A Federated Multi-Task Learning Model Based onAdaptive Distributed Data Latent Correlation Analysis


Shengbin Wu, Yibai Wang, Journal of Information Processing Systems Vol. 17, No. 3, pp. 441-452, Jun. 2021  

10.3745/JIPS.01.0075
Keywords: Data distribution, Federated Multi-Task Learning, Rank Constraint, Underlying Structure
Fulltext:

Abstract

Federated learning provides an efficient integrated model for distributed data, allowing the local training of different data. Meanwhile, the goal of multi-task learning is to simultaneously establish models for multiple related tasks, and to obtain the underlying main structure. However, traditional federated multi-task learning models not only have strict requirements for the data distribution, but also demand large amounts of calculation and have slow convergence, which hindered their promotion in many fields. In our work, we apply the rank constraint on weight vectors of the multi-task learning model to adaptively adjust the task’s similarity learning, according to the distribution of federal node data. The proposed model has a general framework for solving optimal solutions, which can be used to deal with various data types. Experiments show that our model has achieved the best results in different dataset. Notably, our model can still obtain stable results in datasets with large distribution differences. In addition, compared with traditional federated multi-task learning models, our algorithm is able to converge on a local optimal solution within limited training iterations.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from November 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.




Cite this article
[APA Style]
Shengbin Wu and Yibai Wang (2021). A Federated Multi-Task Learning Model Based onAdaptive Distributed Data Latent Correlation Analysis. Journal of Information Processing Systems, 17(3), 441-452. DOI: 10.3745/JIPS.01.0075.

[IEEE Style]
S. Wu and Y. Wang, "A Federated Multi-Task Learning Model Based onAdaptive Distributed Data Latent Correlation Analysis," Journal of Information Processing Systems, vol. 17, no. 3, pp. 441-452, 2021. DOI: 10.3745/JIPS.01.0075.

[ACM Style]
Shengbin Wu and Yibai Wang. 2021. A Federated Multi-Task Learning Model Based onAdaptive Distributed Data Latent Correlation Analysis. Journal of Information Processing Systems, 17, 3, (2021), 441-452. DOI: 10.3745/JIPS.01.0075.