FlexDeMo: Decoupled Momentum Optimization for Hybrid Sharded Data Parallel Training

• URL: http://arxiv.org/abs/2502.06728v2
• Date: Tue, 18 Mar 2025 16:00:57 GMT
• Title: FlexDeMo: Decoupled Momentum Optimization for Hybrid Sharded Data Parallel Training
• Authors: Mogens Henrik From, Jacob Nielsen, Lukas Galke, Peter Schneider-Kamp,
• Abstract summary: Training large neural network models requires extensive computational resources, often distributed across several nodes and accelerators.<n>Recent findings suggest that it may be sufficient to only exchange the fast moving components of the gradients, while accumulating momentum locally (Decoupled Momentum)<n>Here, we propose employing a hybrid sharded data parallel training strategy, FlexDeMo, whereby nodes fully shard model parameters locally between different accelerators.
• Score: 5.191183730031093
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training large neural network models requires extensive computational resources, often distributed across several nodes and accelerators. Recent findings suggest that it may be sufficient to only exchange the fast moving components of the gradients, while accumulating momentum locally (Decoupled Momentum, or DeMo). However, when considering larger models that do not fit on a single accelerator, the exchange of gradient information and the integration of DeMo needs to be reconsidered. Here, we propose employing a hybrid sharded data parallel training strategy, FlexDeMo, whereby nodes fully shard model parameters locally between different accelerators, while inter-node communication bandwidth requirements are reduced by synchronizing only fast-moving components instead of the full gradients. This effectively combines previous hybrid sharded strategies with the advantages of decoupled momentum. Our experimental results show that FlexDeMo is on par with hybrid sharded data parallel training employing AdamW and full gradient synchronization in terms of validation loss, demonstrating its viability. Furthermore, FlexDeMo achieves improved training speed compared to full gradient synchronization across nodes. In a bandwidth-constrained 2-node setup, FlexDeMo allows reaching desired levels of validation loss faster than hybrid sharded data parallel training with full gradient synchronization.

