Prototype-Regularized Federated Learning for Cross-Domain Aspect Sentiment Triplet Extraction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914463314083840 |
|---|---|
| author | Cai, Zongming Tang, Jianhang Zhang, Zhenyong Qin, Jinghui Jin, Kebing Zhuo, Hankz Hankui |
| author_facet | Cai, Zongming Tang, Jianhang Zhang, Zhenyong Qin, Jinghui Jin, Kebing Zhuo, Hankz Hankui |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_09123 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Prototype-Regularized Federated Learning for Cross-Domain Aspect Sentiment Triplet Extraction Cai, Zongming Tang, Jianhang Zhang, Zhenyong Qin, Jinghui Jin, Kebing Zhuo, Hankz Hankui Computation and Language 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. |
| title | Prototype-Regularized Federated Learning for Cross-Domain Aspect Sentiment Triplet Extraction |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.09123 |