{"id":4916,"date":"2023-07-14T17:35:51","date_gmt":"2023-07-14T09:35:51","guid":{"rendered":"https:\/\/inventec2.mjitec.tw\/?page_id=4916"},"modified":"2024-01-17T11:07:00","modified_gmt":"2024-01-17T03:07:00","slug":"a-robust-collaborative-learning-framework-using-data-digests-and-synonyms-to-represent-absent-clients","status":"publish","type":"page","link":"https:\/\/inventec2.mjitec.tw\/en\/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":"

[vc_row full_width=”stretch_row”][vc_column]

\r\n
<\/div>\t\t\t\r\n\t\t\t<\/div>[vc_row_inner el_class=”md-full-col”][vc_column_inner el_class=”m_p” width=”1\/2″]\n
\n \t
\n \t\t\n\t \n\t

A Robust Collaborative Learning Framework Using Data Digests and Synonyms to Represent Absent Clients <\/h2>\n\t <\/div><\/div>[vc_column_text css=”.vc_custom_1689327224626{margin-bottom: 20px !important;}”]<\/p>\n
\n

IEEE International Conference on Multimedia Information Processing and Retrieval (IEEE MIPR 2021)<\/p>\n<\/div>\n

[\/vc_column_text][vc_column_text css=”.vc_custom_1689328195761{margin-bottom: 5px !important;}”]<\/p>\n

\n
Authors<\/h6>\n<\/div>\n

[\/vc_column_text][vc_column_text css=”.vc_custom_1689327233986{margin-bottom: 20px !important;}”]<\/p>\n

\n

Chih-Fan Hsu, Ming-Ching Chang, and Wei-Chao Chen<\/p>\n<\/div>\n

[\/vc_column_text][vc_column_text css=”.vc_custom_1689328207394{margin-bottom: 5px !important;}”]<\/p>\n

\n
Published<\/h6>\n<\/div>\n

[\/vc_column_text][vc_column_text]<\/p>\n

\n

2022\/9\/8<\/p>\n<\/div>\n

[\/vc_column_text][\/vc_column_inner][vc_column_inner el_class=”m_p” width=”1\/2″][vc_single_image image=”13109″ img_size=”full”][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row][vc_row][vc_column]

\r\n
<\/div>\t\t\t\r\n\t\t\t<\/div>[\/vc_column][\/vc_row][vc_row full_width=”stretch_row”][vc_column][vc_row_inner content_placement=”top” css=”.vc_custom_1657794580528{margin-bottom: 20px !important;}”][vc_column_inner el_class=”m_p paragraph_title” width=”1\/3″]\n
\n \t
\n \t\t\n\t \n\t

Abstract <\/h2>\n\t <\/div><\/div>[\/vc_column_inner][vc_column_inner el_class=”m_p” width=”2\/3″][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.
\nClient absence during collaborative training can seriously degrade model performances, particularly for unbalanced and non-IID client data.
\nWe address this issue by introducing the notion of data digests of the training samples from the clients.
\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.
\nWe compare our CLSyn implementations against three centralized Federated Learning algorithms, namely FedAvg, FedProx, and FedNova as baselines.
\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]
\r\n
<\/div>\t\t\t\r\n\t\t\t<\/div>[\/vc_column][\/vc_row][vc_row][vc_column width=”1\/3″ el_class=”m_p keyword_title”][vc_column_text]<\/p>\n

