Adaptive Tip Selection for DAG-Shard-Based Federated Learning with High Concurrency and Fairness
To cope with the challenges posed by high-concurrency training tasks involving large models and big data, Directed Acyclic Graph (DAG) and shard were proposed as alternatives to blockchain-based federated learning, aiming to enhance training concurrency. However, there is insufficient research on th...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/1/19 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549030596804608 |
|---|---|
| author | Ruiqi Xiao Yun Cao Bin Xia |
| author_facet | Ruiqi Xiao Yun Cao Bin Xia |
| author_sort | Ruiqi Xiao |
| collection | DOAJ |
| description | To cope with the challenges posed by high-concurrency training tasks involving large models and big data, Directed Acyclic Graph (DAG) and shard were proposed as alternatives to blockchain-based federated learning, aiming to enhance training concurrency. However, there is insufficient research on the specific consensus designs and the effects of varying shard sizes on federated learning. In this paper, we combine DAG and shard by designing three tip selection consensus algorithms and propose an adaptive algorithm to improve training performance. Additionally, we achieve concurrent control over the scale of the directed acyclic graph’s structure through shard and algorithm adjustments. Finally, we validate the fairness of our model with an incentive mechanism and its robustness under different real-world conditions and demonstrate DAG-Shard-based Federated Learning (DSFL)’s advantages in high concurrency and fairness while adjusting the DAG size through concurrency control. In concurrency, DSFL improves accuracy by 8.19–12.21% and F1 score by 7.27–11.73% compared to DAG-FL. Compared to Blockchain-FL, DSFL shows an accuracy gain of 7.82–11.86% and an F1 score improvement of 8.89–13.27%. Additionally, DSFL outperforms DAG-FL and Chains-FL on both balanced and imbalanced datasets. |
| format | Article |
| id | doaj-art-e34ed29d46004eebba984f246a7ff050 |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-e34ed29d46004eebba984f246a7ff0502025-01-10T13:20:35ZengMDPI AGSensors1424-82202024-12-012511910.3390/s25010019Adaptive Tip Selection for DAG-Shard-Based Federated Learning with High Concurrency and FairnessRuiqi Xiao0Yun Cao1Bin Xia2School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing 210023, ChinaSchool of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing 210023, ChinaSchool of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing 210023, ChinaTo cope with the challenges posed by high-concurrency training tasks involving large models and big data, Directed Acyclic Graph (DAG) and shard were proposed as alternatives to blockchain-based federated learning, aiming to enhance training concurrency. However, there is insufficient research on the specific consensus designs and the effects of varying shard sizes on federated learning. In this paper, we combine DAG and shard by designing three tip selection consensus algorithms and propose an adaptive algorithm to improve training performance. Additionally, we achieve concurrent control over the scale of the directed acyclic graph’s structure through shard and algorithm adjustments. Finally, we validate the fairness of our model with an incentive mechanism and its robustness under different real-world conditions and demonstrate DAG-Shard-based Federated Learning (DSFL)’s advantages in high concurrency and fairness while adjusting the DAG size through concurrency control. In concurrency, DSFL improves accuracy by 8.19–12.21% and F1 score by 7.27–11.73% compared to DAG-FL. Compared to Blockchain-FL, DSFL shows an accuracy gain of 7.82–11.86% and an F1 score improvement of 8.89–13.27%. Additionally, DSFL outperforms DAG-FL and Chains-FL on both balanced and imbalanced datasets.https://www.mdpi.com/1424-8220/25/1/19directed acyclic graphblockchainfederated learninghigh concurrencyfair incentive |
| spellingShingle | Ruiqi Xiao Yun Cao Bin Xia Adaptive Tip Selection for DAG-Shard-Based Federated Learning with High Concurrency and Fairness Sensors directed acyclic graph blockchain federated learning high concurrency fair incentive |
| title | Adaptive Tip Selection for DAG-Shard-Based Federated Learning with High Concurrency and Fairness |
| title_full | Adaptive Tip Selection for DAG-Shard-Based Federated Learning with High Concurrency and Fairness |
| title_fullStr | Adaptive Tip Selection for DAG-Shard-Based Federated Learning with High Concurrency and Fairness |
| title_full_unstemmed | Adaptive Tip Selection for DAG-Shard-Based Federated Learning with High Concurrency and Fairness |
| title_short | Adaptive Tip Selection for DAG-Shard-Based Federated Learning with High Concurrency and Fairness |
| title_sort | adaptive tip selection for dag shard based federated learning with high concurrency and fairness |
| topic | directed acyclic graph blockchain federated learning high concurrency fair incentive |
| url | https://www.mdpi.com/1424-8220/25/1/19 |
| work_keys_str_mv | AT ruiqixiao adaptivetipselectionfordagshardbasedfederatedlearningwithhighconcurrencyandfairness AT yuncao adaptivetipselectionfordagshardbasedfederatedlearningwithhighconcurrencyandfairness AT binxia adaptivetipselectionfordagshardbasedfederatedlearningwithhighconcurrencyandfairness |