Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
An Experimental Study of the Sample Complexity of Domain Adaptation Alan Uyarlamada Örnek Karmaşikliǧinin Deneysel Incelemesi
Date
2023-01-01
Author
Karaca, Huseyin
Akgül, Özlem
Arslan, Ömer Faruk
Aydemir, Atilla Can
Aydin, Firdevs Su
Ünsal, Enes Ata
Vural, Elif
Metadata
Show full item record
This work is licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Item Usage Stats
58
views
0
downloads
Cite This
In this study, we experimentally investigate the sample complexity of semi supervised domain adaptation with deep neural networks. Sweeping the hyper-parameters of domain adaptation neural networks relying on the MMD distance measure and the number of training samples in a controlled manner, we study the test accuracy of the target samples. Both labeled and unlabeled samples from the source and the target domains are used as inputs to the neural network in the experiments. Our experimental findings suggest that the minimum number of samples required for guaranteeing a fixed experimental target accuracy level increases quadratically with both the number and the dimension of the MMD layers in the network used for aligning the source and the target domains. We observe that this relationship is in harmony with some well-known theoretical bounds in the classical deep learning literature. Meanwhile, we also investigate the optimal weighting strategy between the classification loss functions of the source and the target samples, concluding that increasing the weight of the target loss improves the performance as the number of target samples increases.
Subject Keywords
deep neural networks
,
Domain adaptation
,
MMD distance
,
sample complexity
,
target accuracy
URI
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85173546487&origin=inward
https://hdl.handle.net/11511/105695
DOI
https://doi.org/10.1109/siu59756.2023.10223790
Conference Name
31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023
Collections
Department of Electrical and Electronics Engineering, Conference / Seminar
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
H. Karaca et al., “An Experimental Study of the Sample Complexity of Domain Adaptation Alan Uyarlamada Örnek Karmaşikliǧinin Deneysel Incelemesi,” presented at the 31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023, İstanbul, Türkiye, 2023, Accessed: 00, 2023. [Online]. Available: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85173546487&origin=inward.