VFL-RPS: Relevant Participant Selection in Vertical Federated Learning

• URL: http://arxiv.org/abs/2502.14375v1
• Date: Thu, 20 Feb 2025 09:05:55 GMT
• Title: VFL-RPS: Relevant Participant Selection in Vertical Federated Learning
• Authors: Afsana Khan, Marijn ten Thij, Guangzhi Tang, Anna Wilbik,
• Abstract summary: Federated Learning (FL) allows collaboration between different parties, while ensuring that the data across these parties is not shared. We propose a novel method VFL-RPS for participant selection in VFL, as a pre-training step. We show that our method outperforms existing methods for participant selection in VFL.
• Score: 0.06181089784338582
• License:
• Abstract: Federated Learning (FL) allows collaboration between different parties, while ensuring that the data across these parties is not shared. However, not every collaboration is helpful in terms of the resulting model performance. Therefore, it is an important challenge to select the correct participants in a collaboration. As it currently stands, most of the efforts in participant selection in the literature have focused on Horizontal Federated Learning (HFL), which assumes that all features are the same across all participants, disregarding the possibility of different features across participants which is captured in Vertical Federated Learning (VFL). To close this gap in the literature, we propose a novel method VFL-RPS for participant selection in VFL, as a pre-training step. We have tested our method on several data sets performing both regression and classification tasks, showing that our method leads to comparable results as using all data by only selecting a few participants. In addition, we show that our method outperforms existing methods for participant selection in VFL.

Related papers

• Towards Active Participant Centric Vertical Federated Learning: Some Representations May Be All You Need [0.4711628883579317]
  This work introduces a novel approach to VFL, Active Participant Centric VFL ( APC-VFL) APC-VFL excels in scenarios when data samples among participants are partially aligned at training. It consistently outperforms other VFL methods across three popular VFL datasets in terms of F1, accuracy and communication costs.
  arXiv  Detail & Related papers  (2024-10-23T08:07:00Z)
• Vertical Federated Learning for Effectiveness, Security, Applicability: A Survey [67.48187503803847]
  Vertical Federated Learning (VFL) is a privacy-preserving distributed learning paradigm. Recent research has shown promising results addressing various challenges in VFL. This survey offers a systematic overview of recent developments.
  arXiv  Detail & Related papers  (2024-05-25T16:05:06Z)
• Vertical Federated Learning Hybrid Local Pre-training [4.31644387824845]
  We propose a novel VFL Hybrid Local Pre-training (VFLHLP) approach for Vertical Federated Learning (VFL) 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.
  arXiv  Detail & Related papers  (2024-05-20T08:57:39Z)
• DPP-based Client Selection for Federated Learning with Non-IID Data [97.1195165400568]
  This paper proposes a client selection (CS) method to tackle the communication bottleneck of federated learning (FL) We first analyze the effect of CS in FL and show that FL training can be accelerated by adequately choosing participants to diversify the training dataset in each round of training. We leverage data profiling and determinantal point process (DPP) sampling techniques to develop an algorithm termed Federated Learning with DPP-based Participant Selection (FL-DP$3$S)
  arXiv  Detail & Related papers  (2023-03-30T13:14:54Z)
• Vertical Semi-Federated Learning for Efficient Online Advertising [50.18284051956359]
  Semi-VFL (Vertical Semi-Federated Learning) is proposed to achieve a practical industry application fashion for VFL. We build an inference-efficient single-party student model applicable to the whole sample space. New representation distillation methods are designed to extract cross-party feature correlations for both the overlapped and non-overlapped data.
  arXiv  Detail & Related papers  (2022-09-30T17:59:27Z)
• A Survey on Participant Selection for Federated Learning in Mobile Networks [47.88372677863646]
  Federated Learning (FL) is an efficient distributed machine learning paradigm that employs private datasets in a privacy-preserving manner. Due to limited communication bandwidth and unstable availability of such devices in a mobile network, only a fraction of end devices can be selected in each round.
  arXiv  Detail & Related papers  (2022-07-08T04:22:48Z)
• Factorized-FL: Agnostic Personalized Federated Learning with Kernel Factorization & Similarity Matching [70.95184015412798]
  In real-world federated learning scenarios, participants could have their own personalized labels which are incompatible with those from other clients. We introduce Factorized-FL, which allows to effectively tackle label- and task-heterogeneous federated learning settings. We extensively validate our method on both label- and domain-heterogeneous settings, on which it outperforms the state-of-the-art personalized federated learning methods.
  arXiv  Detail & Related papers  (2022-02-01T08:00:59Z)
• FedNLP: A Research Platform for Federated Learning in Natural Language Processing [55.01246123092445]
  We present the FedNLP, a research platform for federated learning in NLP. FedNLP supports various popular task formulations in NLP such as text classification, sequence tagging, question answering, seq2seq generation, and language modeling. Preliminary experiments with FedNLP reveal that there exists a large performance gap between learning on decentralized and centralized datasets.
  arXiv  Detail & Related papers  (2021-04-18T11:04:49Z)
• Multi-Participant Multi-Class Vertical Federated Learning [16.75182305714081]
  We propose the Multi-participant Multi-class Vertical Federated Learning (MMVFL) framework for multi-class VFL problems involving multiple parties. MMVFL enables label sharing from its owner to other VFL participants in a privacypreserving manner. Experiment results on real-world datasets show that MMVFL can effectively share label information among multiple VFL participants and match multi-class classification performance of existing approaches.
  arXiv  Detail & Related papers  (2020-01-30T02:39:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.