Reducing Communication for Split Learning by Randomized Top-k Sparsification

• URL: http://arxiv.org/abs/2305.18469v1
• Date: Mon, 29 May 2023 09:02:05 GMT
• Title: Reducing Communication for Split Learning by Randomized Top-k Sparsification
• Authors: Fei Zheng, Chaochao Chen, Lingjuan Lyu, Binhui Yao
• Abstract summary: Split learning is a simple solution for Vertical Federated Learning (VFL) We investigate multiple communication reduction methods for split learning, including cut layer size reduction, top-k sparsification, quantization, and L1 regularization. Our proposed randomized top-k sparsification achieves a better model performance under the same compression level.
• Score: 25.012786154486164
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Split learning is a simple solution for Vertical Federated Learning (VFL), which has drawn substantial attention in both research and application due to its simplicity and efficiency. However, communication efficiency is still a crucial issue for split learning. In this paper, we investigate multiple communication reduction methods for split learning, including cut layer size reduction, top-k sparsification, quantization, and L1 regularization. Through analysis of the cut layer size reduction and top-k sparsification, we further propose randomized top-k sparsification, to make the model generalize and converge better. This is done by selecting top-k elements with a large probability while also having a small probability to select non-top-k elements. Empirical results show that compared with other communication-reduction methods, our proposed randomized top-k sparsification achieves a better model performance under the same compression level.

Related papers

• Optimizing Split Points for Error-Resilient SplitFed Learning [2.2530496464901106]
  SplitFed aims to minimize the computational burden on individual clients in FL and parallelize SL while maintaining privacy. This study investigates the resilience of SplitFed to packet loss at model split points.
  arXiv  Detail & Related papers  (2024-05-29T19:03:27Z)
• Ada-QPacknet -- adaptive pruning with bit width reduction as an efficient continual learning method without forgetting [0.8681331155356999]
  In this work new architecture based approach Ada-QPacknet is described. It incorporates the pruning for extracting the sub-network for each task. Results show that proposed approach outperforms most of the CL strategies in task and class incremental scenarios.
  arXiv  Detail & Related papers  (2023-08-14T12:17:11Z)
• Improved Distribution Matching for Dataset Condensation [91.55972945798531]
  We propose a novel dataset condensation method based on distribution matching. Our simple yet effective method outperforms most previous optimization-oriented methods with much fewer computational resources.
  arXiv  Detail & Related papers  (2023-07-19T04:07:33Z)
• A Comprehensively Improved Hybrid Algorithm for Learning Bayesian Networks: Multiple Compound Memory Erasing [0.0]
  This paper presents a new hybrid algorithm, MCME (multiple compound memory erasing) MCME retains the advantages of the first two methods, solves the shortcomings of the above CI tests, and makes innovations in the scoring function in the direction discrimination stage. A large number of experiments show that MCME has better or similar performance than some existing algorithms.
  arXiv  Detail & Related papers  (2022-12-05T12:52:07Z)
• Faster Adaptive Federated Learning [84.38913517122619]
  Federated learning has attracted increasing attention with the emergence of distributed data. In this paper, we propose an efficient adaptive algorithm (i.e., FAFED) based on momentum-based variance reduced technique in cross-silo FL.
  arXiv  Detail & Related papers  (2022-12-02T05:07:50Z)
• Communication-Compressed Adaptive Gradient Method for Distributed Nonconvex Optimization [21.81192774458227]
  One of the major bottlenecks is the large communication cost between the central server and the local workers. Our proposed distributed learning framework features an effective gradient gradient compression strategy.
  arXiv  Detail & Related papers  (2021-11-01T04:54:55Z)
• A Simple but Tough-to-Beat Data Augmentation Approach for Natural Language Understanding and Generation [53.8171136907856]
  We introduce a set of simple yet effective data augmentation strategies dubbed cutoff. cutoff relies on sampling consistency and thus adds little computational overhead. cutoff consistently outperforms adversarial training and achieves state-of-the-art results on the IWSLT2014 German-English dataset.
  arXiv  Detail & Related papers  (2020-09-29T07:08:35Z)
• Detached Error Feedback for Distributed SGD with Random Sparsification [98.98236187442258]
  Communication bottleneck has been a critical problem in large-scale deep learning. We propose a new distributed error feedback (DEF) algorithm, which shows better convergence than error feedback for non-efficient distributed problems. We also propose DEFA to accelerate the generalization of DEF, which shows better bounds than DEF.
  arXiv  Detail & Related papers  (2020-04-11T03:50:59Z)
• Attentive CutMix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification [58.20132466198622]
  We propose Attentive CutMix, a naturally enhanced augmentation strategy based on CutMix. In each training iteration, we choose the most descriptive regions based on the intermediate attention maps from a feature extractor. Our proposed method is simple yet effective, easy to implement and can boost the baseline significantly.
  arXiv  Detail & Related papers  (2020-03-29T15:01:05Z)
• Deep Unfolding Network for Image Super-Resolution [159.50726840791697]
  This paper proposes an end-to-end trainable unfolding network which leverages both learning-based methods and model-based methods. The proposed network inherits the flexibility of model-based methods to super-resolve blurry, noisy images for different scale factors via a single model.
  arXiv  Detail & Related papers  (2020-03-23T17:55:42Z)

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.