5 citations · 7 across the 10 of their papers we have counts for
6 papers · 1 filter
Graph data augmentation with Gromow-Wasserstein Barycenters
Andrea Ponti
Graphs are ubiquitous in various fields, and deep learning methods have been successful applied in graph classification tasks. However, building large and diverse graph datasets fo…
A Bayesian approach for prompt optimization in pre-trained language models
Antonio Sabbatella, Andrea Ponti, Antonio Candelieri +2
A prompt is a sequence of symbol or tokens, selected from a vocabulary according to some rule, which is prepended/concatenated to a textual query. A key problem is how to select th…
Gaussian Process regression over discrete probability measures: on the non-stationarity relation between Euclidean and Wasserstein Squared Exponential Kernels
Antonio Candelieri, Andrea Ponti, Francesco Archetti
Gaussian Process regression is a kernel method successfully adopted in many real-life applications. Recently, there is a growing interest on extending this method to non-Euclidean…
BORA: Bayesian Optimization for Resource Allocation
Antonio Candelieri, Andrea Ponti, Francesco Archetti
Optimal resource allocation is gaining a renewed interest due its relevance as a core problem in managing, over time, cloud and high-performance computing facilities. Semi-Bandit F…
Fair and Green Hyperparameter Optimization via Multi-objective and Multiple Information Source Bayesian Optimization
Antonio Candelieri, Andrea Ponti, Francesco Archetti
There is a consensus that focusing only on accuracy in searching for optimal machine learning models amplifies biases contained in the data, leading to unfair predictions and decis…
Multi-Task Learning on Networks
Andrea Ponti
The multi-task learning (MTL) paradigm can be traced back to an early paper of Caruana (1997) in which it was argued that data from multiple tasks can be used with the aim to obtai…