Back to Search

Performance analysis of meta-learning based bayesian deep kernel transfer methods for regression tasks

Title	Performance analysis of meta-learning based bayesian deep kernel transfer methods for regression tasks
Author	Savaşlı, Ahmet Çağatay, Tütüncü, Damla, Ndigande, Alain Patrick, Özer, Sedat
Publication Date:	2023
Publication Place	- IEEE
Subject	Deep kernel transfer, Few-shot learning, Kernel learning, Meta-learning, Regression
Type	Document
Language	English
Digital	Yes
Manuscript	No
Library:	Özyeğin University
Library Asset ID	2-s2.0-85173554810
Record ID	2566dcf4-ecca-490e-ab6d-ba9fa28c9fa9
Library Location	Computer Science
Date	2023
Sample Text	Meta-learning aims to apply existing models on new tasks where the goal is 'learning to learn' so that learning from a limited amount of labeled data or learning in a short amount of time is possible. Deep Kernel Transfer (DKT) is a recently proposed meta-learning approach based on Bayesian framework. DKT's performance depends on the used kernel functions and it has two implementations, namely DKT and GPNet. In this paper, we use a large set of kernel functions on both DKT and GPNet implementations for two regression tasks to study their performances and train them under different optimizers. Furthermore, we compare the training time of both implementations to clarify the ambiguity in terms of which algorithm runs faster for the regression based tasks.
DOI	10.1109/SIU59756.2023.10224015

View in source Özyeğin University Özyeğin University - Historical works, archives, and periodicals search engine

Özyeğin University

Performance analysis of meta-learning based bayesian deep kernel transfer methods for regression tasks

Author Savaşlı, Ahmet Çağatay, Tütüncü, Damla, Ndigande, Alain Patrick, Özer, Sedat

Publication Date 2023

Publication Place - IEEE

Subject Deep kernel transfer, Few-shot learning, Kernel learning, Meta-learning, Regression

Type Document

Language English

Digital Yes

Manuscript No

Library Özyeğin University

Library Asset ID 2-s2.0-85173554810

Record ID 2566dcf4-ecca-490e-ab6d-ba9fa28c9fa9

Library Location Computer Science

Date 2023

Sample Text Meta-learning aims to apply existing models on new tasks where the goal is 'learning to learn' so that learning from a limited amount of labeled data or learning in a short amount of time is possible. Deep Kernel Transfer (DKT) is a recently proposed meta-learning approach based on Bayesian framework. DKT's performance depends on the used kernel functions and it has two implementations, namely DKT and GPNet. In this paper, we use a large set of kernel functions on both DKT and GPNet implementations for two regression tasks to study their performances and train them under different optimizers. Furthermore, we compare the training time of both implementations to clarify the ambiguity in terms of which algorithm runs faster for the regression based tasks.

DOI 10.1109/SIU59756.2023.10224015