paper-with-me

홈 › Papers

Dynamic Knowledge Distillation for Black-box Hypothesis Transfer Learning

2020-07-24 · Yiqin Yu, Xu Min, Shiwan Zhao, Jing Mei, Fei Wang, Dongsheng Li, Kenney Ng, Shaochun Li

In real world applications like healthcare, it is usually difficult to build a machine learning prediction model that works universally well across different institutions. At the same time, the available model is often proprietary, i.e., neither the model parameter nor the data set used for model training is accessible. In consequence, leveraging the knowledge hidden in the available model (aka. the hypothesis) and adapting it to a local data set becomes extremely challenging. Motivated by this situation, in this paper we aim to address such a specific case within the hypothesis transfer learning framework, in which 1) the source hypothesis is a black-box model and 2) the source domain data is unavailable. In particular, we introduce a novel algorithm called dynamic knowledge distillation for hypothesis transfer learning (dkdHTL). In this method, we use knowledge distillation with instance-wise weighting mechanism to adaptively transfer the "dark" knowledge from the source hypothesis to the target domain.The weighting coefficients of the distillation loss and the standard loss are determined by the consistency between the predicted probability of the source hypothesis and the target ground-truth label.Empirical results on both transfer learning benchmark datasets and a healthcare dataset demonstrate the effectiveness of our method.

📄 PDF Abstract BibTeX arXiv:2007.12355

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationTransfer Learning

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation

2022-06-13 · Zihui Xue, Zhengqi Gao, Sucheng Ren, Hang Zhao

Crossmodal knowledge distillation (KD) extends traditional knowledge distillation to the area of multimodal learning and demonstrates great success in various applications. To achieve knowledge transfer across modalities…

Knowledge DistillationTransfer Learning

Self-Evolution Knowledge Distillation for LLM-based Machine Translation

2024-12-19 · Yuncheng Song, Liang Ding, Changtong Zan, ShuJian Huang

Knowledge distillation (KD) has shown great promise in transferring knowledge from larger teacher models to smaller student models. However, existing KD strategies for large language models often minimize output distribu…

Knowledge DistillationMachine TranslationTransfer LearningTranslation

A Functional Perspective on Knowledge Distillation in Neural Networks

2025-10-14 · Israel Mason-Williams, Gabryel Mason-Williams, Helen Yannakoudakis arxiv

Knowledge distillation is considered a compression mechanism when judged on the resulting student's accuracy and loss, yet its functional impact is poorly understood. We quantify the compression capacity of knowledge dis…

Knowledge Distillation

Knowledge Distillation of Black-Box Large Language Models

2024-01-13 · Hongzhan Chen, Ruijun Chen, Yuqi Yi, Xiaojun Quan 외

Given the exceptional performance of proprietary large language models (LLMs) like GPT-4, recent research has increasingly focused on boosting the capabilities of smaller models through knowledge distillation (KD) from t…

Knowledge DistillationTransfer Learning

Model Mimic Attack: Knowledge Distillation for Provably Transferable Adversarial Examples

2024-10-21 · Kirill Lukyanov, Andrew Perminov, Denis Turdakov, Mikhail Pautov

The vulnerability of artificial neural networks to adversarial perturbations in the black-box setting is widely studied in the literature. The majority of attack methods to construct these perturbations suffer from an im…

Knowledge Distillation