{"id":4917,"date":"2023-07-14T17:35:51","date_gmt":"2023-07-14T09:35:51","guid":{"rendered":"https:\/\/inventec2.mjitec.tw\/?page_id=4917"},"modified":"2023-09-28T16:40:03","modified_gmt":"2023-09-28T08:40:03","slug":"a-robust-collaborative-learning-framework-using-data-digests-and-synonyms-to-represent-absent-clients","status":"publish","type":"page","link":"https:\/\/inventec2.mjitec.tw\/zh-hans\/ai\/a-robust-collaborative-learning-framework-using-data-digests-and-synonyms-to-represent-absent-clients\/","title":{"rendered":"A Robust Collaborative Learning Framework Using Data Digests and Synonyms to Represent Absent Clients"},"content":{"rendered":"<div class=\"wpb-content-wrapper\"><p>[vc_row full_width=&#8221;stretch_row&#8221;][vc_column]<div id=\"rs-space-69e10d9c5f600\" class=\"rs-space\">\r\n                <div class=\"rs-space-data\" data-conf=\"{&quot;uqid&quot;:&quot;69e10d9c5f600&quot;,&quot;space_lg&quot;:&quot;150&quot;,&quot;space_md&quot;:&quot;80&quot;,&quot;space_sm&quot;:&quot;60&quot;,&quot;space_xs&quot;:&quot;60&quot;}\"><\/div>\t\t\t\r\n\t\t\t<\/div>[vc_row_inner el_class=&#8221;md-full-col&#8221;][vc_column_inner el_class=&#8221;m_p&#8221; width=&#8221;1\/2&#8243;]\n        <div class=\"rs-heading    \">\n        \t<div class=\"title-inner\"  data-border-color=\"\">\n        \t\t\n\t            \n\t            <h2 class=\"title \" style=\"color: #333333\">A Robust Collaborative Learning Framework Using Data Digests and Synonyms to Represent Absent Clients <\/h2>\n\t        <\/div><\/div>[vc_column_text css=&#8221;.vc_custom_1689327224626{margin-bottom: 20px !important;}&#8221;]<\/p>\n<div>\n<p>IEEE International Conference on Multimedia Information Processing and Retrieval (IEEE MIPR 2021)<\/p>\n<\/div>\n<p>[\/vc_column_text][vc_column_text css=&#8221;.vc_custom_1660542835761{margin-bottom: 5px !important;}&#8221;]<\/p>\n<div>\n<h6>\u4f5c\u8005<\/h6>\n<\/div>\n<p>[\/vc_column_text][vc_column_text css=&#8221;.vc_custom_1689327233986{margin-bottom: 20px !important;}&#8221;]<\/p>\n<div>\n<p>Chih-Fan Hsu, Ming-Ching Chang, and Wei-Chao Chen<\/p>\n<\/div>\n<p>[\/vc_column_text][vc_column_text css=&#8221;.vc_custom_1689328126111{margin-bottom: 5px !important;}&#8221;]<\/p>\n<div>\n<h6>\u53d1\u8868\u65e5\u671f<\/h6>\n<\/div>\n<p>[\/vc_column_text][vc_column_text]<\/p>\n<div>\n<p>Sept 8-10, 2021<\/p>\n<\/div>\n<p>[\/vc_column_text][\/vc_column_inner][vc_column_inner el_class=&#8221;m_p&#8221; width=&#8221;1\/2&#8243;][vc_single_image image=&#8221;13108&#8243; img_size=&#8221;full&#8221;][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row][vc_row][vc_column]<div id=\"rs-space-69e10d9c5f6f0\" class=\"rs-space\">\r\n                <div class=\"rs-space-data\" data-conf=\"{&quot;uqid&quot;:&quot;69e10d9c5f6f0&quot;,&quot;space_lg&quot;:&quot;150&quot;,&quot;space_md&quot;:&quot;80&quot;,&quot;space_sm&quot;:&quot;60&quot;,&quot;space_xs&quot;:&quot;60&quot;}\"><\/div>\t\t\t\r\n\t\t\t<\/div>[\/vc_column][\/vc_row][vc_row full_width=&#8221;stretch_row&#8221;][vc_column][vc_row_inner content_placement=&#8221;top&#8221; css=&#8221;.vc_custom_1657794580528{margin-bottom: 20px !important;}&#8221;][vc_column_inner el_class=&#8221;m_p paragraph_title&#8221; width=&#8221;1\/3&#8243;]\n        <div class=\"rs-heading   vc_custom_1657008747808  \">\n        \t<div class=\"title-inner\"  data-border-color=\"\">\n        \t\t\n\t            \n\t            <h2 class=\"title \" style=\"color: #333333\">\u6982\u8981 <\/h2>\n\t        <\/div><\/div>[\/vc_column_inner][vc_column_inner el_class=&#8221;m_p&#8221; width=&#8221;2\/3&#8243;][vc_column_text]We propose Collaborative Learning with Synonyms (CLSyn), a robust and versatile collaborative machine learning framework that can tolerate unexpected client absence during training while maintaining high model accuracy.<br \/>\nClient absence during collaborative training can seriously degrade model performances, particularly for unbalanced and non-IID client data.<br \/>\nWe address this issue by introducing the notion of data digests of the training samples from the clients.<br \/>\nThe expansion of digests called synonyms can represent the original samples on the server and thus maintain overall model accuracy, even after the clients become unavailable.