paper-with-me

홈 › Papers

Harmonizing knowledge Transfer in Neural Network with Unified Distillation

2024-09-27 · Yaomin Huang, Zaomin Yan, Chaomin Shen, Faming Fang, Guixu Zhang

Knowledge distillation (KD), known for its ability to transfer knowledge from a cumbersome network (teacher) to a lightweight one (student) without altering the architecture, has been garnering increasing attention. Two primary categories emerge within KD methods: feature-based, focusing on intermediate layers' features, and logits-based, targeting the final layer's logits. This paper introduces a novel perspective by leveraging diverse knowledge sources within a unified KD framework. Specifically, we aggregate features from intermediate layers into a comprehensive representation, effectively gathering semantic information from different stages and scales. Subsequently, we predict the distribution parameters from this representation. These steps transform knowledge from the intermediate layers into corresponding distributive forms, thereby allowing for knowledge distillation through a unified distribution constraint at different stages of the network, ensuring the comprehensiveness and coherence of knowledge transfer. Numerous experiments were conducted to validate the effectiveness of the proposed method.

📄 PDF Abstract BibTeX arXiv:2409.18565

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

Towards a Unified View of Affinity-Based Knowledge Distillation

2022-09-30 · Vladimir Li, Atsuto Maki

Knowledge transfer between artificial neural networks has become an important topic in deep learning. Among the open questions are what kind of knowledge needs to be preserved for the transfer, and how it can be effectiv…

image-classificationImage ClassificationKnowledge DistillationRelation+1

Collaborative Teacher-Student Learning via Multiple Knowledge Transfer

2021-01-21 · Liyuan Sun, Jianping Gou, Baosheng Yu, Lan Du 외

Knowledge distillation (KD), as an efficient and effective model compression technique, has been receiving considerable attention in deep learning. The key to its success is to transfer knowledge from a large teacher net…

Knowledge DistillationModel CompressionSelf-LearningTransfer Learning

Semi-Online Knowledge Distillation

2021-11-23 · Zhiqiang Liu, Yanxia Liu, Chengkai Huang

Knowledge distillation is an effective and stable method for model compression via knowledge transfer. Conventional knowledge distillation (KD) is to transfer knowledge from a large and well pre-trained teacher network t…

Knowledge DistillationModel CompressionTransfer Learning

Domain Adaptable Fine-Tune Distillation Framework For Advancing Farm Surveillance

2024-02-10 · Raza Imam, Muhammad Huzaifa, Nabil Mansour, Shaher Bano Mirza 외

In this study, we propose an automated framework for camel farm monitoring, introducing two key contributions: the Unified Auto-Annotation framework and the Fine-Tune Distillation framework. The Unified Auto-Annotation a…

Computational EfficiencyKnowledge Distillationobject-detectionObject Detection+1

Harmonizing Multi-Objective LLM Unlearning via Unified Domain Representation and Bidirectional Logit Distillation

2026-04-16 · Yisheng Zhong, Sijia Liu, Zhuangdi Zhu arxiv

Large Language Models (LLMs) unlearning is crucial for removing hazardous or privacy-leaking information from the model. Practical LLM unlearning demands satisfying multiple challenging objectives simultaneously: removin…