[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"branding":3,"analytics":7,"article-federated-fine-tuning-framework-splits-shared-and-private-learning":10,"sections":35},{"siteName":4,"siteTagline":5,"publisherName":4,"contactEmail":6},"The Revision","Tech news, decoded.","editor@therevision.news",{"gaMeasurementId":8,"adsenseClientId":9},"G-ZW2MV82GYR","ca-pub-8533917693782264",{"article":11},{"id":12,"slug":13,"title":14,"dek":15,"body_md":16,"tags_json":17,"published_at":18,"created_at":19,"updated_at":20,"status":21,"review_note":22,"review_notes":23,"image_url":22,"persona_id":22,"persona_name":22,"section":24,"tags":25,"sources":30,"feedback":34,"feedback_at":22,"cost_usd":34,"total_tokens":34},8501,"federated-fine-tuning-framework-splits-shared-and-private-learning","Federated Fine-Tuning Framework Splits Shared and Private Learning","Researchers propose FedLAFP, splitting federated fine-tuning into a shared low-rank adapter and a private full-rank adapter for better personalization.","FedLAFP splits federated fine-tuning into two jobs instead of forcing one adapter to do both.\n\nResearchers propose FedLAFP, a framework for federated parameter-efficient fine-tuning, the technique that lets phones, hospitals, or other clients adapt a shared pretrained model without uploading raw data. Instead of using one low-rank adapter for both shared knowledge and client-specific quirks, FedLAFP pairs two: a compact LoRA branch that gets averaged across all clients, and a private RandLoRA branch, built from fixed random low-rank bases plus learned scaling coefficients, that never leaves the device. A per-client, per-layer mixing coefficient blends the two, and only the shared LoRA weights are ever transmitted. Across four visual recognition benchmarks, the approach reached an average personalized accuracy of 86.93%, beating the best federated LoRA baseline by 1.30 percentage points.\n\nFederated fine-tuning has mostly reused the same low-rank recipe for both the parts that need to generalize and the parts that need to stay idiosyncratic, and that mismatch is a likely reason personalization has lagged. FedLAFP's contribution is not a bigger model or more data. It is recognizing that aggregation and personalization want different math, then building the plumbing so only the aggregation-friendly piece travels over the network.\n\nA 1.3-point bump on four benchmarks is solid, not spectacular, and \"full-rank-capable\" here means a richer private adapter, not an actually full-rank model. The real test is whether this holds up past image classification, in noisier, real-world federated deployments.","[\"federated learning\",\"fine-tuning\",\"personalization\",\"machine learning\"]","2026-09-30T04:00:00.000Z","2026-09-30T07:40:54.272Z","2026-09-30T07:41:00.949Z","published",null,[],"ai",[26,27,28,29],"federated learning","fine-tuning","personalization","machine learning",[31],{"name":32,"url":33},"arXiv cs.AI","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.37033",0,{"sections":36},[37,40,44,48,53,58,63,68,73,78,83,88,93,98],{"name":38,"slug":24,"count":39,"latest_published_at":18},"AI",5028,{"name":41,"slug":42,"count":43,"latest_published_at":18},"Security","security",780,{"name":45,"slug":46,"count":47,"latest_published_at":18},"Policy","policy",417,{"name":49,"slug":50,"count":51,"latest_published_at":52},"Deals","deals",284,"2026-09-29T21:00:00.000Z",{"name":54,"slug":55,"count":56,"latest_published_at":57},"Hardware","hardware",194,"2026-09-29T13:16:04.000Z",{"name":59,"slug":60,"count":61,"latest_published_at":62},"Science","science",154,"2026-09-28T13:19:18.000Z",{"name":64,"slug":65,"count":66,"latest_published_at":67},"Consumer Tech","consumer-tech",142,"2026-09-29T18:38:03.000Z",{"name":69,"slug":70,"count":71,"latest_published_at":72},"Software","software",91,"2026-09-25T20:55:00.000Z",{"name":74,"slug":75,"count":76,"latest_published_at":77},"Dev Tools","dev-tools",89,"2026-09-29T17:15:00.000Z",{"name":79,"slug":80,"count":81,"latest_published_at":82},"Startups","startups",83,"2026-09-29T21:51:36.000Z",{"name":84,"slug":85,"count":86,"latest_published_at":87},"General","general",49,"2026-09-28T16:44:57.000Z",{"name":89,"slug":90,"count":91,"latest_published_at":92},"Gaming","gaming",48,"2026-09-25T18:35:21.000Z",{"name":94,"slug":95,"count":96,"latest_published_at":97},"Reviews","reviews",31,"2026-09-28T14:31:34.000Z",{"name":99,"slug":100,"count":101,"latest_published_at":102},"How-To","how-to",6,"2026-06-16T09:00:00.000Z"]