DualPFL: A Dual Sparse Pruning Method with Efficient Federated Learning for Edge-Based Object Detection
Source abstract
Abstract
With the increasing complexity of neural network models, the huge communication overhead in federated learning (FL) has become a significant issue. To mitigate resource consumption, incorporating pruning algorithms into federated learning has emerged as a promising approach. However, existing pruning algorithms exhibit high sensitivity to network architectures and typically require multiple sessions of retraining to identify optimal structures. The direct application of such strategies to FL would inevitably introduce an additional communication cost. To this end, we propose a novel communication-efficient federated learning framework, DualPFL (Dual Sparse Pruning Federated Learning), designed to address these issues by implementing dynamic sparse pruning and adaptive model aggregation strategies. The experimental results demonstrate that, compared to similar works, our framework can improve convergence speed by more than two times under non-IID data, achieving up to 84% accuracy on the CIFAR-10 dataset, 95% mean average precision (mAP) on the COCO dataset using YOLOv8, and 96% accuracy on the TT100K traffic sign datasets. These findings indicate that DualPFL facilitates secure and efficient collaborative computing in smart city applications.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Image and Video Retrieval Techniques · Advanced Neural Network Applications · Video Surveillance and Tracking Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201203, China
Funding
National Natural Science Foundation of China · Science and Technology Service Network Initiative of Chinese Academy of Sciences
References (50)
Show source-provided references
1. McMahan, H.B. (2017, January 20–22). Communication-Efficient Learning of Deep Networks from Decentralized Data. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA.
2. Federated Learning in Intelligent Transportation Systems: Recent Applications and Open Problems10.1109/TITS.2023.3324962 ↗
3. Federated Learning for Wireless Communications: Motivation, Opportunities and Challenges10.1109/MCOM.001.1900461 ↗
4. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2021). An Image Is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv.
5. Keskar, N.S., McCann, B., Varshney, L.R., Xiong, C., and Socher, R. (2019). CTRL: A Conditional Transformer Language Model for Controllable Generation. arXiv.
6. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
7. Toward Efficient and Secure Object Detection with Sparse Federated Training Over Internet of Vehicles10.1109/TITS.2024.3389212 ↗
8. Rao, L., Ma, C., Ding, M., Qian, Y., Zhou, L., and Liu, Z. (June, January 28). Sparse Federated Training of Object Detection in the Internet of Vehicles. Proceedings of the ICC 2023—IEEE International Conference on Communications, Rome, Italy.10.1109/ICC45041.2023.10278660 ↗
9. Zhang, Z., Jin, J., Zhang, Z., Zhou, Y., Zhao, X., Ren, J., Liu, J., Wu, L., Jin, R., and Dou, D. (2021, January 6–14). Validating the Lottery Ticket Hypothesis with Inertial Manifold Theory. Proceedings of the 35th International Conference on Neural Information Processing Systems, Virtual.
10. Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., and Zhang, C. (2017, January 22–29). Learning Efficient Convolutional Networks through Network Slimming. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.298 ↗
11. Heterogeneous Federated Learning: State-of-the-Art and Research Challenges
12. Chen, H., Frikha, A., Krompass, D., Gu, J., and Tresp, V. (2023, January 1–6). FRAug: Tackling Federated Learning with Non-IID Features via Representation Augmentation. Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France.10.1109/ICCV51070.2023.00447 ↗
13. Li, A., Sun, J., Zeng, X., Zhang, M., Li, H., and Chen, Y. (2021, January 6–9). FedMask: Joint Computation and Communication-Efficient Personalized Federated Learning via Heterogeneous Masking. Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems, New York, NY, USA.10.1145/3485730.3485929 ↗
14. Dai, R., Shen, L., He, F., Tian, X., and Tao, D. (2022). DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training. arXiv.
15. Neuron-Level Structured Pruning Using Polarization Regularizer
16. Yuan, X., Savarese, P., and Maire, M. (2023). Growing Efficient Deep Networks by Structured Continuous Sparsification. arXiv.
17. StructADMM: Achieving Ultrahigh Efficiency in Structured Pruning for DNNs10.1109/TNNLS.2020.3045153 ↗
18. Ye, X., Dai, P., Luo, J., Guo, X., Qi, Y., Yang, J., Chen, Y., and Zhao, W. (2020, January 23–28). Accelerating CNN Training by Pruning Activation Gradients. Proceedings of the Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK.10.1007/978-3-030-58595-2_20 ↗
19. Evci, U., Gale, T., Menick, J., Castro, P.S., and Elsen, E. (2020, January 12–18). Rigging the Lottery: Making All Tickets Winners. Proceedings of the 37th International Conference on Machine Learning, Vienna, Austria.
20. Li, H., Kadav, A., Durdanovic, I., Samet, H., and Graf, H.P. (2017, January 24–26). Pruning Filters for Efficient ConvNets. Proceedings of the 5th International Conference on Learning Representations (ICLR) 2017, Toulon, France.
