Transferring model structure in Bayesian transfer learning for Gaussian process regression

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F22%3A00559729" target="_blank" >RIV/67985556:_____/22:00559729 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21230/22:00364107

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S095070512200418X?via%3Dihub" target="_blank" >https://www.sciencedirect.com/science/article/pii/S095070512200418X?via%3Dihub</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.knosys.2022.108875" target="_blank" >10.1016/j.knosys.2022.108875</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Transferring model structure in Bayesian transfer learning for Gaussian process regression

Popis výsledku v původním jazyce

Bayesian transfer learning (BTL) is defined in this paper as the task of conditioning a target probability distribution on a transferred source distribution. The target globally models the interaction between the source and target, and conditions on a probabilistic data predictor made available by an independent local source modeller. Fully probabilistic design is adopted to solve this optimal decision-making problem in the target. By successfully transferring higher moments of the source, the target can reject unreliable source knowledge (i.e. it achieves robust transfer). This dual-modeller framework means that the source’s local processing of raw data into a transferred predictive distribution – with compressive possibilities – is enriched by (the possible expertise of) the local source model. In addition, the introduction of the global target modeller allows correlation between the source and target tasks – if known to the target – to be accounted for. Important consequences emerge. Firstly, the new scheme attains the performance of fully modelled (i.e. conventional) multitask learning schemes in (those rare) cases where target model misspecification is avoided. Secondly, and more importantly, the new dual-modeller framework is robust to the model misspecification that undermines conventional multitask learning. We thoroughly explore these issues in the key context of interacting Gaussian process regression tasks. Experimental evidence from both synthetic and real data settings validates our technical findings: that the proposed BTL framework enjoys robustness in transfer while also being robust to model misspecification.

Název v anglickém jazyce

Transferring model structure in Bayesian transfer learning for Gaussian process regression

Popis výsledku anglicky

Bayesian transfer learning (BTL) is defined in this paper as the task of conditioning a target probability distribution on a transferred source distribution. The target globally models the interaction between the source and target, and conditions on a probabilistic data predictor made available by an independent local source modeller. Fully probabilistic design is adopted to solve this optimal decision-making problem in the target. By successfully transferring higher moments of the source, the target can reject unreliable source knowledge (i.e. it achieves robust transfer). This dual-modeller framework means that the source’s local processing of raw data into a transferred predictive distribution – with compressive possibilities – is enriched by (the possible expertise of) the local source model. In addition, the introduction of the global target modeller allows correlation between the source and target tasks – if known to the target – to be accounted for. Important consequences emerge. Firstly, the new scheme attains the performance of fully modelled (i.e. conventional) multitask learning schemes in (those rare) cases where target model misspecification is avoided. Secondly, and more importantly, the new dual-modeller framework is robust to the model misspecification that undermines conventional multitask learning. We thoroughly explore these issues in the key context of interacting Gaussian process regression tasks. Experimental evidence from both synthetic and real data settings validates our technical findings: that the proposed BTL framework enjoys robustness in transfer while also being robust to model misspecification.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA18-15970S" target="_blank" >GA18-15970S: Optimální zpracování externí stochastické znalosti vyjádřené pomocí pravděpodobnostních distribucí</a><br>

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Knowledge-Based System

ISSN

0950-7051

e-ISSN

1872-7409

Svazek periodika

251

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

12

Strana od-do

108875

Kód UT WoS článku

000827395000014

EID výsledku v databázi Scopus

2-s2.0-85132945410