<br \/>\nWe compare our CLSyn implementations against three centralized Federated Learning algorithms, namely FedAvg, FedProx, and FedNova as baselines.<br \/>\nResults on CIFAR-10, CIFAR-100, and EMNIST show that CLSyn consistently outperforms these baselines by significant margins in various client absence scenarios.[\/vc_column_text][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row][vc_row][vc_column]<div id=\"rs-space-69e10d9c5f7a2\" class=\"rs-space\">\r\n                <div class=\"rs-space-data\" data-conf=\"{&quot;uqid&quot;:&quot;69e10d9c5f7a2&quot;,&quot;space_lg&quot;:&quot;80&quot;,&quot;space_md&quot;:&quot;80&quot;,&quot;space_sm&quot;:&quot;60&quot;,&quot;space_xs&quot;:&quot;60&quot;}\"><\/div>\t\t\t\r\n\t\t\t<\/div>[\/vc_column][\/vc_row][vc_row][vc_column width=&#8221;1\/3&#8243; el_class=&#8221;m_p keyword_title&#8221;][vc_column_text]<\/p>\n<h2>\u5173\u952e\u5b57<\/h2>\n<p>[\/vc_column_text][\/vc_column][vc_column width=&#8221;2\/3&#8243; el_class=&#8221;m_p keyword&#8221;][vc_row_inner content_placement=&#8221;middle&#8221;][vc_column_inner width=&#8221;1\/3&#8243;][vc_raw_html]JTNDdWwlMjBjbGFzcyUzRCUyMnN0eWxlbGlzdGluZyUyMiUzRSUwQSUyMCUwOSUzQ2xpJTIwc3R5bGUlM0QlMjJsaW5lLWhlaWdodCUzQTM0cHglM0IlMjIlM0VGZWRlcmF0ZWQlMjBMZWFybmluZyUzQyUyRmxpJTNFJTBBJTNDJTJGdWwlM0U=[\/vc_raw_html][\/vc_column_inner][vc_column_inner width=&#8221;1\/3&#8243;][vc_raw_html]JTNDdWwlMjBjbGFzcyUzRCUyMnN0eWxlbGlzdGluZyUyMiUzRSUwQSUyMCUwOSUzQ2xpJTIwc3R5bGUlM0QlMjJsaW5lLWhlaWdodCUzQTM0cHglM0IlMjIlM0VEYXRhJTIwZGlnZXN0JTNDJTJGbGklM0UlMEElM0MlMkZ1bCUzRQ==[\/vc_raw_html][\/vc_column_inner][vc_column_inner width=&#8221;1\/3&#8243;][vc_raw_html]JTNDdWwlMjBjbGFzcyUzRCUyMnN0eWxlbGlzdGluZyUyMiUzRSUwQSUyMCUwOSUzQ2xpJTIwc3R5bGUlM0QlMjJsaW5lLWhlaWdodCUzQTM0cHglM0IlMjIlM0VQcml2YWN5JTNDJTJGbGklM0UlMEElM0MlMkZ1bCUzRQ==[\/vc_raw_html][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row][vc_row][vc_column]<div id=\"rs-space-69e10d9c5f7d6\" class=\"rs-space\">\r\n                <div class=\"rs-space-data\" data-conf=\"{&quot;uqid&quot;:&quot;69e10d9c5f7d6&quot;,&quot;space_lg&quot;:&quot;80&quot;,&quot;space_md&quot;:&quot;80&quot;,&quot;space_sm&quot;:&quot;60&quot;,&quot;space_xs&quot;:&quot;60&quot;}\"><\/div>\t\t\t\r\n\t\t\t<\/div>[\/vc_column][\/vc_row][vc_row full_width=&#8221;stretch_row&#8221; el_class=&#8221;bg&#8221; css=&#8221;.vc_custom_1657248474326{padding-top: 50px !important;padding-bottom: 50px !important;}&#8221;][vc_column][vc_column_text css=&#8221;.vc_custom_1689328156395{margin-bottom: 20px !important;}&#8221;]<\/p>\n<h3 style=\"text-align: center; color: #fff;\">\u4e0b\u8f7d\u4e0e\u5206\u4eab<\/h3>\n<p>[\/vc_column_text][vc_row_inner content_placement=&#8221;middle&#8221;][vc_column_inner el_class=&#8221;download_btn_wrap&#8221;][vc_btn title=&#8221;PDF&#8221; style=&#8221;flat&#8221; color=&#8221;white&#8221; align=&#8221;center&#8221; link=&#8221;url:https%3A%2F%2Fieeexplore.ieee.org%2Fdocument%2F9874675|target:_blank&#8221; el_class=&#8221;download_btn&#8221;][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row]<\/p>\n<\/div>","protected":false},"excerpt":{"rendered":"<p>[vc_row full_width=&#8221;stretch_row&#8221;][vc_column&#8230;<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":4976,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-4917","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/inventec2.mjitec.tw\/zh-hans\/wp-json\/wp\/v2\/pages\/4917","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/inventec2.mjitec.tw\/zh-hans\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/inventec2.mjitec.tw\/zh-hans\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/inventec2.mjitec.tw\/zh-hans\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/inventec2.mjitec.tw\/zh-hans\/wp-json\/wp\/v2\/comments?post=4917"}],"version-history":[{"count":0,"href":"https:\/\/inventec2.mjitec.tw\/zh-hans\/wp-json\/wp\/v2\/pages\/4917\/revisions"}],"up":[{"embeddable":true,"href":"https:\/\/inventec2.mjitec.tw\/zh-hans\/wp-json\/wp\/v2\/pages\/4976"}],"wp:attachment":[{"href":"https:\/\/inventec2.mjitec.tw\/zh-hans\/wp-json\/wp\/v2\/media?parent=4917"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}