Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Barbero, Federico"'
Autor:
Barbero, Federico, Banino, Andrea, Kapturowski, Steven, Kumaran, Dharshan, Araújo, João G. M., Vitvitskyi, Alex, Pascanu, Razvan, Veličković, Petar
We study how information propagates in decoder-only Transformers, which are the architectural backbone of most existing frontier large language models (LLMs). We rely on a theoretical signal propagation analysis -- specifically, we analyse the repres
Externí odkaz:
http://arxiv.org/abs/2406.04267
The dominant paradigm for learning on graph-structured data is message passing. Despite being a strong inductive bias, the local message passing mechanism suffers from pathological issues such as over-smoothing, over-squashing, and limited node-level
Externí odkaz:
http://arxiv.org/abs/2405.15540
Autor:
Barbero, Federico, Velingker, Ameya, Saberi, Amin, Bronstein, Michael, Di Giovanni, Francesco
Graph Neural Networks (GNNs) are popular models for machine learning on graphs that typically follow the message-passing paradigm, whereby the feature of a node is updated recursively upon aggregating information over its neighbors. While exchanging
Externí odkaz:
http://arxiv.org/abs/2310.01668
Autor:
Di Giovanni, Francesco, Giusti, Lorenzo, Barbero, Federico, Luise, Giulia, Lio', Pietro, Bronstein, Michael
Message Passing Neural Networks (MPNNs) are instances of Graph Neural Networks that leverage the graph to send messages over the edges. This inductive bias leads to a phenomenon known as over-squashing, where a node feature is insensitive to informat
Externí odkaz:
http://arxiv.org/abs/2302.02941
Graph Neural Networks usually rely on the assumption that the graph topology is available to the network as well as optimal for the downstream task. Latent graph inference allows models to dynamically learn the intrinsic graph structure of problems w
Externí odkaz:
http://arxiv.org/abs/2211.16199
We demonstrate the applicability of model-agnostic algorithms for meta-learning, specifically Reptile, to GNN models in molecular regression tasks. Using meta-learning we are able to learn new chemical prediction tasks with only a few model updates,
Externí odkaz:
http://arxiv.org/abs/2209.13410
Autor:
Barbero, Federico, Bodnar, Cristian, Borde, Haitz Sáez de Ocáriz, Bronstein, Michael, Veličković, Petar, Liò, Pietro
A Sheaf Neural Network (SNN) is a type of Graph Neural Network (GNN) that operates on a sheaf, an object that equips a graph with vector spaces over its nodes and edges and linear maps between these spaces. SNNs have been shown to have useful theoret
Externí odkaz:
http://arxiv.org/abs/2206.08702
Machine learning for malware classification shows encouraging results, but real deployments suffer from performance degradation as malware authors adapt their techniques to evade detection. This phenomenon, known as concept drift, occurs as new malwa
Externí odkaz:
http://arxiv.org/abs/2010.03856