{"id":21130,"date":"2025-02-07T13:25:12","date_gmt":"2025-02-07T13:25:12","guid":{"rendered":"https:\/\/dataforpublicgood.org.in\/?p=21130"},"modified":"2025-06-27T00:53:26","modified_gmt":"2025-06-27T00:53:26","slug":"adaptive-self-distillation-for-minimizing-client-drift-in-heterogeneous-federated-learning","status":"publish","type":"post","link":"https:\/\/dataforpublicgood.org.in\/cdpg\/data-privacy\/adaptive-self-distillation-for-minimizing-client-drift-in-heterogeneous-federated-learning\/","title":{"rendered":"Adaptive Self-Distillation for Minimizing Client Drift in Heterogeneous Federated Learning"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-post\" data-elementor-id=\"21130\" class=\"elementor elementor-21130\">\n\t\t\t\t\t\t<div class=\"elementor-inner\">\n\t\t\t\t<div class=\"elementor-section-wrap\">\n\t\t\t\t\t\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-2dac990 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"2dac990\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t\t\t<div class=\"elementor-row\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-top-column elementor-element elementor-element-51804ec\" data-id=\"51804ec\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-column-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t<div class=\"elementor-widget-wrap\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-5ac4424 elementor-widget elementor-widget-text-editor\" data-id=\"5ac4424\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-text-editor elementor-clearfix\">\n\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-438085c elementor-widget elementor-widget-text-editor\" data-id=\"438085c\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-text-editor elementor-clearfix\">\n\t\t\t\t<h1>Adaptive Self-Distillation for Minimizing Client Drift in Heterogeneous Federated Learning<\/h1>\t\t\t\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-ff9263c elementor-widget elementor-widget-text-editor\" data-id=\"ff9263c\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-text-editor elementor-clearfix\">\n\t\t\t\t<p style=\"color: blue;\"><strong>Authors<\/strong>: M. Yashwanth, G. K. Nayak, A. Singh, Y. Simmhan, A. Chakraborty<\/p>\t\t\t\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-9514863 elementor-widget elementor-widget-text-editor\" data-id=\"9514863\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-text-editor elementor-clearfix\">\n\t\t\t\t<p>Federated Learning (FL) is a machine learning paradigm that enables clients to jointly train a global model by aggregating the locally trained models without sharing any local training data. In practice, there can often be substantial heterogeneity (e.g., class imbalance) across the local data distributions observed by each of these clients. Under such non-iid data distributions across clients, FL suffers from the `client-drift\u2019 problem where every client drifts to its own local optimum. This results in slower convergence and poor performance of the aggregated model. To address this limitation, we propose a novel regularization technique based on adaptive self-distillation (ASD) for training models on the client side. Our regularization scheme adaptively adjusts to each client&#8217;s training data based on the global model&#8217;s prediction entropy and the client-data label distribution. We show in this paper that our proposed regularization (ASD) can be easily integrated atop existing, state-of-the-art FL algorithms, leading to a further boost in the performance of these off-the-shelf methods. We theoretically explain how incorporation of ASD regularizer leads to reduction in client-drift and empirically justify the generalization ability of the trained model. We demonstrate the efficacy of our approach through extensive experiments on multiple real-world benchmarks and show substantial gains in performance when the proposed regularizer is combined with popular FL methods. The code is provided as supplementary material.