DC Field | Value | Language |
---|---|---|
dc.contributor.author | KIM, DONGWOO | - |
dc.contributor.author | Park, Moon Jeong | - |
dc.contributor.author | Ok, Jungseul | - |
dc.contributor.author | JEON, YO SEB | - |
dc.date.accessioned | 2022-08-24T06:20:10Z | - |
dc.date.available | 2022-08-24T06:20:10Z | - |
dc.date.created | 2022-08-23 | - |
dc.date.issued | 2022-06-27 | - |
dc.identifier.issn | 2157-8095 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/113551 | - |
dc.description.abstract | Deep learning-based symbol detector gains increasing attention due to the simple algorithm design than the traditional model-based algorithms such as Viterbi and BCJR. The supervised learning framework is often employed to train a model, where true symbols are necessary. There are two major limitations in the supervised approaches: a) a model needs to be retrained from scratch when new train symbols come to adapt to a new channel status, and b) the length of the training symbols needs to be longer than a certain threshold to make the model generalize well on unseen symbols. To overcome these challenges, we propose a meta-learning-based self-supervised symbol detector named MetaSSD. Our contribution is two-fold: a) meta-learning helps the model adapt to a new channel environment based on experience with various meta-training environments, and b) self-supervised learning helps the model to use relatively less supervision than the previously suggested learning-based detectors. In experiments, MetaSSD outperforms OFDM-MMSE with noisy channel information and shows comparable results with BCJR. Further ablation studies show the necessity of each component in our framework. © 2022 IEEE. | - |
dc.publisher | IEEE | - |
dc.relation.isPartOf | International Symposium on Information Theory (ISIT) | - |
dc.title | MetaSSD: Meta-Learned Self-Supervised Detection | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.identifier.bibliographicCitation | International Symposium on Information Theory (ISIT) | - |
dc.citation.conferenceDate | 2022-06-26 | - |
dc.citation.conferencePlace | FI | - |
dc.citation.title | International Symposium on Information Theory (ISIT) | - |
dc.contributor.affiliatedAuthor | KIM, DONGWOO | - |
dc.contributor.affiliatedAuthor | Park, Moon Jeong | - |
dc.contributor.affiliatedAuthor | Ok, Jungseul | - |
dc.contributor.affiliatedAuthor | JEON, YO SEB | - |
dc.identifier.scopusid | 2-s2.0-85136293056 | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.