Probabilistic task modelling for Meta-Learning

Simple item page
dc.contributor.authorNguyen, C.C.
dc.contributor.authorDo, T.-T.
dc.contributor.authorCarneiro, G.
dc.contributor.conferenceConference of Uncertainty on Artificial Intelligence (UAI) (27 Jul 2021 - 30 Jul 2021 : online)
dc.date.issued2021
dc.description.abstractWe 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.
dc.description.statementofresponsibilityCuong C. Nguyen, Thanh-Toan Do, Gustavo Carneiro
dc.identifier.citationProceedings 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
dc.identifier.isbn9781713841548
dc.identifier.issn2640-3498
dc.identifier.issn2640-3498
dc.identifier.orcidNguyen, C.C. [0000-0003-2672-6291]
dc.identifier.orcidCarneiro, G. [0000-0002-5571-6220]
dc.identifier.urihttps://hdl.handle.net/2440/134824
dc.language.isoen
dc.publisherAssociation For Uncertainty in Artificial Intelligence (AUAI)
dc.publisher.placeVancouver BC Canada
dc.relation.granthttp://purl.org/au-research/grants/arc/DP180103232
dc.relation.granthttp://purl.org/au-research/grants/arc/FT190100525
dc.relation.ispartofseriesProceedings of Machine Learning Research; 161
dc.rights© The authors and PMLR 2023. MLResearchPress
dc.source.urihttps://proceedings.mlr.press/v161/nguyen21b.html
dc.subjectcs.LG
dc.titleProbabilistic task modelling for Meta-Learning
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Computer Science publications
Australian Institute for Machine Learning publications