{
  "annotation_id": "9fa82161-6c63-4630-84d6-a41845a7d27a",
  "date_created": "2026-02-17T05:53:20.216000Z",
  "date_modified": "2026-02-17T05:53:20.216000Z",
  "file_hash": "5c12cd1c43be22629ac7951eea95d1dfe9f15735142bb07c85aecf9f753aa825",
  "private": false,
  "record": {
    "abstract": "Split Federated Learning (SFL) enables collaborative training between resource-constrained edge devices and a compute-rich server. Communication overhead is a central issue in SFL and can be mitigated with auxiliary networks. Yet, the fundamental client-side computation challenge remains, as back-propagation requires substantial memory and computation costs, severely limiting the scale of models that edge devices can support. To enable more resource-efficient client computation and reduce the client-server communication, we propose HERON-SFL, a novel hybrid optimization framework that integrates zeroth-order (ZO) optimization for local client training while retaining first-order (FO) optimization on the server. With the assistance of auxiliary networks, ZO updates enable clients to approximate local gradients using perturbed forward-only evaluations per step, eliminating memory-intensive activation caching and avoiding explicit gradient computation in the traditional training process. Leveraging the low effective rank assumption, we theoretically prove that HERON-SFL\u0027s convergence rate is independent of model dimensionality, addressing a key scalability concern common to ZO algorithms. Empirically, on ResNet training and language model (LM) fine-tuning tasks, HERON-SFL matches benchmark accuracy while reducing client peak memory by up to 64% and client-side compute cost by up to 33% per step, substantially expanding the range of models that can be trained or adapted on resource-limited devices.",
    "arxiv_id": "2601.09076",
    "authors": [
      "Zhoubin Kou",
      "Zihan Chen",
      "Jing Yang",
      "Cong Shen"
    ],
    "categories": [
      "cs.LG",
      "cs.DC",
      "cs.IT",
      "cs.NI",
      "eess.SP",
      "math.IT"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "Lean Clients, Full Accuracy: Hybrid Zeroth- and First-Order Split Federated Learning",
    "url": "https://arxiv.org/abs/2601.09076",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "9be8fa2e-41ce-40b6-96d9-08c776e0670d",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}