Massimiliano Patacchiola — accepted AI-conference papers

2023

FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification

Aliaksandra Shysheya, John F Bronskill, Massimiliano Patacchiola, Sebastian Nowozin, Richard E Turner

ICLR 2023poster

Modern deep learning systems are increasingly deployed in situations such as personalization and federated learning where it is necessary to support i) learning on small amounts of data, and ii) communication efficient distributed training protocols. In this work, we develop FiLM Transfer (FiT) whic…

Cited by 29 Source ↗PDF ↗code ↗Scholar ↗

2022

Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification

Massimiliano Patacchiola, John F Bronskill, Aliaksandra Shysheya, Katja Hofmann, Sebastian Nowozin, Richard E Turner

NeurIPS 2022accept

Recent years have seen a growth in user-centric applications that require effective knowledge transfer across tasks in the low-data regime. An example is personalization, where a pretrained system is adapted by learning on small amounts of labeled data belonging to a specific user. This setting requ…

Cited by 16 Source ↗PDF ↗code ↗Scholar ↗

2021

Memory Efficient Meta-Learning with Large Images

John F Bronskill, Daniela Massiceti, Massimiliano Patacchiola, Katja Hofmann, Sebastian Nowozin, Richard E Turner

NeurIPS 2021poster

Meta learning approaches to few-shot classification are computationally efficient at test time, requiring just a few optimization steps or single forward pass to learn a new task, but they remain highly memory-intensive to train. This limitation arises because a task's entire support set, which can…

Cited by 26 Source ↗PDF ↗Scholar ↗

2021

Non-Gaussian Gaussian Processes for Few-Shot Regression

Marcin Sendera, Jacek Tabor, Aleksandra Nowak, Andrzej Bedychaj, Massimiliano Patacchiola, Tomasz Trzcinski +2

NeurIPS 2021poster

Gaussian Processes (GPs) have been widely used in machine learning to model distributions over functions, with applications including multi-modal regression, time-series prediction, and few-shot learning. GPs are particularly useful in the last application since they rely on Normal distributions and…

Cited by 20 Source ↗PDF ↗code ↗Scholar ↗

2020

Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels

Massimiliano Patacchiola, Jack Turner, Elliot J. Crowley, Michael O'Boyle, Amos J. Storkey

NeurIPS 2020spotlight

Recently, different machine learning methods have been introduced to tackle the challenging few-shot learning scenario that is, learning from a small labeled dataset related to a specific task. Common approaches have taken the form of meta-learning: learning to learn on the new problem given the old…

Cited by 172 Source ↗PDF ↗code ↗Scholar ↗

2020

Self-Supervised Relational Reasoning for Representation Learning

Massimiliano Patacchiola, Amos J. Storkey

NeurIPS 2020spotlight

In self-supervised learning, a system is tasked with achieving a surrogate objective by defining alternative targets on a set of unlabeled data. The aim is to build useful representations that can be used in downstream tasks, without costly manual annotation. In this work, we propose a novel self-su…

Cited by 77 Source ↗PDF ↗code ↗Scholar ↗

2019

Sample-efficient Deep Reinforcement Learning with Imaginary Rollouts for Human-Robot Interaction

Mohammad Thabet, Massimiliano Patacchiola, Angelo Cangelosi

IROS 2019poster

Deep reinforcement learning has proven to be a great success in allowing agents to learn complex tasks. However, its application to actual robots can be prohibitively expensive. Furthermore, the unpredictability of human behavior in human-robot interaction tasks can hinder convergence to a good poli…

Cited by 20 Source ↗Scholar ↗