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

arXiv cs.CL / 4/13/2026

📰 NewsSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper introduces a cross-domain aspect sentiment triplet extraction approach that targets the limitations of training on single datasets and the inability to capture shared representations across domains.
It proposes a prototype-regularized federated learning framework (PCD-SpanProto) that lets distributed clients exchange class-level span prototypes rather than full model parameters to respect privacy constraints.
The method includes a weighted, performance-aware aggregation strategy and a contrastive regularization module to improve global prototypes under domain heterogeneity.
Experiments on four ASTE datasets show that the approach outperforms existing baselines while lowering communication costs, indicating effective cross-domain knowledge transfer with federated constraints.

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.