Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/134824
Type: | Conference paper |
Title: | Probabilistic task modelling for Meta-Learning |
Author: | Nguyen, C.C. Do, T.-T. Carneiro, G. |
Citation: | Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence (UAI 2021), as published in Proceedings of Machine Learning Research, 2021, vol.161, pp.781-791 |
Publisher: | Association For Uncertainty in Artificial Intelligence (AUAI) |
Publisher Place: | Vancouver BC Canada |
Issue Date: | 2021 |
Series/Report no.: | Proceedings of Machine Learning Research; 161 |
ISBN: | 9781713841548 |
ISSN: | 2640-3498 2640-3498 |
Conference Name: | Conference of Uncertainty on Artificial Intelligence (UAI) (27 Jul 2021 - 30 Jul 2021 : online) |
Statement of Responsibility: | Cuong C. Nguyen, Thanh-Toan Do, Gustavo Carneiro |
Abstract: | We propose probabilistic task modelling – a generative probabilistic model for collections of tasks used in meta-learning. The proposed model combines variational auto-encoding and latent Dirichlet allocation to model each task as a mixture of Gaussian distribution in an embedding space. Such modelling provides an explicit representation of a task through its task-theme mixture. We present an efficient approximation inference technique based on variational inference method for empirical Bayes parameter estimation. We perform empirical evaluations to validate the task uncertainty and task distance produced by the proposed method through correlation diagrams of the prediction accuracy on testing tasks. We also carry out experiments of task selection in meta-learning to demonstrate how the task relatedness inferred from the proposed model help to facilitate meta-learning algorithms. |
Keywords: | cs.LG |
Rights: | © The authors and PMLR 2023. MLResearchPress |
Grant ID: | http://purl.org/au-research/grants/arc/DP180103232 http://purl.org/au-research/grants/arc/FT190100525 |
Published version: | https://proceedings.mlr.press/v161/nguyen21b.html |
Appears in Collections: | Australian Institute for Machine Learning publications Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.