{"id":153,"date":"2024-06-10T08:04:01","date_gmt":"2024-06-10T08:04:01","guid":{"rendered":"https:\/\/mledge.networks.imdea.org\/?p=153"},"modified":"2024-06-28T08:20:34","modified_gmt":"2024-06-28T08:20:34","slug":"fedqv-leveraging-quadratic-voting-in-fl","status":"publish","type":"post","link":"https:\/\/mledge.networks.imdea.org\/en\/2024\/06\/10\/fedqv-leveraging-quadratic-voting-in-fl\/","title":{"rendered":"FEDQV: Leveraging Quadratic Voting in FL"},"content":{"rendered":"<p><span style=\"font-weight: 400\">MLEDGE has already started producing relevant papers in top CS venues. This month, our colleague Tianyue Chu is presenting the paper \u201c<\/span><span style=\"font-weight: 400\">FedQV: Leveraging Quadratic Voting in Federated Learning<\/span><span style=\"font-weight: 400\">\u201c at the SIGMETRICS conference (ranked A* according to CORE2023) in Venice, Italy. This paper relates to the FedSecure research component of the project.<\/span><\/p>\n<p><span style=\"font-weight: 400\">Federated Learning (FL) permits different parties to collaboratively train a global model without disclosing their respective local labels. This paper introduces FEDQV, a novel aggregation algorithm built upon the quadratic voting scheme. Its theoretical analysis establishes that FEDQV is a truthful mechanism in which bidding according to one\u2019s true valuation is a dominant strategy that achieves a convergence rate matching that of state-of-the-art methods. Furthermore, its empirical analysis using multiple real-world datasets shows that combining FEDQV with unequal voting \u201cbudgets\u201d according to a reputation score increases its performance benefits even further. Finally, it shows that FEDQV can enhance the robustness of FL against poisoning attacks and, combined with Byzantine-robust privacy-preserving mechanisms,\u00a0 against privacy attacks.<\/span><\/p>","protected":false},"excerpt":{"rendered":"MLEDGE has already started producing relevant papers in top CS venues. This month, our colleague Tianyue Chu is presenting the paper \u201cFedQV: Leveraging Quadratic Voting in Federated Learning\u201c at the SIGMETRICS conference (ranked A* according to CORE2023) in Venice, Italy. This paper relates to the FedSecure research component of the project. Federated Learning (FL) permits&#8230;","protected":false},"author":171,"featured_media":154,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[4],"tags":[],"class_list":["post-153","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-investigacion"],"acf":[],"_links":{"self":[{"href":"https:\/\/mledge.networks.imdea.org\/en\/wp-json\/wp\/v2\/posts\/153","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mledge.networks.imdea.org\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mledge.networks.imdea.org\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mledge.networks.imdea.org\/en\/wp-json\/wp\/v2\/users\/171"}],"replies":[{"embeddable":true,"href":"https:\/\/mledge.networks.imdea.org\/en\/wp-json\/wp\/v2\/comments?post=153"}],"version-history":[{"count":1,"href":"https:\/\/mledge.networks.imdea.org\/en\/wp-json\/wp\/v2\/posts\/153\/revisions"}],"predecessor-version":[{"id":155,"href":"https:\/\/mledge.networks.imdea.org\/en\/wp-json\/wp\/v2\/posts\/153\/revisions\/155"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/mledge.networks.imdea.org\/en\/wp-json\/wp\/v2\/media\/154"}],"wp:attachment":[{"href":"https:\/\/mledge.networks.imdea.org\/en\/wp-json\/wp\/v2\/media?parent=153"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mledge.networks.imdea.org\/en\/wp-json\/wp\/v2\/categories?post=153"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mledge.networks.imdea.org\/en\/wp-json\/wp\/v2\/tags?post=153"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}