{"id":118468,"date":"2021-10-11T21:53:59","date_gmt":"2021-10-11T12:53:59","guid":{"rendered":"http:\/\/175.125.95.178\/ai-in-communication\/18468\/"},"modified":"2026-04-13T03:40:05","modified_gmt":"2026-04-12T18:40:05","slug":"18468","status":"publish","type":"ai-in-communication","link":"http:\/\/ee.presscat.kr\/en\/ai-in-communication\/18468\/","title":{"rendered":"Learning to Demodulate from Few Pilots via Offline and Online Meta-Learning"},"content":{"rendered":"<p style=\"text-indent:18.0pt\"><span style=\"font-size:12pt\"><span style=\"line-height:109%\"><span><span style=\"font-family:Calibri,sans-serif\"><span lang=\"EN-GB\" style=\"font-size:13.0pt\"><span style=\"line-height:109%\"><span>Authors: <b>Sangwoo Park<\/b>, Hyeryung Jang, Osvaldo Simeone, <b>Joonhyuk Kang<\/b><\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/p>\n<p style=\"text-indent:18.0pt\"><span style=\"font-size:12pt\"><span style=\"line-height:109%\"><span><span style=\"font-family:Calibri,sans-serif\"><span lang=\"EN-GB\" style=\"font-size:13.0pt\"><span style=\"line-height:109%\"><span>Journal: IEEE Transactions on Signal Processing (publication date: Dec. 2020)<\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/p>\n<p style=\"text-indent:18.0pt\"><span style=\"font-size:12pt\"><span style=\"line-height:109%\"><span><span style=\"font-family:Calibri,sans-serif\"><span lang=\"EN-GB\" style=\"font-size:13.0pt\"><span style=\"line-height:109%\"><span>Abstract: We propose meta-learning aided AI demodulator that outperforms conventional communication-theory-based demodulator especially for hardware imperfect IoT transmitters. Unlike conventional AI demodulators that require enormous pilot data, we significantly reduced pilot overhead (e.g., 4 pilots for 16QAM) via meta-learning. Since meta-learning requires additional offline phase for pilot data collection\/training, we introduce online meta-learning that alleviates this requirement of additional phase.<\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/p>\n<p style=\"text-indent:18.0pt\">&nbsp;<\/p>\n<p style=\"text-indent:18.0pt\"><span style=\"font-size:12pt\"><span style=\"line-height:109%\"><span><span style=\"font-family:Calibri,sans-serif\"><span lang=\"EN-GB\" style=\"font-size:13.0pt\"><span style=\"line-height:109%\"><span><\/p>\n<div class=\"\"><img decoding=\"async\" class=\"\" src=\"\/wp-content\/uploads\/drupal\/\uac15\uc8fc\ud601\uad50\uc218\ub2d81.png\" alt=\"\" title=\"\"><\/div>\n<p><\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/p>\n<p style=\"text-indent:18.0pt\"><span style=\"font-size:12pt\"><span style=\"line-height:109%\"><span><span style=\"font-family:Calibri,sans-serif\"><span lang=\"EN-GB\" style=\"font-size:11.0pt\"><span style=\"line-height:109%\"><span>Fig. 1: Symbol error rate with respect to the number of pilots (used during meta-testing) for offline meta-learning with16-QAM, Rayleigh fading, and I\/Q imbalance for 1,000 meta-training devices. The symbol error is averaged over 10,000data symbols and 100 meta-test devices.<\/span><\/span><\/span><\/span><\/span><\/span><\/span><\/p>\n<p style=\"text-indent:18.0pt\">&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>723<\/p>\n","protected":false},"featured_media":0,"template":"","class_list":["post-118468","ai-in-communication","type-ai-in-communication","status-publish","hentry"],"acf":[],"_links":{"self":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/ai-in-communication\/118468","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/ai-in-communication"}],"about":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/types\/ai-in-communication"}],"wp:attachment":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/media?parent=118468"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}