Learning From Human Educational Wisdom: A Student-Centered Knowledge Distillation Method

计算机科学 遗忘 人工智能 机器学习 课程 集合(抽象数据类型) 过程(计算) 心理学 教育学 哲学 语言学 程序设计语言 操作系统
作者
Shunzhi Yang,Jinfeng Yang,MengChu Zhou,Zhenhua Huang,Wei‐Shi Zheng,Xiong Yang,Jin Ren
出处
期刊:IEEE Transactions on Pattern Analysis and Machine Intelligence [IEEE Computer Society]
卷期号:46 (6): 4188-4205 被引量:12
标识
DOI:10.1109/tpami.2024.3354928
摘要

Existing studies on knowledge distillation typically focus on teacher-centered methods, in which the teacher network is trained according to its own standards before transferring the learned knowledge to a student one. However, due to differences in network structure between the teacher and the student, the knowledge learned by the former may not be desired by the latter. Inspired by human educational wisdom, this paper proposes a Student-Centered Distillation (SCD) method that enables the teacher network to adjust its knowledge transfer according to the student network's needs. We implemented SCD based on various human educational wisdom, e.g., the teacher network identified and learned the knowledge desired by the student network on the validation set, and then transferred it to the latter through the training set. To address the problems of current deficiency knowledge, hard sample learning and knowledge forgetting faced by a student network in the learning process, we introduce and improve Proportional-Integral-Derivative (PID) algorithms from automation fields to make them effective in identifying the current knowledge required by the student network. Furthermore, we propose a curriculum learning-based fuzzy strategy and apply it to the proposed PID control algorithm, such that the student network in SCD can actively pay attention to the learning of challenging samples after with certain knowledge. The overall performance of SCD is verified in multiple tasks by comparing it with state-of-the-art ones. Experimental results show that our student-centered distillation method outperforms existing teacher-centered ones.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
蚌埠住不了完成签到,获得积分10
3秒前
3秒前
东东完成签到,获得积分10
4秒前
壮观的白羊完成签到 ,获得积分10
5秒前
hhhhhh发布了新的文献求助10
6秒前
完美世界应助Phoenix Hu采纳,获得10
7秒前
七七七完成签到,获得积分10
9秒前
10秒前
11秒前
11秒前
lz1023完成签到,获得积分10
13秒前
lz1023发布了新的文献求助30
15秒前
Wenhao发布了新的文献求助10
18秒前
量子星尘发布了新的文献求助30
18秒前
18秒前
周少发布了新的文献求助10
18秒前
Jasper应助ruaruaburua采纳,获得10
20秒前
Lily完成签到,获得积分10
20秒前
高兴新梅发布了新的文献求助10
23秒前
Ava应助椰子冻采纳,获得10
24秒前
25秒前
burn发布了新的文献求助10
26秒前
贾克斯完成签到,获得积分20
27秒前
28秒前
玛卡巴卡发布了新的文献求助10
29秒前
GAO发布了新的文献求助10
30秒前
强健的雅绿完成签到,获得积分10
30秒前
酷波er应助贾克斯采纳,获得10
31秒前
聪明煎饼完成签到,获得积分10
31秒前
小马甲应助小白白采纳,获得10
32秒前
科目三应助松鼠桂鱼采纳,获得10
33秒前
科研通AI5应助碧蓝的青荷采纳,获得10
33秒前
alisa完成签到,获得积分10
34秒前
nobody发布了新的文献求助10
34秒前
34秒前
Lily发布了新的文献求助10
35秒前
华仔应助huan采纳,获得30
37秒前
37秒前
晚风完成签到,获得积分10
37秒前
alisa发布了新的文献求助10
38秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3976177
求助须知:如何正确求助?哪些是违规求助? 3520366
关于积分的说明 11202745
捐赠科研通 3256847
什么是DOI,文献DOI怎么找? 1798509
邀请新用户注册赠送积分活动 877704
科研通“疑难数据库(出版商)”最低求助积分说明 806516