OCFL automatically picks the clustering round by detecting a rise in the p-norm of the pairwise cosine-distance matrix of client gradients, and with density-based clustering it recovers client cohorts earlier and more accurately than prior methods.
Evaluation of Saliency-based Explainability Method
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
A particular class of Explainable AI (XAI) methods provide saliency maps to highlight part of the image a Convolutional Neural Network (CNN) model looks at to classify the image as a way to explain its working. These methods provide an intuitive way for users to understand predictions made by CNNs. Other than quantitative computational tests, the vast majority of evidence to highlight that the methods are valuable is anecdotal. Given that humans would be the end-users of such methods, we devise three human subject experiments through which we gauge the effectiveness of these saliency-based explainability methods.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
One-Shot Clustering for Federated Learning Under Clustering-Agnostic Assumption
OCFL automatically picks the clustering round by detecting a rise in the p-norm of the pairwise cosine-distance matrix of client gradients, and with density-based clustering it recovers client cohorts earlier and more accurately than prior methods.