# PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture

arXiv: https://arxiv.org/abs/2510.12494 · HTML: https://mlsanity.com/paper/2510.12494/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 55 references that are in the map.
- First posted on arXiv 14 Oct 2025.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Towards Federated Learning at Scale: System Design](https://mlsanity.com/paper/1902.01046/) (2019)
- [Information Leakage in Embedding Models](https://mlsanity.com/paper/2004.00053/) (2020)
- [SecureBoost: A Lossless Federated Learning Framework](https://mlsanity.com/paper/1901.08755/) (2019)
- [FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings](https://mlsanity.com/paper/2210.04620/) (2022)
- [Vertical Federated Learning: Concepts, Advances and Challenges](https://mlsanity.com/paper/2211.12814/) (2022)
- [VAFL: a Method of Vertical Asynchronous Federated Learning](https://mlsanity.com/paper/2007.06081/) (2020)
- [Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning](https://mlsanity.com/paper/2206.08307/) (2022)
- [CAFE: Catastrophic Data Leakage in Vertical Federated Learning](https://mlsanity.com/paper/2110.15122/) (2021)
- [Split Learning for collaborative deep learning in healthcare](https://mlsanity.com/paper/1912.12115/) (2019)
- [Natural Language Understanding with Privacy-Preserving BERT](https://mlsanity.com/paper/2104.07504/) (2021)
- [QUOTIENT: Two-Party Secure Neural Network Training and Prediction](https://mlsanity.com/paper/1907.03372/) (2019)
- [Secure Bilevel Asynchronous Vertical Federated Learning with Backward Updating](https://mlsanity.com/paper/2103.00958/) (2021)
- [Federated Doubly Stochastic Kernel Learning for Vertically Partitioned Data](https://mlsanity.com/paper/2008.06197/) (2020)
- [On Privacy and Personalization in Cross-Silo Federated Learning](https://mlsanity.com/paper/2206.07902/) (2022)
- [Compressed-VFL: Communication-Efficient Learning with Vertically Partitioned Data](https://mlsanity.com/paper/2206.08330/) (2022)
- [AutoFed: Heterogeneity-Aware Federated Multimodal Learning for Robust Autonomous Driving](https://mlsanity.com/paper/2302.08646/) (2023)
- [TimelyFL: Heterogeneity-aware Asynchronous Federated Learning with Adaptive Partial Training](https://mlsanity.com/paper/2304.06947/) (2023)
- [FairVFL: A Fair Vertical Federated Learning Framework with Contrastive Adversarial Learning](https://mlsanity.com/paper/2206.03200/) (2022)
- [Convergence Analysis of Sequential Federated Learning on Heterogeneous Data](https://mlsanity.com/paper/2311.03154/) (2023)
- [Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning](https://mlsanity.com/paper/2201.12023/) (2022)
- [Flexible Vertical Federated Learning with Heterogeneous Parties](https://mlsanity.com/paper/2208.12672/) (2022)
- [Vertical Federated Knowledge Transfer via Representation Distillation for Healthcare Collaboration Networks](https://mlsanity.com/paper/2302.05675/) (2023)
- [AsySQN: Faster Vertical Federated Learning Algorithms with Better Computation Resource Utilization](https://mlsanity.com/paper/2109.12519/) (2021)
- [Nimbus: Secure and Efficient Two-Party Inference for Transformers](https://mlsanity.com/paper/2411.15707/) (2024)
- [Asteroid: Resource-Efficient Hybrid Pipeline Parallelism for Collaborative DNN Training on Heterogeneous Edge Devices](https://mlsanity.com/paper/2408.08015/) (2024)
- [VertiMRF: Differentially Private Vertical Federated Data Synthesis](https://mlsanity.com/paper/2406.19008/) (2024)

## Abstract (arXiv)

With the rapid advancement of the digital economy, data collaboration between organizations has become a well-established business model, driving the growth of various industries. However, privacy concerns make direct data sharing impractical. To address this, Two-Party Split Learning (a.k.a. Vertical Federated Learning (VFL)) has emerged as a promising solution for secure collaborative learning. Despite its advantages, this architecture still suffers from low computational resource utilization and training efficiency. Specifically, its synchronous dependency design increases training latency, while resource and data heterogeneity among participants further hinder efficient computation. To overcome these challenges, we propose PubSub-VFL, a novel VFL paradigm with a Publisher/Subscriber architecture optimized for two-party collaborative learning with high computational efficiency. PubSub-VFL leverages the decoupling capabilities of the Pub/Sub architecture and the data parallelism of the parameter server architecture to design a hierarchical asynchronous mechanism, reducing training latency and improving system efficiency. Additionally, to mitigate the training imbalance caused by resource and data heterogeneity, we formalize an optimization problem based on participants' system profiles, enabling the selection of optimal hyperparameters while preserving privacy. We conduct a theoretical analysis to demonstrate that PubSub-VFL achieves stable convergence and is compatible with security protocols such as differential privacy. Extensive case studies on five benchmark datasets further validate its effectiveness, showing that, compared to state-of-the-art baselines, PubSub-VFL not only accelerates training by 2 ~ 7× without compromising accuracy, but also achieves a computational resource utilization rate of up to 91.07%.