Prototype-Regularized Federated Learning for Cross-Domain Aspect Sentiment Triplet Extraction

2026-04-10

AI Summary

This work addresses the limited generalization capability in cross-domain aspect-level sentiment triplet extraction (ASTE) caused by data silos and privacy constraints. To tackle this challenge, the authors propose PCD-SpanProto, a prototype-regularized federated learning framework that enables privacy-preserving cross-domain knowledge transfer by exchanging category-level prototypes among clients instead of full model parameters. The framework further incorporates a weighted performance-aware aggregation strategy and a contrastive regularization module to enhance global prototype quality, thereby improving intra-class compactness and inter-class separability. Experimental results on four ASTE datasets demonstrate that the proposed method significantly outperforms existing baselines while reducing communication overhead, validating the effectiveness and efficiency of cross-domain prototype-based knowledge transfer.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Natural Language Processing: Safety and Robustness
• Application Domains: Humanities & Computational Social Science

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Aspect Sentiment Triplet Extraction (ASTE) aims to extract all sentiment triplets of aspect terms, opinion terms, and sentiment polarities from a sentence. Existing methods are typically trained on individual datasets in isolation, failing to jointly capture the common feature representations shared across domains. Moreover, data privacy constraints prevent centralized data aggregation. To address these challenges, we propose Prototype-based Cross-Domain Span Prototype extraction (PCD-SpanProto), a prototype-regularized federated learning framework to enable distributed clients to exchange class-level prototypes instead of full model parameters. Specifically, we design a weighted performance-aware aggregation strategy and a contrastive regularization module to improve the global prototype under domain heterogeneity and the promotion between intra-class compactness and inter-class separability across clients. Extensive experiments on four ASTE datasets demonstrate that our method outperforms baselines and reduces communication costs, validating the effectiveness of prototype-based cross-domain knowledge transfer.

Problem

• Aspect Sentiment Triplet Extraction
• Cross-Domain
• Federated Learning
• Data Privacy
• Feature Representation

Innovation

• Federated Learning
• Prototype Regularization
• Cross-Domain ASTE
• Contrastive Regularization
• Communication Efficiency