Salvato in:
Dettagli Bibliografici
Autori principali: Li, Wenguo, Guo, Xinling, Jiao, Xu, Huang, Tiancheng, Yan, Xiaoran, Yang, Yao
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2405.11884
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910453609791488
author Li, Wenguo
Guo, Xinling
Jiao, Xu
Huang, Tiancheng
Yan, Xiaoran
Yang, Yao
author_facet Li, Wenguo
Guo, Xinling
Jiao, Xu
Huang, Tiancheng
Yan, Xiaoran
Yang, Yao
contents Vertical Federated Learning (VFL), which has a broad range of real-world applications, has received much attention in both academia and industry. Enterprises aspire to exploit more valuable features of the same users from diverse departments to boost their model prediction skills. VFL addresses this demand and concurrently secures individual parties from exposing their raw data. However, conventional VFL encounters a bottleneck as it only leverages aligned samples, whose size shrinks with more parties involved, resulting in data scarcity and the waste of unaligned data. To address this problem, we propose a novel VFL Hybrid Local Pre-training (VFLHLP) approach. VFLHLP first pre-trains local networks on the local data of participating parties. Then it utilizes these pre-trained networks to adjust the sub-model for the labeled party or enhance representation learning for other parties during downstream federated learning on aligned data, boosting the performance of federated models. The experimental results on real-world advertising datasets, demonstrate that our approach achieves the best performance over baseline methods by large margins. The ablation study further illustrates the contribution of each technique in VFLHLP to its overall performance.
format Preprint
id arxiv_https___arxiv_org_abs_2405_11884
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Vertical Federated Learning Hybrid Local Pre-training
Li, Wenguo
Guo, Xinling
Jiao, Xu
Huang, Tiancheng
Yan, Xiaoran
Yang, Yao
Machine Learning
Distributed, Parallel, and Cluster Computing
Vertical Federated Learning (VFL), which has a broad range of real-world applications, has received much attention in both academia and industry. Enterprises aspire to exploit more valuable features of the same users from diverse departments to boost their model prediction skills. VFL addresses this demand and concurrently secures individual parties from exposing their raw data. However, conventional VFL encounters a bottleneck as it only leverages aligned samples, whose size shrinks with more parties involved, resulting in data scarcity and the waste of unaligned data. To address this problem, we propose a novel VFL Hybrid Local Pre-training (VFLHLP) approach. VFLHLP first pre-trains local networks on the local data of participating parties. Then it utilizes these pre-trained networks to adjust the sub-model for the labeled party or enhance representation learning for other parties during downstream federated learning on aligned data, boosting the performance of federated models. The experimental results on real-world advertising datasets, demonstrate that our approach achieves the best performance over baseline methods by large margins. The ablation study further illustrates the contribution of each technique in VFLHLP to its overall performance.
title Vertical Federated Learning Hybrid Local Pre-training
topic Machine Learning
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2405.11884