paper-with-me

Papers

MLKD-BERT: Multi-level Knowledge Distillation for Pre-trained Language Models

2024-07-03 · Ying Zhang, Ziheng Yang, Shufan Ji

Knowledge distillation is an effective technique for pre-trained language model compression. Although existing knowledge distillation methods perform well for the most typical model BERT, they could be further improved in two aspects: the relation-level knowledge could be further explored to improve model performance; and the setting of student attention head number could be more flexible to decrease inference time. Therefore, we are motivated to propose a novel knowledge distillation method MLKD-BERT to distill multi-level knowledge in teacher-student framework. Extensive experiments on GLUE benchmark and extractive question answering tasks demonstrate that our method outperforms state-of-the-art knowledge distillation methods on BERT. In addition, MLKD-BERT can flexibly set student attention head number, allowing for substantial inference time decrease with little performance drop.

📄 PDF Abstract BibTeX arXiv:2407.02775

Code (0)

등록된 구현이 없습니다.

Tasks

Extractive Question-AnsweringKnowledge DistillationLanguage ModelingLanguage ModellingModel CompressionQuestion Answering

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Weight Decay 설명 없음
Residual Connection 설명 없음
Multi-Head Attention 설명 없음
WordPiece 설명 없음

Similar Papers 제목 키워드 기반

Multi-level Knowledge Distillation via Knowledge Alignment and Correlation

2020-12-01 · Fei Ding, Yin Yang, Hongxin Hu, Venkat Krovi 외

Knowledge distillation (KD) has become an important technique for model compression and knowledge transfer. In this work, we first perform a comprehensive analysis of the knowledge transferred by different KD methods. We…

Contrastive LearningKnowledge DistillationModel CompressionTransfer Learning

Mutual-Learning Knowledge Distillation for Nighttime UAV Tracking

2023-12-13 · Yufeng Liu

Nighttime unmanned aerial vehicle (UAV) tracking has been facilitated with indispensable plug-and-play low-light enhancers. However, the introduction of low-light enhancers increases the extra computational burden for th…

Knowledge Distillation

Multi-Level Knowledge Distillation and Dynamic Self-Supervised Learning for Continual Learning

2025-08-18 · Taeheon Kim, San Kim, Minhyuk Seo, Dongjae Jeon 외 arxiv

Class-incremental with repetition (CIR), where previously trained classes repeatedly introduced in future tasks, is a more realistic scenario than the traditional class incremental setup, which assumes that each task con…

Self-Supervised LearningKnowledge DistillationContinual Learning

Large Language Model Teaches Visual Students: Cross-Modality Transfer of Fine-Grained Conceptual Knowledge

2026-06-25 · Thomas Shih-Chao Liang, Zhuoran Yu, Yong Jae Lee arxiv

Large Language Models (LLMs) possess broad conceptual knowledge acquired through large-scale text pretraining, yet their potential to supervise models in other modalities remains underexplored. In this work, we propose L…

Knowledge Distillation

SKDBERT: Compressing BERT via Stochastic Knowledge Distillation

2022-11-26 · Zixiang Ding, Guoqing Jiang, Shuai Zhang, Lin Guo 외

In this paper, we propose Stochastic Knowledge Distillation (SKD) to obtain compact BERT-style language model dubbed SKDBERT. In each iteration, SKD samples a teacher model from a pre-defined teacher ensemble, which cons…

Knowledge DistillationLanguage ModelingLanguage Modelling