Browsing by Author "Pujol Perich, David"
Now showing items 1-9 of 9
-
Framework for fast prototyping of graph neural networks
(Universitat Politècnica de Catalunya, 2020-06-21)
Bachelor thesis
Open AccessAl llarg dels últims anys, hem pogut comprovar el gran potencial que tenen les Graph Neural Networks (GNN) al aplicar-se a una gran varietat de problemes que es formalitzen en forma de grafs (e.g xarxes de telecomunicacions, ... -
IGNNITION: A framework for fast prototyping of Graph Neural Networks
(2021)
Conference report
Open AccessRecent years have seen the vast potential of Graph Neural Networks (GNN) in many fields where data is structured as graphs (e.g., chemistry, logistics). However, implementing a GNN prototype is still a cumbersome task that ... -
IGNNITION: Bridging the gap between graph neural networks and networking systems
(2021-11)
Article
Open AccessRecent years have seen the vast potential of graph neural networks (GNN) in many fields where data is structured as graphs (e.g., chemistry, recommender systems). In particular, GNNs are becoming increasingly popular in ... -
IGNNITION: fast prototyping of graph neural networks for communication networks
(Association for Computing Machinery (ACM), 2021)
Conference lecture
Open AccessGraph Neural Networks (GNN) have recently exploded in the Machine Learning area as a novel technique for modeling graph-structured data. This makes them especially suitable for applications in the networking field, as ... -
NetXplain: Real-time explainability of graph neural networks applied to computer networks
(2021)
Conference report
Open AccessRecent advancements in Deep Learning (DL) have revolutionized the way we can efficiently tackle complex optimization problems. However, existing DL-based solutions are often considered as black boxes due to their high inner ... -
NetXplain: Real-time explainability of graph neural networks applied to networking
(2021-08-05)
Article
Open AccessRecent advancements in Deep Learning (DL) have revolutionized the way we can efficiently tackle complex optimization problems. However, existing DL-based solutions are often considered as black boxes with high inner ... -
The graph neural networking challenge: a worldwide competition for education in AI/ML for networks
(2021-07-01)
Article
Open AccessDuring the last decade, Machine Learning (ML) has increasingly become a hot topic in the field of Computer Networks and is expected to be gradually adopted for a plethora of control, monitoring and management tasks in ... -
Understanding and improving self-attention mechanisms
(Universitat Politècnica de Catalunya, 2022-07-10)
Master thesis
Restricted access - author's decision
Covenantee: École polytechnique fédérale de LausanneRecent years have seen the vast potential of the Transformer model, as it is arguably the first general-purpose architecture in the sense that achieves state-of-the-art performance in numerous fields –e.g., Computer Vision, ... -
Unveiling the potential of graph neural networks for robust intrusion detection
(2021)
Conference report
Open AccessThe last few years have seen an increasing wave of attacks with serious economic and privacy damages, which evinces the need for accurate Network Intrusion Detection Systems (NIDS). Recent works propose the use of Machine ...
