TY - GEN
T1 - Few-shot and transfer learning with manifold distributed datasets
AU - Qayyumi, Sayed Waleed
AU - Park, Laurence A.F.
AU - Obst, Oliver
PY - 2024
Y1 - 2024
N2 - A manifold distributed dataset with limited labels makes it difficult to train a high-mean accuracy classifier. Transfer learning is beneficial in such circumstances. For transfer learning to succeed, the target and base datasets should have a similar manifold structure. A novel method is presented in this paper for determining the similarity between two manifold structures. To determine whether target and base datasets have similar manifolds and are suitable for transfer learning, this method can be used. A novel few-shot algorithm is then presented that uses transfer learning to classify manifold distributed datasets with a limited number of labels. Using the base and target datasets, the manifold structure and its relevant label distribution are learned. Using this information in combination with the few labels and unlabeled data from the target dataset, we can develop a classifier with high mean accuracy.
AB - A manifold distributed dataset with limited labels makes it difficult to train a high-mean accuracy classifier. Transfer learning is beneficial in such circumstances. For transfer learning to succeed, the target and base datasets should have a similar manifold structure. A novel method is presented in this paper for determining the similarity between two manifold structures. To determine whether target and base datasets have similar manifolds and are suitable for transfer learning, this method can be used. A novel few-shot algorithm is then presented that uses transfer learning to classify manifold distributed datasets with a limited number of labels. Using the base and target datasets, the manifold structure and its relevant label distribution are learned. Using this information in combination with the few labels and unlabeled data from the target dataset, we can develop a classifier with high mean accuracy.
KW - Few-shot learning
KW - manifold distributed datasets
KW - measuring similarity
KW - Transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85180623157&partnerID=8YFLogxK
UR - https://go.openathens.net/redirector/westernsydney.edu.au?url=https://doi.org/10.1007/978-981-99-8696-5_10
U2 - 10.1007/978-981-99-8696-5_10
DO - 10.1007/978-981-99-8696-5_10
M3 - Conference Paper
AN - SCOPUS:85180623157
SN - 9789819986958
T3 - Communications in Computer and Information Science
SP - 137
EP - 149
BT - Data Science and Machine Learning
A2 - Benavides-Prado, Diana
A2 - Erfani, Sarah
A2 - Fournier-Viger, Philippe
A2 - Boo, Yee Ling
A2 - Koh, Yun Sing
PB - Springer Nature Singapore
CY - Singapore
T2 - 21st Australasian Conference on Data Science and Machine Learning, AusDM 2023
Y2 - 11 December 2023 through 13 December 2023
ER -