# Decoupled Vertical Federated Learning for Practical Training on Vertically Partitioned Data

arXiv: https://arxiv.org/abs/2403.03871 · HTML: https://mlsanity.com/paper/2403.03871/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 41 references that are in the map.
- First posted on arXiv 6 Mar 2024.

## Builds on (most cited first, 27 of 27)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Distributed learning of deep neural network over multiple agents](https://mlsanity.com/paper/1810.06060/) (2018)
- [Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption](https://mlsanity.com/paper/1711.10677/) (2017)
- [Decoupled Neural Interfaces using Synthetic Gradients](https://mlsanity.com/paper/1608.05343/) (2016)
- [Greedy Layerwise Learning Can Scale to ImageNet](https://mlsanity.com/paper/1812.11446/) (2018)
- [Feature Inference Attack on Model Predictions in Vertical Federated Learning](https://mlsanity.com/paper/2010.10152/) (2020)
- [VAFL: a Method of Vertical Asynchronous Federated Learning](https://mlsanity.com/paper/2007.06081/) (2020)
- [Decoupled Greedy Learning of CNNs](https://mlsanity.com/paper/1901.08164/) (2019)
- [On the Computational Efficiency of Training Neural Networks](https://mlsanity.com/paper/1410.1141/) (2014)
- [Revisiting Locally Supervised Learning: an Alternative to End-to-end Training](https://mlsanity.com/paper/2101.10832/) (2021)
- [Hebbian Deep Learning Without Feedback](https://mlsanity.com/paper/2209.11883/) (2022)
- [UnSplit: Data-Oblivious Model Inversion, Model Stealing, and Label Inference Attacks Against Split Learning](https://mlsanity.com/paper/2108.09033/) (2021)
- [Multi-Participant Multi-Class Vertical Federated Learning](https://mlsanity.com/paper/2001.11154/) (2020)
- [SplitNN-driven Vertical Partitioning](https://mlsanity.com/paper/2008.04137/) (2020)
- [PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNN](https://mlsanity.com/paper/2104.00489/) (2021)
- [Approximate Byzantine Fault-Tolerance in Distributed Optimization](https://mlsanity.com/paper/2101.09337/) (2021)
- [Entity Resolution and Federated Learning get a Federated Resolution](https://mlsanity.com/paper/1803.04035/) (2018)
- [Vertical Federated Learning without Revealing Intersection Membership](https://mlsanity.com/paper/2106.05508/) (2021)
- [Practical Vertical Federated Learning with Unsupervised Representation Learning](https://mlsanity.com/paper/2208.10278/) (2022)
- [FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models](https://mlsanity.com/paper/2304.13407/) (2023)
- [Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples](https://mlsanity.com/paper/2303.16270/) (2023)
- [A Survey on Fault-tolerance in Distributed Optimization and Machine Learning](https://mlsanity.com/paper/2106.08545/) (2021)
- [An Algorithm for Training Polynomial Networks](https://mlsanity.com/paper/1304.7045/) (2013)

## Built on by (most cited first, 1 of 1)

- [Entity Augmentation for Efficient Classification of Vertically Partitioned Data with Limited Overlap](https://mlsanity.com/paper/2406.17899/) (2024)

## Abstract (arXiv)

Vertical Federated Learning (VFL) is an emergent distributed machine learning paradigm for collaborative learning between clients who have disjoint features of common entities. However, standard VFL lacks fault tolerance, with each participant and connection being a single point of failure. Prior attempts to induce fault tolerance in VFL focus on the scenario of "straggling clients", usually entailing that all messages eventually arrive or that there is an upper bound on the number of late messages. To handle the more general problem of arbitrary crashes, we propose Decoupled VFL (DVFL). To handle training with faults, DVFL decouples training between communication rounds using local unsupervised objectives. By further decoupling label supervision from aggregation, DVFL also enables redundant aggregators. As secondary benefits, DVFL can enhance data efficiency and provides immunity against gradient-based attacks. In this work, we implement DVFL for split neural networks with a self-supervised autoencoder loss. When there are faults, DVFL outperforms the best VFL-based alternative (97.58% vs 96.95% on an MNIST task). Even under perfect conditions, performance is comparable.