Federated Multi-Task Learning on Non-IID Data Silos: An Experimental Study
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911841612988416 |
|---|---|
| author | Yang, Yuwen Lu, Yuxiang Huang, Suizhi Sirejiding, Shalayiding Lu, Hongtao Ding, Yue |
| author_facet | Yang, Yuwen Lu, Yuxiang Huang, Suizhi Sirejiding, Shalayiding Lu, Hongtao Ding, Yue |
| contents | The innovative Federated Multi-Task Learning (FMTL) approach consolidates the benefits of Federated Learning (FL) and Multi-Task Learning (MTL), enabling collaborative model training on multi-task learning datasets. However, a comprehensive evaluation method, integrating the unique features of both FL and MTL, is currently absent in the field. This paper fills this void by introducing a novel framework, FMTL-Bench, for systematic evaluation of the FMTL paradigm. This benchmark covers various aspects at the data, model, and optimization algorithm levels, and comprises seven sets of comparative experiments, encapsulating a wide array of non-independent and identically distributed (Non-IID) data partitioning scenarios. We propose a systematic process for comparing baselines of diverse indicators and conduct a case study on communication expenditure, time, and energy consumption. Through our exhaustive experiments, we aim to provide valuable insights into the strengths and limitations of existing baseline methods, contributing to the ongoing discourse on optimal FMTL application in practical scenarios. The source code can be found on https://github.com/youngfish42/FMTL-Benchmark . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_12876 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Federated Multi-Task Learning on Non-IID Data Silos: An Experimental Study Yang, Yuwen Lu, Yuxiang Huang, Suizhi Sirejiding, Shalayiding Lu, Hongtao Ding, Yue Machine Learning Cryptography and Security Distributed, Parallel, and Cluster Computing The innovative Federated Multi-Task Learning (FMTL) approach consolidates the benefits of Federated Learning (FL) and Multi-Task Learning (MTL), enabling collaborative model training on multi-task learning datasets. However, a comprehensive evaluation method, integrating the unique features of both FL and MTL, is currently absent in the field. This paper fills this void by introducing a novel framework, FMTL-Bench, for systematic evaluation of the FMTL paradigm. This benchmark covers various aspects at the data, model, and optimization algorithm levels, and comprises seven sets of comparative experiments, encapsulating a wide array of non-independent and identically distributed (Non-IID) data partitioning scenarios. We propose a systematic process for comparing baselines of diverse indicators and conduct a case study on communication expenditure, time, and energy consumption. Through our exhaustive experiments, we aim to provide valuable insights into the strengths and limitations of existing baseline methods, contributing to the ongoing discourse on optimal FMTL application in practical scenarios. The source code can be found on https://github.com/youngfish42/FMTL-Benchmark . |
| title | Federated Multi-Task Learning on Non-IID Data Silos: An Experimental Study |
| topic | Machine Learning Cryptography and Security Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2402.12876 |