21. Lin, S., Ji, R., Li, Y., Wu, Y., Huang, F., and Zhang, B. (2018, January 13–19). Accelerating Convolutional Networks via Global & Dynamic Filter Pruning. Proceedings of the 27th International Joint Conference on Artificial Intelligence, Stockholm, Sweden.10.24963/ijcai.2018/336 ↗
22. He, Y., Kang, G., Dong, X., Fu, Y., and Yang, Y. (2018, January 13–19). Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks. Proceedings of the 27th International Joint Conference on Artificial Intelligence, Stockholm, Sweden.10.24963/ijcai.2018/309 ↗
23. J-IEEETFS23-Federated Fuzzy Neural Network with Evolutionary Rule Learning10.1109/TFUZZ.2022.3207607 ↗
24. J-IEEETII23-R2Fed: Resilient Reinforcement Federated Learning for Industrial Applications10.1109/TII.2022.3222369 ↗
25. Towards Personalized Federated Learning10.1109/TNNLS.2022.3160699 ↗
26. Wang, K., Mathews, R., Kiddon, C., Eichner, H., Beaufays, F., and Ramage, D. (2019). Federated Evaluation of On-Device Personalization. arXiv.
27. Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach
28. Khodak, M., Balcan, M.-F.F., and Talwalkar, A.S. (2019). Adaptive Gradient-Based Meta-Learning Methods. Advances in Neural Information Processing Systems, Curran Associates, Inc.
29. Federated Optimization in Heterogeneous Networks
30. Personalized Federated Learning with Moreau Envelopes
31. Li, T., Hu, S., Beirami, A., and Smith, V. (2021, January 18–24). Ditto: Fair and Robust Federated Learning Through Personalization. Proceedings of the 38th International Conference on Machine Learning, Virtual.
32. Mendieta, M., Yang, T., Wang, P., Lee, M., Ding, Z., and Chen, C. (2022, January 18–24). Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.00821 ↗
33. Hanzely, F., and Richtárik, P. (2021). Federated Learning of a Mixture of Global and Local Models. arXiv.
34. Liang, P.P., Liu, T., Ziyin, L., Allen, N.B., Auerbach, R.P., Brent, D., Salakhutdinov, R., and Morency, L.-P. (2020). Think Locally, Act Globally: Federated Learning with Local and Global Representations. arXiv.
35. Marfoq, O., Neglia, G., Vidal, R., and Kameni, L. (2022, January 17–23). Personalized Federated Learning through Local Memorization. Proceedings of the 39th International Conference on Machine Learning, Baltimore, MD, USA.
36. Li, D., and Wang, J. (2019). FedMD: Heterogenous Federated Learning via Model Distillation. arXiv.
37. Zhu, Z., Hong, J., and Zhou, J. (2021, January 18–24). Data-Free Knowledge Distillation for Heterogeneous Federated Learning. Proceedings of the 38th International Conference on Machine Learning, Virtual.
38. Zhang, L., Shen, L., Ding, L., Tao, D., and Duan, L.-Y. (2022, January 21–24). Fine-Tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.00993 ↗
39. Zhou, Y., Shi, M., Tian, Y., Li, Y., Ye, Q., and Lv, J. (2024, January 14–19). Federated CINN Clustering for Accurate Clustered Federated Learning. Proceedings of the ICASSP 2024—2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Republic of Korea.10.1109/ICASSP48485.2024.10447282 ↗
40. Clustered Federated Learning: Model-Agnostic Distributed Multitask Optimization Under Privacy Constraints10.1109/TNNLS.2020.3015958 ↗
41. Liu, B., Guo, Y., and Chen, X. (2021, January 19–23). C-WWW21-PFA: Privacy-Preserving Federated Adaptation for Effective Model Personalization. Proceedings of the Web Conference 2021, Virtual.10.1145/3442381.3449847 ↗
42. Zhang, H., Liu, J., Jia, J., Zhou, Y., Dai, H., and Dou, D. (2022). FedDUAP: Federated Learning with Dynamic Update and Adaptive Pruning Using Shared Data on the Server. arXiv.10.24963/ijcai.2022/385 ↗
43. Jiang, Z., Xu, Y., Xu, H., Wang, Z., Qiao, C., and Zhao, Y. (2022, January 9–12). FedMP: Federated Learning through Adaptive Model Pruning in Heterogeneous Edge Computing. Proceedings of the 2022 IEEE 38th International Conference on Data Engineering (ICDE), Kuala Lumpur, Malaysia.10.1109/ICDE53745.2022.00062 ↗
44. Zhan, Z., and Zhang, X. (2023, January 18–21). Computation-Effective Personalized Federated Learning: A Meta Learning Approach. Proceedings of the 2023 IEEE 43rd International Conference on Distributed Computing Systems (ICDCS), Hong Kong, China.10.1109/ICDCS57875.2023.00106 ↗
45. A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS10.3390/make5040083 ↗
46. YOLOv1 to v8: Unveiling Each Variant–A Comprehensive Review of YOLO10.1109/ACCESS.2024.3378568 ↗
47. Zhu, Z., Liang, D., Zhang, S., Huang, X., Li, B., and Hu, S. (2016, January 27–30). Traffic-Sign Detection and Classification in the Wild. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.232 ↗
48. Zhu, Z., Shi, Y., Luo, J., Wang, F., Peng, C., Fan, P., and Letaief, K.B. (June, January 28). FedLP: Layer-Wise Pruning Mechanism for Communication-Computation Efficient Federated Learning. Proceedings of the ICC 2023—IEEE International Conference on Communications, Rome, Italy.10.1109/ICC45041.2023.10278563 ↗
49. FedKD: Communication Efficient Federated Learning via Knowledge Distillation10.1038/s41467-022-29763-x ↗
50. Zhang, J., Hua, Y., Wang, H., Song, T., Xue, Z., Ma, R., and Guan, H. (2023, January 7–14). FedALA: Adaptive Local Aggregation for Personalized Federated Learning. Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA.10.1609/aaai.v37i9.26330 ↗