<\/p>\t\t\t\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-85f0dee elementor-widget elementor-widget-text-editor\" data-id=\"85f0dee\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-text-editor elementor-clearfix\">\n\t\t\t\t<p><strong>Journal\/Conference<\/strong><\/p><p>Transactions on Machine Learning Research (TMLR)<\/p>\t\t\t\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-top-column elementor-element elementor-element-979fd33\" data-id=\"979fd33\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-column-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t<div class=\"elementor-widget-wrap\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-4ce5c30 elementor-widget elementor-widget-image\" data-id=\"4ce5c30\" data-element_type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-image\">\n\t\t\t\t\t\t\t\t\t\t\t\t<img loading=\"lazy\" decoding=\"async\" width=\"400\" height=\"300\" src=\"https:\/\/dataforpublicgood.org.in\/cdpg\/wp-content\/uploads\/2025\/02\/Adaptive-Self-Distillation.jpg\" class=\"attachment-full size-full\" alt=\"\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-c27cce3 elementor-button-success elementor-align-center elementor-widget elementor-widget-button\" data-id=\"c27cce3\" data-element_type=\"widget\" data-widget_type=\"button.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"elementor-button-wrapper\">\n\t\t\t<a href=\"https:\/\/arxiv.org\/abs\/2305.19600\" target=\"_blank\" class=\"elementor-button-link elementor-button elementor-size-sm elementor-animation-shrink\" role=\"button\">\n\t\t\t\t\t\t<span class=\"elementor-button-content-wrapper\">\n\t\t\t\t\t\t<span class=\"elementor-button-text\">Know more<\/span>\n\t\t<\/span>\n\t\t\t\t\t<\/a>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-3d308ba elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"3d308ba\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t\t\t<div class=\"elementor-row\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-e1458bc\" data-id=\"e1458bc\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-column-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t<div class=\"elementor-widget-wrap\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-5229c9c elementor-widget elementor-widget-html\" data-id=\"5229c9c\" data-element_type=\"widget\" data-widget_type=\"html.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\n    .post-style-3 .entry-header {\n        display: none;\n    }\n    \n    h1 {\n        font-size:28px !important;\n        text-transform: inherit !important;\n    }\n    \n<\/style>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<div style=\"margin-top: 0px; margin-bottom: 0px;\" class=\"sharethis-inline-share-buttons\" ><\/div>","protected":false},"excerpt":{"rendered":"<p>Adaptive Self-Distillation for Minimizing Client Drift in Heterogeneous Federated Learning Authors: M. Yashwanth, G. K. Nayak, A. Singh, Y. Simmhan, A. Chakraborty Federated Learning (FL) is a machine learning paradigm that enables clients to jointly train a global model by aggregating the locally trained models without sharing any local training data. In practice, there can often be substantial heterogeneity (e.g., &hellip;<\/p>\n","protected":false},"author":2,"featured_media":21131,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","_links_to":"","_links_to_target":""},"categories":[92],"tags":[],"class_list":["post-21130","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-data-privacy"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v20.12 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Adaptive Self-Distillation for Minimizing Client Drift in Heterogeneous Federated Learning - Data for Public Good<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/dataforpublicgood.org.in\/cdpg\/data-privacy\/adaptive-self-distillation-for-minimizing-client-drift-in-heterogeneous-federated-learning\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Adaptive Self-Distillation for Minimizing Client Drift in Heterogeneous Federated Learning - Data for Public Good\" \/>\n<meta property=\"og:description\" content=\"Adaptive Self-Distillation for Minimizing