GOVERN: Gradient Orientation Vote Ensemble for Multi-Teacher Reinforced Distillation
원문 초록
Pre-trained language models have become an integral component of question-answering systems, achieving remarkable performance. However, for practical deployment, it is crucial to perform knowledge distillation to maintain high performance while operating under computational constraints. In this paper, we address a key question: given the importance of unsupervised distillation for student model performance, how can knowledge from multiple teacher models be effectively ensemble during this stage without the guidance of labels? We propose a novel algorithm, GOVERN, to tackle this issue. GOVERN has demonstrated significant improvements in both offline and online experiments, enabling the student model to achieve results comparable to that of teacher ensembles. Our experiments show that GOVERN remarkably requires a mere 1\% of the ensemble method's inference budget to achieve 99.5\% of performance. The proposed algorithm has been successfully deployed in a real-world commercial question-answering system, demonstrating its real-world applicability.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
SeqPE: Transformer with Sequential Position Encoding
A Simple Linear Patch Revives Layer-Pruned Large Language Models
Disentangled Self-Supervision in Sequential Recommenders
From Roots to Rewards: Dynamic Tree Reasoning with RL
DVFL-Net: A Lightweight Distilled Video Focal Modulation Network for Spatio-Temporal Action Recognition
Describe Anything Model for Visual Question Answering on Text-rich Images
토론
이 논문과 연결된 포럼 글이 아직 없습니다.