Unified Alignment Protocol: Making Sense of the Unlabeled Data in New Domains

2025-05-27

AI Summary

To address insufficient generalization in semi-supervised federated learning (SSFL) caused by unlabeled client data and domain shift during testing, this paper proposes the Unified Alignment Protocol (UAP). UAP introduces a novel server-client co-designed unsupervised domain adaptation framework, featuring an alternating two-stage mechanism: (i) server-side parametric modeling of feature distributions, and (ii) client-side unsupervised alignment—both executed without additional communication overhead. The method jointly integrates feature distribution modeling, cross-domain alignment, and multi-architecture-compatible training to support heterogeneous clients. Evaluated on multiple standard domain generalization benchmarks, UAP significantly improves accuracy and robustness on unseen target domains, achieving state-of-the-art performance in semi-supervised federated learning.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Multiagent Systems: Adversarial Agents
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Semi-Supervised Federated Learning (SSFL) is gaining popularity over conventional Federated Learning in many real-world applications. Due to the practical limitation of limited labeled data on the client side, SSFL considers that participating clients train with unlabeled data, and only the central server has the necessary resources to access limited labeled data, making it an ideal fit for real-world applications (e.g., healthcare). However, traditional SSFL assumes that the data distributions in the training phase and testing phase are the same. In practice, however, domain shifts frequently occur, making it essential for SSFL to incorporate generalization capabilities and enhance their practicality. The core challenge is improving model generalization to new, unseen domains while the client participate in SSFL. However, the decentralized setup of SSFL and unsupervised client training necessitates innovation to achieve improved generalization across domains. To achieve this, we propose a novel framework called the Unified Alignment Protocol (UAP), which consists of an alternating two-stage training process. The first stage involves training the server model to learn and align the features with a parametric distribution, which is subsequently communicated to clients without additional communication overhead. The second stage proposes a novel training algorithm that utilizes the server feature distribution to align client features accordingly. Our extensive experiments on standard domain generalization benchmark datasets across multiple model architectures reveal that proposed UAP successfully achieves SOTA generalization performance in SSFL setting.

Problem

• Improving model generalization to new domains in SSFL
• Addressing domain shifts in semi-supervised federated learning
• Aligning client and server features without extra communication

Innovation

• Alternating two-stage training process
• Parametric distribution feature alignment
• Server-guided client feature alignment