Client Drift in Heterogeneous Federated Learning Authors: M. Yashwanth, G. K. Nayak, A. Singh, Y. Simmhan, A. Chakraborty Federated Learning (FL) is a machine learning paradigm that enables clients to jointly train a global model by aggregating the locally trained models without sharing any local training data. In practice, there can often be substantial heterogeneity (e.g., &hellip;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dataforpublicgood.org.in\/cdpg\/data-privacy\/adaptive-self-distillation-for-minimizing-client-drift-in-heterogeneous-federated-learning\/\" \/>\n<meta property=\"og:site_name\" content=\"Data for Public Good\" \/>\n<meta property=\"article:published_time\" content=\"2025-02-07T13:25:12+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-06-27T00:53:26+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dataforpublicgood.org.in\/cdpg\/wp-content\/uploads\/2025\/02\/Adaptive-Self-Distillation.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"400\" \/>\n\t<meta property=\"og:image:height\" content=\"300\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"CDPG\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@AgriDataXchange\" \/>\n<meta name=\"twitter:site\" content=\"@AgriDataXchange\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"CDPG\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/dataforpublicgood.org.in\/cdpg\/data-privacy\/adaptive-self-distillation-for-minimizing-client-drift-in-heterogeneous-federated-learning\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/dataforpublicgood.org.in\/cdpg\/data-privacy\/adaptive-self-distillation-for-minimizing-client-drift-in-heterogeneous-federated-learning\/\"},\"author\":{\"name\":\"CDPG\",\"@id\":\"https:\/\/dataforpublicgood.org.in\/#\/schema\/person\/c521da9a85ddb366900e8ab41c092fb4\"},\"headline\":\"Adaptive Self-Distillation for Minimizing Client Drift in Heterogeneous Federated Learning\",\"datePublished\":\"2025-02-07T13:25:12+00:00\",\"dateModified\":\"2025-06-27T00:53:26+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/dataforpublicgood.org.in\/cdpg\/data-privacy\/adaptive-self-distillation-for-minimizing-client-drift-in-heterogeneous-federated-learning\/\"},\"wordCount\":265,\"publisher\":{\"@id\":\"https:\/\/dataforpublicgood.org.in\/#organization\"},\"articleSection\":[\"Data Privacy\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/dataforpublicgood.org.in\/cdpg\/data-privacy\/adaptive-self-distillation-for-minimizing-client-drift-in-heterogeneous-federated-learning\/\",\"url\":\"https:\/\/dataforpublicgood.org.in\/cdpg\/data-privacy\/adaptive-self-distillation-for-minimizing-client-drift-in-heterogeneous-federated-learning\/\",\"name\":\"Adaptive Self-Distillation for Minimizing Client Drift in Heterogeneous Federated Learning - Data for Public Good\",\"isPartOf\":{\"@id\":\"https:\/\/dataforpublicgood.org.in\/#website\"},\"datePublished\":\"2025-02-07T13:25:12+00:00\",\"dateModified\":\"2025-06-27T00:53:26+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/dataforpublicgood.org.in\/cdpg\/data-privacy\/adaptive-self-distillation-for-minimizing-client-drift-in-heterogeneous-federated-learning\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/dataforpublicgood.org.in\/cdpg\/data-privacy\/adaptive-self-distillation-for-minimizing-client-drift-in-heterogeneous-federated-learning\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/dataforpublicgood.org.in\/cdpg\/data-privacy\/adaptive-self-distillation-for-minimizing-client-drift-in-heterogeneous-federated-learning\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/dataforpublicgood.org.in\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Adaptive Self-Distillation for Minimizing Client Drift in Heterogeneous Federated Learning\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/dataforpublicgood.org.in\/#website\",\"url\":\"https:\/\/dataforpublicgood.org.in\/\",\"name\":\"Data for Public Good\",\"description\":\"Data for Public