Related papers: Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data

Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data

URL: http://arxiv.org/abs/2507.22488v1
Date: Wed, 30 Jul 2025 08:48:33 GMT
Title: Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data
Authors: Wei Guo, Yiyang Duan, Zhaojun Hu, Yiqi Tong, Fuzhen Zhuang, Xiao Zhang, Jin Dong, Ruofan Wu, Tengfei Liu, Yifan Sun,
Abstract summary: In vertical federated learning (VFL), unaligned samples across different parties in VFL can be extremely class-imbalanced.<n>We propose Proto-EVFL, an enhanced VFL framework via dual prototypes.<n>We prove that Proto-EVFL, as the first bi-level optimization framework in VFL, has a convergence rate of 1/sqrt T.
Score: 28.626677790020082
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: In vertical federated learning (VFL), multiple enterprises address aligned sample scarcity by leveraging massive locally unaligned samples to facilitate collaborative learning. However, unaligned samples across different parties in VFL can be extremely class-imbalanced, leading to insufficient feature representation and limited model prediction space. Specifically, class-imbalanced problems consist of intra-party class imbalance and inter-party class imbalance, which can further cause local model bias and feature contribution inconsistency issues, respectively. To address the above challenges, we propose Proto-EVFL, an enhanced VFL framework via dual prototypes. We first introduce class prototypes for each party to learn relationships between classes in the latent space, allowing the active party to predict unseen classes. We further design a probabilistic dual prototype learning scheme to dynamically select unaligned samples by conditional optimal transport cost with class prior probability. Moreover, a mixed prior guided module guides this selection process by combining local and global class prior probabilities. Finally, we adopt an \textit{adaptive gated feature aggregation strategy} to mitigate feature contribution inconsistency by dynamically weighting and aggregating local features across different parties. We proved that Proto-EVFL, as the first bi-level optimization framework in VFL, has a convergence rate of 1/\sqrt T. Extensive experiments on various datasets validate the superiority of our Proto-EVFL. Even in a zero-shot scenario with one unseen class, it outperforms baselines by at least 6.97%

Related papers

Heterogeneous Federated Learning with Prototype Alignment and Upscaling [0.7373617024876724]
Prototype Normalization (ProtoNorm) is a novel PBFL framework that addresses suboptimal prototype separation.<n>We show that our approach better separates prototypes and thus consistently outperforms existing HtFL approaches.
arXiv Detail & Related papers (2025-07-06T09:34:41Z)
Probabilistic Prototype Calibration of Vision-Language Models for Generalized Few-shot Semantic Segmentation [75.18058114915327]
Generalized Few-Shot Semanticnative (GFSS) aims to extend a segmentation model to novel classes with only a few annotated examples.<n>We propose FewCLIP, a probabilistic prototype calibration framework over multi-modal prototypes from the pretrained CLIP.<n>We show FewCLIP significantly outperforms state-of-the-art approaches across both GFSS and class-incremental setting.
arXiv Detail & Related papers (2025-06-28T18:36:22Z)
FedORGP: Guiding Heterogeneous Federated Learning with Orthogonality Regularization on Global Prototypes [31.93057335216804]
Federated Learning (FL) has emerged as an essential framework for distributed machine learning.<n>Current approaches face limitations in achieving separation between classes.<n>This paper introduces FedtFLORG, which encourages intra-class prototype similarity and expands the inter-class angular separation.
arXiv Detail & Related papers (2025-02-22T07:02:51Z)
Over-the-Air Fair Federated Learning via Multi-Objective Optimization [52.295563400314094]
We propose an over-the-air fair federated learning algorithm (OTA-FFL) to train fair FL models.<n>Experiments demonstrate the superiority of OTA-FFL in achieving fairness and robust performance.
arXiv Detail & Related papers (2025-01-06T21:16:51Z)
Training-Free Unsupervised Prompt for Vision-Language Models [27.13778811871694]
We propose Training-Free Unsupervised Prompts (TFUP) to preserve inherent representation capabilities and enhance them with a residual connection to similarity-based prediction probabilities. TFUP achieves surprising performance, even surpassing the training-base method on multiple classification datasets. Our TFUP-T achieves new state-of-the-art classification performance compared to unsupervised and few-shot adaptation approaches on multiple benchmarks.
arXiv Detail & Related papers (2024-04-25T05:07:50Z)
PromptSync: Bridging Domain Gaps in Vision-Language Models through Class-Aware Prototype Alignment and Discrimination [14.50214193838818]
A zero-shot generalization in vision-language (V-L) models such as CLIP has spurred their widespread adoption. Previous methods have employed test-time prompt tuning to adapt the model to unseen domains, but they overlooked the issue of imbalanced class distributions. In this study, we employ class-aware prototype alignment weighted by mean class probabilities obtained for a test sample and filtered augmented views.
arXiv Detail & Related papers (2024-04-11T07:26:00Z)
Probabilistic Contrastive Learning for Long-Tailed Visual Recognition [78.70453964041718]
Longtailed distributions frequently emerge in real-world data, where a large number of minority categories contain a limited number of samples. Recent investigations have revealed that supervised contrastive learning exhibits promising potential in alleviating the data imbalance. We propose a novel probabilistic contrastive (ProCo) learning algorithm that estimates the data distribution of the samples from each class in the feature space.
arXiv Detail & Related papers (2024-03-11T13:44:49Z)
Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning [49.72857433721424]
Vision Transformers (ViT) and Visual Prompt Tuning (VPT) achieve state-of-the-art performance with improved efficiency in various computer vision tasks. We present a novel algorithm, SGPT, that integrates Generalized FL (GFL) and Personalized FL (PFL) approaches by employing a unique combination of both shared and group-specific prompts.
arXiv Detail & Related papers (2023-10-27T17:22:09Z)
FedABC: Targeting Fair Competition in Personalized Federated Learning [76.9646903596757]
Federated learning aims to collaboratively train models without accessing their client's local private data. We propose a novel and generic PFL framework termed Federated Averaging via Binary Classification, dubbed FedABC. In particular, we adopt the one-vs-all'' training strategy in each client to alleviate the unfair competition between classes.
arXiv Detail & Related papers (2023-02-15T03:42:59Z)
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)
FedCVT: Semi-supervised Vertical Federated Learning with Cross-view Training [9.638604434238882]
Federated Cross-view Training (FedCVT) is a semi-supervised learning approach that improves the performance of a vertical federated learning model. FedCVT does not require parties to share their original data and model parameters, thus preserving data privacy.
arXiv Detail & Related papers (2020-08-25T06:20:31Z)

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