mlsanityData to 7 Oct 2026

Multi-Tier Federated Learning for Vertically Partitioned Data

arXiv 2102.03620 ↗First posted 6 Feb 2021cs.LG cs.DCcited by 7

Not on the map. Why?

Abstract (arXiv)

We consider decentralized model training in tiered communication networks. Our network model consists of a set of silos, each holding a vertical partition of the data. Each silo contains a hub and a set of clients, with the silo's vertical data shard partitioned horizontally across its clients. We propose Tiered Decentralized Coordinate Descent (TDCD), a communication-efficient decentralized training algorithm for such two-tiered networks. To reduce communication overhead, the clients in each silo perform multiple local gradient steps before sharing updates with their hub. Each hub adjusts its coordinates by averaging its workers' updates, and then hubs exchange intermediate updates with one another. We present a theoretical analysis of our algorithm and show the dependence of the convergence rate on the number of vertical partitions, the number of local updates, and the number of clients in each hub. We further validate our approach empirically via simulation-based experiments using a variety of datasets and both convex and non-convex objectives.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 14 of its 18 references that are in the map. First posted on arXiv 6 Feb 2021.

Builds on

14 of 18 references.

References · 14

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2018Local SGD Converges Fast and Communicates Littlecited by 595
  5. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  6. 2019Client-Edge-Cloud Hierarchical Federated Learningcited by 202
  7. 2017Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryptioncited by 174
  8. 2018Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithmscited by 106
  9. 2019Hierarchical Federated Learning Across Heterogeneous Cellular Networkscited by 98
  10. 2020VAFL: a Method of Vertical Asynchronous Federated Learningcited by 87
  11. 2019Parallel Distributed Logistic Regression for Vertical Federated Learning without Third-Party Coordinatorcited by 51
  12. 2020Multi-Participant Multi-Class Vertical Federated Learningcited by 47
2 more
  1. 2019A Communication Efficient Collaborative Learning Framework for Distributed Featurescited by 21
  2. 2020Multi-Level Local SGD for Heterogeneous Hierarchical Networkscited by 9

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 2; 2023: 1; 2024: 2.

7 papers.

  1. 2022Compressed-VFL: Communication-Efficient Learning with Vertically Partitioned Datacited by 36
  2. 2023A Survey on Vertical Federated Learning: From a Layered Perspectivecited by 30
  3. 2022ADI: Adversarial Dominating Inputs in Vertical Federated Learning Systemscited by 8
  4. 2021Cross-Silo Federated Learning for Multi-Tier Networks with Vertical and Horizontal Data Partitioningcited by 6
  5. 2024Communication-Efficient Hybrid Federated Learning for E-health with Horizontal and Vertical Data Partitioningcited by 6
  6. 2021A Vertical Federated Learning Framework for Horizontally Partitioned Labelscited by 4
  7. 2024Federated and Transfer Learning for Cancer Detection Based on Image Analysiscited by 3