LEAF: A Robust Expert-Based Framework for Few-Shot Continual Event Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918150499467264 |
|---|---|
| author | Dao, Bao-Ngoc Nguyen, Quang Dinh, Luyen Ngo Le, Minh Van, Linh Ngo |
| author_facet | Dao, Bao-Ngoc Nguyen, Quang Dinh, Luyen Ngo Le, Minh Van, Linh Ngo |
| contents | Few-shot Continual Event Detection (FCED) poses the dual challenges of learning from limited data and mitigating catastrophic forgetting across sequential tasks. Existing approaches often suffer from severe forgetting due to the full fine-tuning of a shared base model, which leads to knowledge interference between tasks. Moreover, they frequently rely on data augmentation strategies that can introduce unnatural or semantically distorted inputs. To address these limitations, we propose LEAF, a novel and robust expert-based framework for FCED. LEAF integrates a specialized mixture of experts architecture into the base model, where each expert is parameterized with low-rank adaptation (LoRA) matrices. A semantic-aware expert selection mechanism dynamically routes instances to the most relevant experts, enabling expert specialization and reducing knowledge interference. To improve generalization in limited-data settings, LEAF incorporates a contrastive learning objective guided by label descriptions, which capture high-level semantic information about event types. Furthermore, to prevent overfitting on the memory buffer, our framework employs a knowledge distillation strategy that transfers knowledge from previous models to the current one. Extensive experiments on multiple FCED benchmarks demonstrate that LEAF consistently achieves state-of-the-art performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_24547 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LEAF: A Robust Expert-Based Framework for Few-Shot Continual Event Detection Dao, Bao-Ngoc Nguyen, Quang Dinh, Luyen Ngo Le, Minh Van, Linh Ngo Machine Learning Computation and Language Few-shot Continual Event Detection (FCED) poses the dual challenges of learning from limited data and mitigating catastrophic forgetting across sequential tasks. Existing approaches often suffer from severe forgetting due to the full fine-tuning of a shared base model, which leads to knowledge interference between tasks. Moreover, they frequently rely on data augmentation strategies that can introduce unnatural or semantically distorted inputs. To address these limitations, we propose LEAF, a novel and robust expert-based framework for FCED. LEAF integrates a specialized mixture of experts architecture into the base model, where each expert is parameterized with low-rank adaptation (LoRA) matrices. A semantic-aware expert selection mechanism dynamically routes instances to the most relevant experts, enabling expert specialization and reducing knowledge interference. To improve generalization in limited-data settings, LEAF incorporates a contrastive learning objective guided by label descriptions, which capture high-level semantic information about event types. Furthermore, to prevent overfitting on the memory buffer, our framework employs a knowledge distillation strategy that transfers knowledge from previous models to the current one. Extensive experiments on multiple FCED benchmarks demonstrate that LEAF consistently achieves state-of-the-art performance. |
| title | LEAF: A Robust Expert-Based Framework for Few-Shot Continual Event Detection |
| topic | Machine Learning Computation and Language |
| url | https://arxiv.org/abs/2509.24547 |