{"id":1472,"date":"2024-12-09T13:59:09","date_gmt":"2024-12-09T12:59:09","guid":{"rendered":"https:\/\/www.labdma.unina.it\/?page_id=1472"},"modified":"2025-03-21T15:10:02","modified_gmt":"2025-03-21T14:10:02","slug":"robustfl-ijcnn-2025","status":"publish","type":"page","link":"https:\/\/www.labdma.unina.it\/index.php\/robustfl-ijcnn-2025\/","title":{"rendered":"RobustFL @IJCNN 2025"},"content":{"rendered":"\n<div style=\"max-width: 800px; margin: 0 auto; font-family: Arial, sans-serif;\">\n    <!-- Header Image Placeholder -->\n    <div style=\"text-align: center; margin-bottom: 20px;\">\n        <img decoding=\"async\" src=\"https:\/\/www.labdma.unina.it\/wp-content\/uploads\/2024\/12\/headerijcnn.jpg\" alt=\"Special Session Header\" style=\"width: 100%; max-height: 300px; object-fit: cover;\">\n    <\/div>\n    \n    <!-- Special Session Content -->\n    <h1 style=\"text-align: center; color: #333;\">Special Session: RobustFL<\/h1>\n    <h2 style=\"text-align: center; color: #555;\">Towards Robust Federated Learning: Addressing Data and Device Heterogeneity<\/h2>\n    \n    <h3>Organizers<\/h3>\n    <ul>\n        <li><a href=\"https:\/\/scholar.google.com\/citations?user=n1VGy-gAAAAJ&#038;hl=it\" target=\"_blank\" rel=\"noopener\">Dr. Diletta Chiaro<\/a>, University of Naples Federico II<\/li>\n        <li><a href=\"https:\/\/wpage.unina.it\/francesco.piccialli\/\" target=\"_blank\" rel=\"noopener\">Prof. Francesco Piccialli<\/a>, University of Naples Federico II<\/li>\n        <li><a href=\"https:\/\/scholar.google.com\/citations?user=I8q5NwUAAAAJ&#038;hl=it\" target=\"_blank\" rel=\"noopener\">Dr. Fabio Giampaolo<\/a>, University of Naples Federico II<\/li>\n    <\/ul>\n    \n    <h3>Primary Contact<\/h3>\n    <p>Email: <a href=\"mailto:diletta.chiaro@unina.it\">diletta.chiaro@unina.it<\/a><\/p>\n    \n    <h3>Abstract<\/h3>\n    <p>\n        Federated Learning (FL) has emerged as a groundbreaking approach to enabling AI across decentralized and sensitive data sources without requiring data centralization, addressing privacy concerns that align with regulations like GDPR. For a leading conference like IJCNN, which emphasizes advancements in neural networks and transformative AI, FL offers a rich avenue for exploration. While past sessions at IJCNN (see IJCNN 2024) have largely focused on privacy and trustworthiness, the next critical frontier is addressing the inherent challenges of non-iid data distributions and device heterogeneity\u2014barriers that must be overcome for FL to scale and perform effectively in real-world settings.\n    <\/p>\n    <p>\n        In practical FL deployments, data generated across decentralized sources is not only non-iid but is also produced by diverse devices with varying computational power, network stability, and memory capacity. This device heterogeneity complicates learning, as not all devices can contribute equally or reliably. Such variability can degrade model performance, create biases, and complicate both convergence and fairness. For example, FL applications in healthcare and IoT span a range of devices, from powerful servers to lightweight edge devices, each with unique data characteristics and resource constraints. Addressing non-iid data and device heterogeneity is essential for FL to be scalable, fair, and ethically viable, especially in critical areas like medical diagnostics and financial forecasting.\n    <\/p>\n\n\n<h3>Important Dates<\/h3>\n\n<p>Submission Deadline: January 15, 2025<\/p>\n    \n    <h3>Scope and Topics of Interest<\/h3>\n    <ul>\n        <li>Algorithmic and Theoretical Advances: New algorithms that improve FL\u2019s performance and adaptability to both non-iid data and heterogeneous device constraints.<\/li>\n        <li>Fairness and Robustness: Strategies for creating models that are fair and resilient across varying data sources and device capacities.<\/li>\n        <li>Interpretability and Explainability: Approaches to ensure transparency and interpretability in FL models that operate across diverse data and devices.