an appropriate embedding for the problem at hand are far from being trivial tasks with deep adversarial learning approaches and constant curvature manifold transformation showing to be appropriate transformations able to solve the problem. Deep autoregressive predictive models can then be designed to operate directly on graphs, hence providing the building blocks for other future sophisticated neural processing.
CESARE ALIPPI received the degree in electronic engineering cum laude in 1990 and the PhD in 1995 from Politecnico di Milano, Italy. Currently, he is a Professor with the Politecnico di Milano, Milano, Italy and Università della Svizzera italiana, Lugano, Switzerland. He is a visiting professor at the University of Kobe, Japan, the University of Guangzhou, China and Consultant Professor at the Northwestern Polytechnic in Xi’An, China. He has been a visiting researcher at UCL (UK), MIT (USA), ESPCI (F), CASIA (RC), A*STAR (SIN).
Alippi is an IEEE Fellow, Member of the Administrative Committee of the IEEE Computational Intelligence Society, Board of Governors member of the International Neural Network Society, Board of Directors member of the European Neural Network Society, Past Vice-President education of the IEEE Computational Intelligence Society, past associate editor of the IEEE Transactions on Emerging topics in computational intelligence, the IEEE Computational Intelligence Magazine, the IEEE-Transactions on Instrumentation and Measurements, the IEEE-Transactions on Neural Networks.
In 2018 he received IEEE CIS Outstanding Computational Intelligence Magazine Award, the 2016 Gabor award from the International Neural Networks Society and the IEEE Computational Intelligence Society Outstanding Transactions on Neural Networks and Learning Systems Paper Award; in 2013 the IBM Faculty award; in 2004 the IEEE Instrumentation and Measurement Society Young Engineer Award.
Current research activity addresses adaptation and learning in non-stationary environments, graph learning and Intelligence for embedded, IoT and cyber-physical systems.
He holds 8 patents, has published one monograph book, 7 edited books and about 200 papers in international journals and conference proceedings.