Probabilistic task modelling for Meta-Learning

Date

2021

Authors

Nguyen, C.C.
Do, T.-T.
Carneiro, G.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

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

Statement of Responsibility

Cuong C. Nguyen, Thanh-Toan Do, Gustavo Carneiro

Conference Name

Conference of Uncertainty on Artificial Intelligence (UAI) (27 Jul 2021 - 30 Jul 2021 : online)

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.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

© The authors and PMLR 2023. MLResearchPress

License

Call number

Persistent link to this record