Keywords<\/h2>\n

[\/vc_column_text][\/vc_column][vc_column width=”2\/3″ el_class=”m_p keyword”][vc_row_inner content_placement=”middle”][vc_column_inner width=”1\/3″][vc_raw_html]JTNDdWwlMjBjbGFzcyUzRCUyMnN0eWxlbGlzdGluZyUyMiUzRSUwQSUyMCUwOSUzQ2xpJTIwc3R5bGUlM0QlMjJsaW5lLWhlaWdodCUzQTM0cHglM0IlMjIlM0VGZWRlcmF0ZWQlMjBMZWFybmluZyUzQyUyRmxpJTNFJTBBJTNDJTJGdWwlM0U=[\/vc_raw_html][\/vc_column_inner][vc_column_inner width=”1\/3″][vc_raw_html]JTNDdWwlMjBjbGFzcyUzRCUyMnN0eWxlbGlzdGluZyUyMiUzRSUwQSUyMCUwOSUzQ2xpJTIwc3R5bGUlM0QlMjJsaW5lLWhlaWdodCUzQTM0cHglM0IlMjIlM0VEYXRhJTIwZGlnZXN0JTNDJTJGbGklM0UlMEElM0MlMkZ1bCUzRQ==[\/vc_raw_html][\/vc_column_inner][vc_column_inner width=”1\/3″][vc_raw_html]JTNDdWwlMjBjbGFzcyUzRCUyMnN0eWxlbGlzdGluZyUyMiUzRSUwQSUyMCUwOSUzQ2xpJTIwc3R5bGUlM0QlMjJsaW5lLWhlaWdodCUzQTM0cHglM0IlMjIlM0VQcml2YWN5JTNDJTJGbGklM0UlMEElM0MlMkZ1bCUzRQ==[\/vc_raw_html][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row][vc_row][vc_column]

\r\n
<\/div>\t\t\t\r\n\t\t\t<\/div>[\/vc_column][\/vc_row][vc_row full_width=”stretch_row” el_class=”bg” css=”.vc_custom_1657248474326{padding-top: 50px !important;padding-bottom: 50px !important;}”][vc_column][vc_column_text css=”.vc_custom_1689328251694{margin-bottom: 20px !important;}”]<\/p>\n

Download<\/h3>\n

[\/vc_column_text][vc_row_inner content_placement=”middle”][vc_column_inner el_class=”download_btn_wrap”][vc_btn title=”PDF” style=”flat” color=”white” align=”center” link=”url:https%3A%2F%2Fieeexplore.ieee.org%2Fdocument%2F9874675|target:_blank” el_class=”download_btn”][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row]<\/p>\n<\/div>","protected":false},"excerpt":{"rendered":"

[vc_row full_width=”stretch_row”][vc_column][vc_row_inner el_class=”md-full-col”][vc_column_inner el_class=”m_p” width=”1\/2″][vc_column_text css=”.vc_custom_1689327224626{margin-bottom: 20px !important;}”] IEEE International Conference on Multimedia Information Processing and Retrieval (IEEE MIPR 2021) [\/vc_column_text][vc_column_text css=”.vc_custom_1689328195761{margin-bottom: 5px !important;}”] Authors [\/vc_column_text][vc_column_text css=”.vc_custom_1689327233986{margin-bottom: 20px !important;}”] Chih-Fan Hsu, Ming-Ching Chang, and Wei-Chao Chen [\/vc_column_text][vc_column_text css=”.vc_custom_1689328207394{margin-bottom: 5px !important;}”] Published [\/vc_column_text][vc_column_text] 2022\/9\/8 [\/vc_column_text][\/vc_column_inner][vc_column_inner el_class=”m_p” width=”1\/2″][vc_single_image image=”13109″ img_size=”full”][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row][vc_row][vc_column][\/vc_column][\/vc_row][vc_row full_width=”stretch_row”][vc_column][vc_row_inner content_placement=”top” css=”.vc_custom_1657794580528{margin-bottom: 20px !important;}”][vc_column_inner el_class=”m_p paragraph_title”…<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":4975,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-4916","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/pages\/4916","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/comments?post=4916"}],"version-history":[{"count":0,"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/pages\/4916\/revisions"}],"up":[{"embeddable":true,"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/pages\/4975"}],"wp:attachment":[{"href":"https:\/\/inventec2.mjitec.tw\/en\/wp-json\/wp\/v2\/media?parent=4916"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}