3 papers
cs.LG2026
Sinkhorn doubly stochastic attention rank decay analysis
Michela Lapenna, Rita Fioresi, Bahman Gharesifard
The self-attention mechanism is central to the success of Transformer architectures. However, standard row-stochastic attention has been shown to suffer from significant signal deg…
stat.ML2025
How do Probabilistic Graphical Models and Graph Neural Networks Look at Network Data?
Michela Lapenna, Caterina De Bacco
Graphs are a powerful data structure for representing relational data and are widely used to describe complex real-world systems. Probabilistic Graphical Models (PGMs) and Graph Ne…
cs.LG2023
Geometric Deep Learning: a Temperature Based Analysis of Graph Neural Networks
M. Lapenna, F. Faglioni, F. Zanchetta +1
We examine a Geometric Deep Learning model as a thermodynamic system treating the weights as non-quantum and non-relativistic particles. We employ the notion of temperature previou…