<\/li>\n        <li>Personalization and Client Adaptivity: Techniques for personalizing FL models to specific clients while maintaining overall robustness, despite differing device capabilities and data.<\/li>\n        <li>Resource-Aware FL: Frameworks that optimize FL for resource-limited devices, accounting for constraints in memory, battery life, and connectivity.<\/li>\n        <li>Application Case Studies: Real-world applications demonstrating FL\u2019s performance in managing non-iid data and device heterogeneity, particularly in sensitive areas like healthcare and IoT.<\/li>\n        <li>Tools and Benchmarks: Development of benchmark datasets and evaluation metrics that reflect the challenges of both non-iid data and diverse device conditions.<\/li>\n    <\/ul>\n    \n    \n    <h3>Program Committee<\/h3>\n    <ul>\n<li>Afaf Ta\u00efk, Mila &#8211; Quebec AI Institute\u00a0<\/li>\n<li>Afsana\u00a0 Khan, Maastricht University\u00a0\u00a0\u00a0 <\/li>\n<li>Alessio\u00a0 Mora, University of Bologna\u00a0\u00a0\u00a0 <\/li>\n<li>Alessio\u00a0 Masano, Universit\u00e0 degli studi di Catania<\/li>\n<li>Bingjie\u00a0 Yan, Institute of Computing Technology, Chinese Academy of Sciences\u00a0 <\/li>\n<li>Bostan\u00a0 Khan, M\u00e4lardalens University\u00a0\u00a0\u00a0 <\/li>\n<li>Chaochao Sun, Shanghai University of Electric Power\u00a0\u00a0\u00a0\u00a0<\/li>\n<li>Daniela Annunziata, University of Naples Federico II\u00a0\u00a0\u00a0<\/li>\n<li>Danilo\u00a0 Menegatti, Sapienza University of Rome\u00a0\u00a0\u00a0 <\/li>\n<li>Depeng\u00a0 Chen, Anhui University\u00a0\u00a0\u00a0 <\/li>\n<li>Diletta\u00a0 Chiaro, Universit\u00e0 degli Studi di Napoli Federico II\u00a0\u00a0\u00a0 <\/li>\n<li>Divya Kulkarni, Harvard Medical School &#8211; Massachusetts General Hospital\u00a0\u00a0\u00a0<\/li> \n<li>Enrique Tom\u00e1s Mart\u00ednez Beltr\u00e1n, University of Murcia\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Fabio Giampaolo, University of Naples Federico II\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Giovanni Paragliola, CNR\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Guanglei Yu, \u65b0\u7586\u533b\u79d1\u5927\u5b66\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Hanyue\u00a0 Xu, School of AI and Advanced Computing, Xi\u2019an Jiaotong-Liverpool University<\/li>\n<li>Haokun\u00a0 Chen, University of Munich\u00a0\u00a0\u00a0 <\/li>\n<li>Jayant Vyas, Indian Institute of Technology Jodhpur<\/li>\n<li>Jiayi Mao, Zhejiang University\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Jing Xu, School of Computer and Communication Engineering, Changsha University of Science and Technology\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Judith S\u00e1inz-Pardo D\u00edaz, Spanish National Research Council (CSIC)\u00a0\u00a0\u00a0<\/li> \n<li>Jue Xiao, Huazhong University of Science and Technology\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Junfeng\u00a0 Chen, Jinan University\u00a0\u00a0\u00a0 <\/li>\n<li>Kejia Zhang, School of Computer Science and Big Data (School of Cybersecurity) Heilongjiang University\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Ljubomir Rokvic, EPFL\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\nLorenzo\u00a0 Valerio, IIT-CNR\u00a0\u00a0\u00a0 <\/li>\n<li>Manasa Mariam Mammen, Mercedes-Benz AG\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Manuel R\u00f6der, Technical University of Applied Sciences W\u00fcrzburg-Schweinfurt\u00a0 <\/li>\n<li>Marco Garofalo, University of Pisa\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Mario Colosi, University of Messina\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Martina Savoia, University of Naples Federico II\u00a0\u00a0\u00a0<\/li>\n<li>Marzia Canzaniello, University of Naples Federico II\u00a0\u00a0\u00a0\u00a0<\/li>\n<li>Melike Ge\u00e7er, University of Lausanne\u00a0\u00a0\u00a0\u00a0<\/li>\n<li>Mengchen Fan, University of the Alabama at Birmingham\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Mingjia\u00a0 Shi, Sichuan University\u00a0\u00a0\u00a0 <\/li>\n<li>Mingkai\u00a0 Hu, Henan University of Science and Technology\u00a0\u00a0\u00a0 <\/li>\n<li>Monika Farsang, Technische Universit\u00e4t Wien (TU Wien)\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Mrinmay\u00a0 Sen, Indian Institute of Technology Hyderabad\u00a0\u00a0\u00a0 <\/li>\n<li>Nan Yang, The University of Sydney\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Neena Goveas, BITS Pilani, Goa\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Obaidullah Zaland, Ume\u00e5 University\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Oudom Kem, CEA\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Paul Zheng, RWTH Aachen University\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Pian Qi, University of Naples Federico II\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Raman Zatsarenko, Rochester Institute of Technology\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Renyou\u00a0 Xie, Central South University\u00a0\u00a0\u00a0 \n<li>Samuele\u00a0 Fonio, Universit\u00e0 degli studi di Torino\u00a0\u00a0\u00a0 <\/li>\n<li>Sheng\u00a0 Wan, The Hong Kong University of Science and Technology\u00a0\u00a0\u00a0 <\/li>\n<li>Sileshi Nibret Zeleke, University of Bari, Department of Computer Science\u00a0 <\/li>\n<li>Songlian Yan, \u534e\u5357\u5e08\u8303\u5927\u5b66\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Tianxiang Chen,\u00a0 Beihang University\u00a0\u00a0\u00a0 <\/li>\n<li>Truong\u00a0 Thao Nguyen, National Institute of Advanced Industrial Science and Technology (AIST)\u00a0\u00a0\u00a0 <\/li>\n<li>Wai Fong Tam, Queen Mary University of London\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Xuwei Fan, Zhejiang Gongshang University\u00a0\u00a0\u00a0\u00a0\u00a0<\/li> \n<li>Yan Zhou, Kunsan National University\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Yansong\u00a0 Zhao, Nanyang Technological University\u00a0\u00a0\u00a0 <\/li>\n<li>Yichen\u00a0 Li, Huazhong University of Science and Technology\u00a0\u00a0\u00a0 <\/li>\n<li>Yihang\u00a0 Wu, \u6842\u6797\u7535\u5b50\u79d1\u6280\u5927\u5b66\u00a0\u00a0\u00a0 <\/li>\n<li>Yiming\u00a0 Chen, Tsinghua University\u00a0\u00a0\u00a0<\/li>\n<li>Yitao Chen, Arizona State University\u00a0\u00a0\u00a0\u00a0<\/li>\n<li>Youngjoon Lee, KAIST\u00a0\u00a0\u00a0\u00a0\u00a0<\/li>\n<li>Yu Huo, The Chinese University of Hong Kong, Shenzhen\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Zahra Batool, Mila &#8211; Quebec AI Institute\u00a0\u00a0\u00a0\u00a0\u00a0 <\/li>\n<li>Zhe Li, Rochester Institute of Technology<\/li>\n    <\/ul>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<div class=\"slide-text-bg2\">\n<h3>&lt;div class=&quot;slide-text-bg2&quot;&gt;<br \/>\n&lt;h3&gt;Special Session: RobustFL Towards Robust Federated Learning: Addressing Data and Device Heterogeneity Organizers Dr. Diletta Chiaro, University of Naples Federico&lt;\/h3&gt;<br \/>\n&lt;\/div&gt;<br \/>\n&lt;div class=&quot;flex-btn-div&quot;&gt;&lt;a href=&quot;https:\/\/www.labdma.unina.it\/index.php\/robustfl-ijcnn-2025\/&quot; class=&quot;btn1 flex-btn&quot;&gt;Leggi tutto&lt;\/a&gt;&lt;\/div&gt;<br \/>\n<\/h3>\n<\/div>\n<div class=\"flex-btn-div\"><a href=\"https:\/\/www.labdma.unina.it\/index.php\/robustfl-ijcnn-2025\/\" class=\"btn1 flex-btn\">Leggi tutto<\/a><\/div>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":[],"_links":{"self":[{"href":"https:\/\/www.labdma.unina.it\/index.php\/wp-json\/wp\/v2\/pages\/1472"}],"collection":[{"href":"https:\/\/www.labdma.unina.it\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.labdma.unina.it\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.labdma.unina.it\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.labdma.unina.it\/index.php\/wp-json\/wp\/v2\/comments?post=1472"}],"version-history":[{"count":17,"href":"https:\/\/www.labdma.unina.it\/index.php\/wp-json\/wp\/v2\/pages\/1472\/revisions"}],"predecessor-version":[{"id":1542,"href":"https:\/\/www.labdma.unina.it\/index.php\/wp-json\/wp\/v2\/pages\/1472\/revisions\/1542"}],"wp:attachment":[{"href":"https:\/\/www.labdma.unina.it\/index.php\/wp-json\/wp\/v2\/media?parent=1472"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}