Litcius/Paper detail

PanDa: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation

Qihuang Zhong, Liang Ding, Juhua Liu, Bo Du, Dacheng Tao

2024IEEE Transactions on Knowledge and Data Engineering17 citationsDOI

Abstract

Prompt Transfer (PoT) is a recently-proposed approach to improve prompt-tuning, by initializing the target prompt with the existing prompt trained on similar source tasks. However, such a vanilla PoT approach usually achieves sub-optimal performance, as (i) the PoT is sensitive to the similarity of source-target pair and (ii) directly fine-tuning the prompt initialized with source prompt on target task might lead to forgetting of the useful general knowledge learned from source task. To tackle these issues, we propose a new metric to accurately predict the prompt transferability (regarding (i)), and a novel PoT approach (namely <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PanDa</small> ) that leverages the knowledge distillation technique to alleviate the knowledge forgetting effectively (regarding (ii)). Extensive and systematic experiments on 189 combinations of 21 source and 9 target datasets across 5 scales of PLMs demonstrate that: 1) <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">our proposed metric works well to predict the prompt transferability</i> ; 2) <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">our</i> <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PanDa</small> <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">consistently outperforms the vanilla PoT approach by 2.3% average score (up to 24.1%) among all tasks and model sizes</i> ; 3) <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">with our</i> <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PanDa</small> <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">approach, prompt-tuning can achieve competitive and even better performance than model-tuning in various PLM scales scenarios</i> .

Topics & Concepts

Computer scienceAdaptation (eye)DistillationKnowledge transferArtificial intelligenceKnowledge managementPhysicsOpticsChemistryOrganic chemistryTopic ModelingSpeech Recognition and SynthesisDomain Adaptation and Few-Shot Learning