11 citations · 22 across the 8 of their papers we have counts for
4 papers · 1 filter
Model Selection with Model Zoo via Graph Learning
Ziyu Li, Hilco van der Wilk, Danning Zhan +3
Pre-trained deep learning (DL) models are increasingly accessible in public repositories, i.e., model zoos. Given a new prediction task, finding the best model to fine-tune can be…
Active Hybrid Classification
Evgeny Krivosheev, Fabio Casati, Alessandro Bozzon
Hybrid crowd-machine classifiers can achieve superior performance by combining the cost-effectiveness of automatic classification with the accuracy of human judgment. This paper sh…
Designing Evaluations of Machine Learning Models for Subjective Inference: The Case of Sentence Toxicity
Agathe Balayn, Alessandro Bozzon
Machine Learning (ML) is increasingly applied in real-life scenarios, raising concerns about bias in automatic decision making. We focus on bias as a notion of opinion exclusion, t…
Unfairness towards subjective opinions in Machine Learning
Agathe Balayn, Alessandro Bozzon, Zoltan Szlavik
Despite the high interest for Machine Learning (ML) in academia and industry, many issues related to the application of ML to real-life problems are yet to be addressed. Here we pu…