Prijava

Poziv na predavanje "Causal Temporal GNNs as Decentralized Memory Networks"

Odjel za komunikacije Hrvatske sekcije IEEE poziva Vas na predavanje

"Causal Temporal GNNs as Decentralized Memory Networks"

koje će održati Lodovico Giaretta, istraživač instituta RISE Research Institutes of Sweden, u srijedu, 8. studenog 2023. godine, s početkom u 16.30 sati u Sivoj vijećnici Fakulteta elektrotehnike i računarstva Sveučilišta u Zagrebu, Unska 3.

Predavanje će se održati na engleskom jeziku, a predviđeno trajanje s raspravom je 60 minuta. Predavanje je otvoreno za sve zainteresirane, a posebno pozivamo studente.

Više informacija o predavanju i predavaču pročitajte u opširnijem sadržaju obavijesti.

Sažetak predavanja:

In this talk, we will review the topic of causal temporal GNNs as the key enabler of scalable inference on dynamic graphs, and we will show a connection to the concept of memory networks. As a representative use-case, we will discuss IoT security, and we will introduce our lightweight causal GNN/memory network architecture for real-time IoT botnet detection.

We will then move to the core of our research, which focuses on decentralizing inference on dynamic graphs. We will show how we can deploy our lightweight botnet detector in a decentralized fashion, running directly on the IoT devices, thus avoiding the need for unscalable central monitoring of the IoT traffic. Finally, we will present our wider vision for decentralized, collaborative AI at the edge using GNNs.

Biografija predavača:

Lodovico Giaretta is a researcher in the Department of Computer Science, RISE Research Institutes of Sweden. He obtained a double M.Sc. degree in Cloud Computing from Technische Universitaet Berlin and the Royal Institute of Technology, Stockholm, in 2019. In 2023, he obtained his Ph.D. degree in Information and Communication Technology from the Royal Institute of Technology, Stockholm, with a thesis titled "Towards Decentralized Graph Learning".

Lodovico's research focuses on achieving "decentralized graph learning", where a network of edge/IoT devices can continuously, dynamically learn and collaborate based on their interactions with their neighbours. Due to the significant interdisciplinarity of this vision, Lodovico's research interest range from decentralized ML to privacy-preserving computation techniques, graph representation learning approaches, edge computing, and ML security.