no code implementations • 31 May 2023 • Domenico Tortorella, Alessio Micheli
Graph neural networks compute node representations by performing multiple message-passing steps that consist in local aggregations of node features.
1 code implementation • Neurocomputing 2023 • Alessio Micheli, Domenico Tortorella
Node classification tasks on graphs are addressed via fully-trained deep message-passing models that learn a hierarchy of node representations via multiple aggregations of a node's neighbourhood.
Ranked #1 on Node Classification on genius (1:1 Accuracy metric)
no code implementations • 13 Dec 2022 • Domenico Tortorella, Alessio Micheli
Recent works have investigated the role of graph bottlenecks in preventing long-range information propagation in message-passing graph neural networks, causing the so-called `over-squashing' phenomenon.
no code implementations • 30th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) 2022 • Domenico Tortorella, Alessio Micheli
Graph Echo State Networks (GESN) have already demonstrated their efficacy and efficiency in graph classification tasks.
Ranked #5 on Node Classification on Pubmed Full-supervised
1 code implementation • 16 Oct 2021 • Domenico Tortorella, Alessio Micheli
Dynamic temporal graphs represent evolving relations between entities, e. g. interactions between social network users or infection spreading.