Related papers

• Accelerating Mixture-of-Experts Training with Adaptive Expert Replication [1.8764600940655036]
  We introduce SwiftMoE, an adaptive MoE training system. SwiftMoE right-sizes the GPU resources allocated to each expert, on a per-iteration basis, with minimal overheads. Compared to state-of-the-art MoE training systems, DeepSpeed and FlexMoE, SwiftMoE is able to achieve a 30.5% and 25.9% faster time-to-convergence.
  arXiv  Detail & Related papers  (2025-04-28T15:58:55Z)
• DeMo: Decoupled Momentum Optimization [6.169574689318864]
  Training large neural networks typically requires sharing between accelerators through specialized high-speed interconnects.<n>We introduce bfDecoupled textbfMomentum (DeMo), a fused magnitude and data parallel algorithm that reduces inter-accelerator communication requirements.<n> Empirical results show that models trained with DeMo match or exceed the performance of equivalent models trained with AdamW.
  arXiv  Detail & Related papers  (2024-11-29T17:31:47Z)
• MobileMamba: Lightweight Multi-Receptive Visual Mamba Network [51.33486891724516]
  Previous research on lightweight models has primarily focused on CNNs and Transformer-based designs. We propose the MobileMamba framework, which balances efficiency and performance. MobileMamba achieves up to 83.6% on Top-1, surpassing existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-11-24T18:01:05Z)
• Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging [111.8456671452411]
  Multi-task learning (MTL) leverages a shared model to accomplish multiple tasks and facilitate knowledge transfer. We propose a Weight-Ensembling Mixture of Experts (WEMoE) method for multi-task model merging. We show that WEMoE and E-WEMoE outperform state-of-the-art (SOTA) model merging methods in terms of MTL performance, generalization, and robustness.
  arXiv  Detail & Related papers  (2024-10-29T07:16:31Z)
• Stragglers-Aware Low-Latency Synchronous Federated Learning via Layer-Wise Model Updates [71.81037644563217]
  Synchronous federated learning (FL) is a popular paradigm for collaborative edge learning. As some of the devices may have limited computational resources and varying availability, FL latency is highly sensitive to stragglers. We propose straggler-aware layer-wise federated learning (SALF) that leverages the optimization procedure of NNs via backpropagation to update the global model in a layer-wise fashion.
  arXiv  Detail & Related papers  (2024-03-27T09:14:36Z)
• LocMoE: A Low-Overhead MoE for Large Language Model Training [13.153904674287546]
  We propose a novel routing strategy that combines load balance and locality by converting partial inter-node communication to that of intra-node. The proposed LocMoE reduces training time per epoch by 12.68% to 22.24% compared to classical routers.
  arXiv  Detail & Related papers  (2024-01-25T03:36:39Z)
• Ravnest: Decentralized Asynchronous Training on Heterogeneous Devices [0.0]
  Ravnest facilitates decentralized training by efficiently organizing compute nodes into clusters. We have framed our asynchronous SGD loss function as a block structured optimization problem with delayed updates.
  arXiv  Detail & Related papers  (2024-01-03T13:07:07Z)
• Efficient Asynchronous Federated Learning with Sparsification and Quantization [55.6801207905772]
  Federated Learning (FL) is attracting more and more attention to collaboratively train a machine learning model without transferring raw data. FL generally exploits a parameter server and a large number of edge devices during the whole process of the model training. We propose TEASQ-Fed to exploit edge devices to asynchronously participate in the training process by actively applying for tasks.
  arXiv  Detail & Related papers  (2023-12-23T07:47:07Z)
• Adaptive Federated Pruning in Hierarchical Wireless Networks [69.6417645730093]
  Federated Learning (FL) is a privacy-preserving distributed learning framework where a server aggregates models updated by multiple devices without accessing their private datasets. In this paper, we introduce model pruning for HFL in wireless networks to reduce the neural network scale. We show that our proposed HFL with model pruning achieves similar learning accuracy compared with the HFL without model pruning and reduces about 50 percent communication cost.
  arXiv  Detail & Related papers  (2023-05-15T22:04:49Z)
• Pipeline MoE: A Flexible MoE Implementation with Pipeline Parallelism [91.9372563527801]
  Existing MoE models suffer from tremendous inner-node and inter-node communication overhead. We propose a novel MoE architecture called Pipeline MoE (PPMoE) to tackle them. PPMoE builds expert parallel incorporating with tensor parallel and replaces communication-intensive all-to-all dispatching and gathering.
  arXiv  Detail & Related papers  (2023-04-22T14:09:14Z)
• Decouple Graph Neural Networks: Train Multiple Simple GNNs Simultaneously Instead of One [60.5818387068983]
  Graph neural networks (GNN) suffer from severe inefficiency. We propose to decouple a multi-layer GNN as multiple simple modules for more efficient training. We show that the proposed framework is highly efficient with reasonable performance.
  arXiv  Detail & Related papers  (2023-04-20T07:21:32Z)
• Multi-Carrier NOMA-Empowered Wireless Federated Learning with Optimal Power and Bandwidth Allocation [31.80744279032665]
  Wireless federated learning (WFL) undergoes a bottleneck communication in uplink, limiting the number of users that can upload their local models in each global aggregation round. This paper presents a new multi-carrier non-orthogonal multiple-access (MC-NOMA) WFL that allows the users to train different numbers of iterations per round. As corroborated using a convolutional neural network and an 18-layer residential network, the proposed MC-NOMA WFL can efficiently reduce communication, increase local model training times, and accelerate the convergence by over 40%, compared to its existing alternative.
  arXiv  Detail & Related papers  (2023-02-13T22:41:14Z)
• SMILE: Scaling Mixture-of-Experts with Efficient Bi-level Routing [47.11171833082974]
  We introduce SMILE, which exploits heterogeneous network bandwidth and splits a single-step routing into bi-level routing. Our experimental results show that the proposed method obtains a 2.5x speedup over Switch Transformer in terms of pretraining throughput on the Colossal Clean Crawled Corpus without losing any convergence speed.
  arXiv  Detail & Related papers  (2022-12-10T03:44:16Z)
• AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation [104.0979785739202]
  Mixture-of-Expert (MoE) models have obtained state-of-the-art performance in Neural Machine Translation (NMT) tasks. Existing MoE models mostly consider a homogeneous design where the same number of experts of the same size are placed uniformly throughout the network. We develop AutoMoE -- a framework for designing heterogeneous MoE's under computational constraints.
  arXiv  Detail & Related papers  (2022-10-14T05:32:17Z)
• Predictive GAN-powered Multi-Objective Optimization for Hybrid Federated Split Learning [56.125720497163684]
  We propose a hybrid federated split learning framework in wireless networks. We design a parallel computing scheme for model splitting without label sharing, and theoretically analyze the influence of the delayed gradient caused by the scheme on the convergence speed.
  arXiv  Detail & Related papers  (2022-09-02T10:29:56Z)
• Tutel: Adaptive Mixture-of-Experts at Scale [20.036168971435306]
  Sparsely-gated mixture-of-experts (MoE) has been widely adopted to scale deep learning models to trillion-plus parameters with fixed computational cost. We present Flex, a highly scalable stack design and implementation for MoE with dynamically adaptive parallelism and pipelining. Our evaluation shows that Flex efficiently and effectively runs a real-world MoE-based model named SwinV2-MoE, built upon Swin Transformer V2, a state-of-the-art computer vision architecture.
  arXiv  Detail & Related papers  (2022-06-07T15:20:20Z)
• Scaling Distributed Deep Learning Workloads beyond the Memory Capacity with KARMA [58.040931661693925]
  We propose a strategy that combines redundant recomputing and out-of-core methods. We achieve an average of 1.52x speedup in six different models over the state-of-the-art out-of-core methods. Our data parallel out-of-core solution can outperform complex hybrid model parallelism in training large models, e.g. Megatron-LM and Turning-NLG.
  arXiv  Detail & Related papers  (2020-08-26T07:24:34Z)

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.