Good\",\"publisher\":{\"@id\":\"https:\/\/dataforpublicgood.org.in\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/dataforpublicgood.org.in\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/dataforpublicgood.org.in\/#organization\",\"name\":\"Data for Public Good\",\"url\":\"https:\/\/dataforpublicgood.org.in\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/dataforpublicgood.org.in\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/adex.org.in\/wp-content\/uploads\/2022\/12\/adex-logo.png\",\"contentUrl\":\"https:\/\/adex.org.in\/wp-content\/uploads\/2022\/12\/adex-logo.png\",\"width\":720,\"height\":270,\"caption\":\"Data for Public Good\"},\"image\":{\"@id\":\"https:\/\/dataforpublicgood.org.in\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/twitter.com\/AgriDataXchange\",\"https:\/\/www.linkedin.com\/company\/agricultural-data-exchange\/?viewAsMember=true\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/dataforpublicgood.org.in\/#\/schema\/person\/c521da9a85ddb366900e8ab41c092fb4\",\"name\":\"CDPG\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/dataforpublicgood.org.in\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/07c2cc51f2149e714f30055318fd3fbb92c6e503091ab59827d9bd261e19342a?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/07c2cc51f2149e714f30055318fd3fbb92c6e503091ab59827d9bd261e19342a?s=96&d=mm&r=g\",\"caption\":\"CDPG\"},\"url\":\"https:\/\/dataforpublicgood.org.in\/cdpg\/author\/iudx\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Adaptive Self-Distillation for Minimizing Client Drift in Heterogeneous Federated Learning - Data for Public Good","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/dataforpublicgood.org.in\/cdpg\/data-privacy\/adaptive-self-distillation-for-minimizing-client-drift-in-heterogeneous-federated-learning\/","og_locale":"en_US","og_type":"article","og_title":"Adaptive Self-Distillation for Minimizing Client Drift in Heterogeneous Federated Learning - Data for Public Good","og_description":"Adaptive Self-Distillation for Minimizing Client Drift in Heterogeneous Federated Learning Authors: M. Yashwanth, G. K. Nayak, A. Singh, Y. Simmhan, A. Chakraborty Federated Learning (FL) is a machine learning paradigm that enables clients to jointly train a global model by aggregating the locally trained models without sharing any local training data. In practice, there can often be substantial heterogeneity (e.g., &hellip;","og_url":"https:\/\/dataforpublicgood.org.in\/cdpg\/data-privacy\/adaptive-self-distillation-for-minimizing-client-drift-in-heterogeneous-federated-learning\/","og_site_name":"Data for Public Good","article_published_time":"2025-02-07T13:25:12+00:00","article_modified_time":"2025-06-27T00:53:26+00:00","og_image":[{"width":400,"height":300,"url":"https:\/\/dataforpublicgood.org.in\/cdpg\/wp-content\/uploads\/2025\/02\/Adaptive-Self-Distillation.jpg","type":"image\/jpeg"}],"author":"CDPG","twitter_card":"summary_large_image","twitter_creator":"@AgriDataXchange","twitter_site":"@AgriDataXchange","twitter_misc":{"Written by":"CDPG","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/dataforpublicgood.org.in\/cdpg\/data-privacy\/adaptive-self-distillation-for-minimizing-client-drift-in-heterogeneous-federated-learning\/#article","isPartOf":{"@id":"https:\/\/dataforpublicgood.org.in\/cdpg\/data-privacy\/adaptive-self-distillation-for-minimizing-client-drift-in-heterogeneous-federated-learning\/"},"author":{"name":"CDPG","@id":"https:\/\/dataforpublicgood.org.in\/#\/schema\/person\/c521da9a85ddb366900e8ab41c092fb4"},"headline":"Adaptive Self-Distillation for Minimizing Client Drift in Heterogeneous Federated Learning","datePublished":"2025-02-07T13:25:12+00:00","dateModified":"2025-06-27T00:53:26+00:00","mainEntityOfPage":{"@id":"https:\/\/dataforpublicgood.org.in\/cdpg\/data-privacy\/adaptive-self-distillation-for-minimizing-client-drift-in-heterogeneous-federated-learning\/"},"wordCount":265,"publisher":{"@id":"https:\/\/dataforpublicgood.org.in\/#organization"},"articleSection":["Data