Show simple item record

dc.contributor.authorAgarwal, Rohit
dc.contributor.authorPrasad, Dilip Kumar
dc.contributor.authorHorsch, Ludwig Alexander
dc.contributor.authorGupta, Deepak Kumar
dc.date.accessioned2024-03-19T14:35:39Z
dc.date.available2024-03-19T14:35:39Z
dc.date.issued2023
dc.description.abstractMany real-world applications based on online learning produce streaming data that is haphazard in nature, i.e., contains missing features, features becoming obsolete in time, the appearance of new features at later points in time and a lack of clarity on the total number of input features. These challenges make it hard to build a learnable system for such applications, and almost no work exists in deep learning that addresses this issue. In this paper, we present Aux-Drop, an auxiliary dropout regularization strategy for online learning that handles the haphazard input features in an effective manner. Aux-Drop adapts the conventional dropout regularization scheme for the haphazard input feature space ensuring that the final output is minimally impacted by the chaotic appearance of such features. It helps to prevent the co-adaptation of especially the auxiliary and base features, as well as reduces the strong dependence of the output on any of the auxiliary inputs of the model. This helps in better learning for scenarios where certain features disappear in time or when new features are to be modelled. The efficacy of Aux-Drop has been demonstrated through extensive numerical experiments on SOTA benchmarking datasets that include Italy Power Demand, HIGGS, SUSY and multiple UCI datasets. The code is available at https://github.com/Rohit102497/Aux-Drop.en_US
dc.descriptionSource at <a href=https://www.jmlr.org/tmlr/index.html>https://www.jmlr.org/tmlr/index.html</a>.en_US
dc.identifier.citationAgarwal R, Prasad DK, Horsch A, Gupta. Aux-Drop: Handling Haphazard Inputs in Online Learning Using Auxiliary Dropouts. Transactions on Machine Learning Research (TMLR). 2023en_US
dc.identifier.cristinIDFRIDAID 2184909
dc.identifier.issn2835-8856
dc.identifier.urihttps://hdl.handle.net/10037/33194
dc.language.isoengen_US
dc.publisherTransactions on Machine Learning Research (TMLR)en_US
dc.relation.journalTransactions on Machine Learning Research (TMLR)
dc.rights.accessRightsopenAccessen_US
dc.rights.holderCopyright 2023 The Author(s)en_US
dc.titleAux-Drop: Handling Haphazard Inputs in Online Learning Using Auxiliary Dropoutsen_US
dc.type.versionacceptedVersionen_US
dc.typeJournal articleen_US
dc.typeTidsskriftartikkelen_US
dc.typePeer revieweden_US


File(s) in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record