Hetero-SplitEE: Split Learning of Neural Networks with Early Exits for Heterogeneous IoT Devices

• URL: http://arxiv.org/abs/2512.09313v1
• Date: Wed, 10 Dec 2025 04:58:26 GMT
• Title: Hetero-SplitEE: Split Learning of Neural Networks with Early Exits for Heterogeneous IoT Devices
• Authors: Yuki Oda, Yuta Ono, Hiroshi Nakamura, Hideki Takase,
• Abstract summary: Hetero-SplitEE is a novel method that enables heterogeneous IoT devices to train a shared deep neural network in parallel collaboratively.<n>By integrating heterogeneous early exits into hierarchical training, our approach allows each client to select distinct split points tailored to its computational capacity.<n>In addition, we propose two cooperative training strategies, the Sequential strategy and the Averaging strategy, to facilitate this collaboration among clients with different split points.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The continuous scaling of deep neural networks has fundamentally transformed machine learning, with larger models demonstrating improved performance across diverse tasks. This growth in model size has dramatically increased the computational resources required for the training process. Consequently, distributed approaches, such as Federated Learning and Split Learning, have become essential paradigms for scalable deployment. However, existing Split Learning approaches assume client homogeneity and uniform split points across all participants. This critically limits their applicability to real-world IoT systems where devices exhibit heterogeneity in computational resources. To address this limitation, this paper proposes Hetero-SplitEE, a novel method that enables heterogeneous IoT devices to train a shared deep neural network in parallel collaboratively. By integrating heterogeneous early exits into hierarchical training, our approach allows each client to select distinct split points (cut layers) tailored to its computational capacity. In addition, we propose two cooperative training strategies, the Sequential strategy and the Averaging strategy, to facilitate this collaboration among clients with different split points. The Sequential strategy trains clients sequentially with a shared server model to reduce computational overhead. The Averaging strategy enables parallel client training with periodic cross-layer aggregation. Extensive experiments on CIFAR-10, CIFAR-100, and STL-10 datasets using ResNet-18 demonstrate that our method maintains competitive accuracy while efficiently supporting diverse computational constraints, enabling practical deployment of collaborative deep learning in heterogeneous IoT ecosystems.

Related papers

• CollaPipe: Adaptive Segment-Optimized Pipeline Parallelism for Collaborative LLM Training in Heterogeneous Edge Networks [57.95170323315603]
  We introduce CollaPipe, a distributed learning framework that integrates collaborative pipeline parallelism with federated aggregation to support self-evolving networks.<n>In CollaPipe, the encoder part is adaptively partitioned into variable-sized segments and deployed across mobile devices for pipeline-parallel training, while the decoder is deployed on edge servers to handle generative tasks.<n>To enhance training efficiency, we formulate a joint optimization problem that adaptively allocates model segments, micro-batches, bandwidth, and transmission power.
  arXiv  Detail & Related papers  (2025-09-24T07:54:01Z)
• FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression [55.992528247880685]
  Decentralized training faces significant challenges regarding system design and efficiency. We present FusionLLM, a decentralized training system designed and implemented for training large deep neural networks (DNNs) We show that our system and method can achieve 1.45 - 9.39x speedup compared to baseline methods while ensuring convergence.
  arXiv  Detail & Related papers  (2024-10-16T16:13:19Z)
• An effective and efficient green federated learning method for one-layer neural networks [0.22499166814992436]
  Federated learning (FL) is one of the most active research lines in machine learning. We present a FL method, based on a neural network without hidden layers, capable of generating a global collaborative model in a single training round. We show that the method performs equally well in both identically and non-identically distributed scenarios.
  arXiv  Detail & Related papers  (2023-12-22T08:52:08Z)
• FedLALR: Client-Specific Adaptive Learning Rates Achieve Linear Speedup for Non-IID Data [54.81695390763957]
  Federated learning is an emerging distributed machine learning method. We propose a heterogeneous local variant of AMSGrad, named FedLALR, in which each client adjusts its learning rate. We show that our client-specified auto-tuned learning rate scheduling can converge and achieve linear speedup with respect to the number of clients.
  arXiv  Detail & Related papers  (2023-09-18T12:35:05Z)
• Effectively Heterogeneous Federated Learning: A Pairing and Split Learning Based Approach [16.093068118849246]
  This paper presents a novel split federated learning (SFL) framework that pairs clients with different computational resources. A greedy algorithm is proposed by reconstructing the optimization of training latency as a graph edge selection problem. Simulation results show the proposed method can significantly improve the FL training speed and achieve high performance.
  arXiv  Detail & Related papers  (2023-08-26T11:10:54Z)
• Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networks [44.37047471448793]
  In this paper, we advocate the integration of edge computing paradigm and parallel split learning (PSL) We propose an innovative PSL framework, namely, efficient parallel split learning (EPSL) to accelerate model training. We show that the proposed EPSL framework significantly decreases the training latency needed to achieve a target accuracy.
  arXiv  Detail & Related papers  (2023-03-26T16:09:48Z)
• Unifying Synergies between Self-supervised Learning and Dynamic Computation [53.66628188936682]
  We present a novel perspective on the interplay between SSL and DC paradigms. We show that it is feasible to simultaneously learn a dense and gated sub-network from scratch in a SSL setting. The co-evolution during pre-training of both dense and gated encoder offers a good accuracy-efficiency trade-off.
  arXiv  Detail & Related papers  (2023-01-22T17:12:58Z)
• Sparse Interaction Additive Networks via Feature Interaction Detection and Sparse Selection [10.191597755296163]
  We develop a tractable selection algorithm to efficiently identify the necessary feature combinations. Our proposed Sparse Interaction Additive Networks (SIAN) construct a bridge from simple and interpretable models to fully connected neural networks.
  arXiv  Detail & Related papers  (2022-09-19T19:57:17Z)
• Flexible Parallel Learning in Edge Scenarios: Communication, Computational and Energy Cost [20.508003076947848]
  Fog- and IoT-based scenarios often require combining both approaches. We present a framework for flexible parallel learning (FPL), achieving both data and model parallelism. Our experiments, carried out using state-of-the-art deep-network architectures and large-scale datasets, confirm that FPL allows for an excellent trade-off among computational (hence energy) cost, communication overhead, and learning performance.
  arXiv  Detail & Related papers  (2022-01-19T03:47:04Z)
• Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data [77.88594632644347]
  Decentralized training of deep learning models is a key element for enabling data privacy and on-device learning over networks. In realistic learning scenarios, the presence of heterogeneity across different clients' local datasets poses an optimization challenge. We propose a novel momentum-based method to mitigate this decentralized training difficulty.
  arXiv  Detail & Related papers  (2021-02-09T11:27:14Z)
• Fitting the Search Space of Weight-sharing NAS with Graph Convolutional Networks [100.14670789581811]
  We train a graph convolutional network to fit the performance of sampled sub-networks. With this strategy, we achieve a higher rank correlation coefficient in the selected set of candidates.
  arXiv  Detail & Related papers  (2020-04-17T19:12:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.