paper-with-me

홈 › Papers

Knowledge Distillation Under Ideal Joint Classifier Assumption

2023-04-19 · Huayu Li, Xiwen Chen, Gregory Ditzler, Janet Roveda, Ao Li

Knowledge distillation constitutes a potent methodology for condensing substantial neural networks into more compact and efficient counterparts. Within this context, softmax regression representation learning serves as a widely embraced approach, leveraging a pre-established teacher network to guide the learning process of a diminutive student network. Notably, despite the extensive inquiry into the efficacy of softmax regression representation learning, the intricate underpinnings governing the knowledge transfer mechanism remain inadequately elucidated. This study introduces the 'Ideal Joint Classifier Knowledge Distillation' (IJCKD) framework, an overarching paradigm that not only furnishes a lucid and exhaustive comprehension of prevailing knowledge distillation techniques but also establishes a theoretical underpinning for prospective investigations. Employing mathematical methodologies derived from domain adaptation theory, this investigation conducts a comprehensive examination of the error boundary of the student network contingent upon the teacher network. Consequently, our framework facilitates efficient knowledge transference between teacher and student networks, thereby accommodating a diverse spectrum of applications.

📄 PDF Abstract BibTeX arXiv:2304.11004

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationKnowledge DistillationregressionRepresentation LearningTransfer Learning

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
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

Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why

2026-05-11 · Mohammadreza Armandpour, Fatih Ilhan, David Harrison, Ajay Jaiswal 외 arxiv

On-policy distillation offers dense, per-token supervision for training reasoning models; however, it remains unclear under which conditions this signal is beneficial and under which it is detrimental. Which teacher mode…

IDEAL: Query-Efficient Data-Free Learning from Black-box Models

2022-05-23 · Jie Zhang, Chen Chen, Lingjuan Lyu

Knowledge Distillation (KD) is a typical method for training a lightweight student model with the help of a well-trained teacher model. However, most KD methods require access to either the teacher's training data or mod…

Knowledge Distillation

UNIDEAL: Curriculum Knowledge Distillation Federated Learning

2023-09-16 · Yuwen Yang, Chang Liu, Xun Cai, Suizhi Huang 외

Federated Learning (FL) has emerged as a promising approach to enable collaborative learning among multiple clients while preserving data privacy. However, cross-domain FL tasks, where clients possess data from different…

Federated LearningKnowledge Distillation

Towards Understanding Knowledge Distillation

2021-05-27 · Mary Phuong, Christoph H. Lampert

Knowledge distillation, i.e., one classifier being trained on the outputs of another classifier, is an empirically very successful technique for knowledge transfer between classifiers. It has even been observed that clas…

Knowledge DistillationTransfer Learning

Knowledge Distillation with Adversarial Samples Supporting Decision Boundary

2018-05-15 · Byeongho Heo, Minsik Lee, Sangdoo Yun, Jin Young Choi

Many recent works on knowledge distillation have provided ways to transfer the knowledge of a trained network for improving the learning process of a new one, but finding a good technique for knowledge distillation is st…

Adversarial AttackKnowledge Distillation