Privacy"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/dataforpublicgood.org.in\/cdpg\/data-privacy\/adaptive-self-distillation-for-minimizing-client-drift-in-heterogeneous-federated-learning\/","url":"https:\/\/dataforpublicgood.org.in\/cdpg\/data-privacy\/adaptive-self-distillation-for-minimizing-client-drift-in-heterogeneous-federated-learning\/","name":"Adaptive Self-Distillation for Minimizing Client Drift in Heterogeneous Federated Learning - Data for Public Good","isPartOf":{"@id":"https:\/\/dataforpublicgood.org.in\/#website"},"datePublished":"2025-02-07T13:25:12+00:00","dateModified":"2025-06-27T00:53:26+00:00","breadcrumb":{"@id":"https:\/\/dataforpublicgood.org.in\/cdpg\/data-privacy\/adaptive-self-distillation-for-minimizing-client-drift-in-heterogeneous-federated-learning\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dataforpublicgood.org.in\/cdpg\/data-privacy\/adaptive-self-distillation-for-minimizing-client-drift-in-heterogeneous-federated-learning\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/dataforpublicgood.org.in\/cdpg\/data-privacy\/adaptive-self-distillation-for-minimizing-client-drift-in-heterogeneous-federated-learning\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dataforpublicgood.org.in\/"},{"@type":"ListItem","position":2,"name":"Adaptive Self-Distillation for Minimizing Client Drift in Heterogeneous Federated Learning"}]},{"@type":"WebSite","@id":"https:\/\/dataforpublicgood.org.in\/#website","url":"https:\/\/dataforpublicgood.org.in\/","name":"Data for Public Good","description":"Data for Public Good","publisher":{"@id":"https:\/\/dataforpublicgood.org.in\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/dataforpublicgood.org.in\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/dataforpublicgood.org.in\/#organization","name":"Data for Public Good","url":"https:\/\/dataforpublicgood.org.in\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/dataforpublicgood.org.in\/#\/schema\/logo\/image\/","url":"https:\/\/adex.org.in\/wp-content\/uploads\/2022\/12\/adex-logo.png","contentUrl":"https:\/\/adex.org.in\/wp-content\/uploads\/2022\/12\/adex-logo.png","width":720,"height":270,"caption":"Data for Public Good"},"image":{"@id":"https:\/\/dataforpublicgood.org.in\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/twitter.com\/AgriDataXchange","https:\/\/www.linkedin.com\/company\/agricultural-data-exchange\/?viewAsMember=true"]},{"@type":"Person","@id":"https:\/\/dataforpublicgood.org.in\/#\/schema\/person\/c521da9a85ddb366900e8ab41c092fb4","name":"CDPG","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/dataforpublicgood.org.in\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/07c2cc51f2149e714f30055318fd3fbb92c6e503091ab59827d9bd261e19342a?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/07c2cc51f2149e714f30055318fd3fbb92c6e503091ab59827d9bd261e19342a?s=96&d=mm&r=g","caption":"CDPG"},"url":"https:\/\/dataforpublicgood.org.in\/cdpg\/author\/iudx\/"}]}},"_links":{"self":[{"href":"https:\/\/dataforpublicgood.org.in\/cdpg\/wp-json\/wp\/v2\/posts\/21130","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dataforpublicgood.org.in\/cdpg\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dataforpublicgood.org.in\/cdpg\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dataforpublicgood.org.in\/cdpg\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/dataforpublicgood.org.in\/cdpg\/wp-json\/wp\/v2\/comments?post=21130"}],"version-history":[{"count":16,"href":"https:\/\/dataforpublicgood.org.in\/cdpg\/wp-json\/wp\/v2\/posts\/21130\/revisions"}],"predecessor-version":[{"id":22468,"href":"https:\/\/dataforpublicgood.org.in\/cdpg\/wp-json\/wp\/v2\/posts\/21130\/revisions\/22468"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dataforpublicgood.org.in\/cdpg\/wp-json\/wp\/v2\/media\/21131"}],"wp:attachment":[{"href":"https:\/\/dataforpublicgood.org.in\/cdpg\/wp-json\/wp\/v2\/media?parent=21130"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dataforpublicgood.org.in\/cdpg\/wp-json\/wp\/v2\/categories?post=21130"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dataforpublicgood.org.in\/cdpg\/wp-json\/wp\/v2\/tags?post=21130"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}