{"ID":5676602,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-03T19:58:09.389792377Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01272","arxiv_id":"2607.01272","title":"Benchmarking Federated Learning and Knowledge Distillation for Point Cloud Classification","abstract":"Deploying 3D point cloud analysis in privacy-sensitive, resource-constrained settings faces two barriers: data cannot be centralized, and models must run on limited edge hardware. We present a multi-seed benchmark jointly evaluating federated learning (FL) and knowledge distillation (KD) for 3D point cloud classification. It spans 13 FL algorithms and 10 KD objectives (a 130-pair cross-product) across 504 training runs, evaluated on ModelNet40 and a clinical craniosynostosis dataset. We report three findings. First, under extreme non-IID label skew, standalone FL degrades sharply: on ModelNet40, the strongest method reaches 76.32% against a 92.26% centralized reference; on clinical data, the best reaches 75.83% against 100%. Second, distillation successfully compresses the teacher into a student 74.51% smaller and roughly twice as fast at inference, often matching or surpassing the teacher. Third, the combined pipeline exposes an evaluation pitfall: when distillation keeps a hard-label cross-entropy term on a labeled proxy split, a collapsed federated teacher (8.50%) paired with Logit-MSE still yields a 92.94% student. This 84.4-point gap reflects the proxy labels rather than the federated model, reusing the very labels whose privacy motivated federation. Objectives without hard labels instead track teacher quality ($r \\approx 0.99$) and collapse when the teacher does. We therefore recommend evaluating FL-KD pipelines with label-free distillation so reported accuracy reflects the federated teacher, not the proxy.","short_abstract":"Deploying 3D point cloud analysis in privacy-sensitive, resource-constrained settings faces two barriers: data cannot be centralized, and models must run on limited edge hardware. We present a multi-seed benchmark jointly evaluating federated learning (FL) and knowledge distillation (KD) for 3D point cloud classificati...","url_abs":"https://arxiv.org/abs/2607.01272","url_pdf":"https://arxiv.org/pdf/2607.01272v1","authors":"[\"Aizierjiang Aiersilan\"]","published":"2026-06-30T20:12:27Z","proceeding":"cs.GR","tasks":"[\"cs.GR\",\"cs.AI\",\"cs.CV\",\"cs.DC\",\"cs.LG\"]","methods":"[]","has_code":false}