当前位置:网站首页>论文笔记: 多标签学习 DM2L
论文笔记: 多标签学习 DM2L
2022-06-24 06:56:00 【闵帆】
摘要: 分享对论文的理解. 原文见 Ma, Z.-C., & Chen, S.-C. (2021). Expand globally, shrink locally: Discrimi-nant multi-label learning with missing labels. Pattern Recognition, 111, 107675.
1. 论文贡献
- 从全局和局部两个方面同时优化;
- 用核函数支撑非线性变换;
- 理论分析到位.
2. 基本符号
| 符号 | 含义 | 说明 |
|---|---|---|
| X ∈ R n × d \mathbf{X} \in \mathbb{R}^{n \times d} X∈Rn×d | 属性矩阵 | |
| X k ∈ R n k × d \mathbf{X}_k \in \mathbb{R}^{n_k \times d} Xk∈Rnk×d | 具有第 k k k 个标签的属性子矩阵 | |
| Y ∈ { − 1 , + 1 } n × c \mathbf{Y} \in \{-1, +1\}^{n \times c} Y∈{ −1,+1}n×c | 标签矩阵 | |
| Y ~ ∈ { − 1 , + 1 } n × l \tilde{\mathbf{Y}} \in \{-1, +1\}^{n \times l} Y~∈{ −1,+1}n×l | 观测到的标签矩阵 | |
| Ω = { 1 , … , n } × { 1 , … , c } \mathbf{\Omega} = \{1, \dots, n\} \times \{1, \dots, c\} Ω={ 1,…,n}×{ 1,…,c} | 观测标签位置集合 | |
| W ∈ R m × l \mathbf{W} \in \mathbb{R}^{m \times l} W∈Rm×l | 系数矩阵 | 仍然是线性模型 |
| w i ∈ R m \mathbf{w}_i \in \mathbb{R}^m wi∈Rm | 某一标签的系数向量 | |
| C ∈ R l × l \mathbf{C} \in \mathbb{R}^{l \times l} C∈Rl×l | 标签相关性矩阵 | 成对相关性, 不满足对称性 |
3. 算法
基本优化目标:
min 1 2 ∥ R Ω ( X W ) − Y ~ ∥ F 2 + λ d ∥ X W ∥ ∗ (1) \min \frac{1}{2} \|R_{\Omega}(\mathbf{XW}) - \tilde{\mathbf{Y}}\|_F^2 + \lambda_d \|\mathbf{XW}\|_*\tag{1} min21∥RΩ(XW)−Y~∥F2+λd∥XW∥∗(1)
其中,
- 损失函数部分不考虑缺失值, 这个属于常规操作.
- 核正则 (nuclear norm) 部分考虑了预测的矩阵, 而不仅仅是 X W \mathbf{XW} XW, 有点奇怪.
考虑标签结构后的优化目标:
min 1 2 ∥ R Ω ( X W ) − Y ~ ∥ F 2 + λ d ( ∑ k = 1 c ∥ X k W ∥ ∗ − ∥ X W ∥ ∗ ) , (2) \min \frac{1}{2} \|R_{\Omega}(\mathbf{XW}) - \tilde{\mathbf{Y}}\|_F^2 + \lambda_d \left(\sum_{k = 1}^c \|\mathbf{X}_k\mathbf{W}\|_* - \|\mathbf{XW}\|_*\right), \tag{2} min21∥RΩ(XW)−Y~∥F2+λd(k=1∑c∥XkW∥∗−∥XW∥∗),(2)
其中,
- ∥ X k W ∥ ∗ \|\mathbf{X}_k\mathbf{W}\|_* ∥XkW∥∗ 表达了局部标签结构, 轶越小越好;
- ∥ X W ∥ ∗ \|\mathbf{XW}\|_* ∥XW∥∗ 表达了全局标签结构, 轶越大越好 (可分性更强, 信息量越高).
- 这两点就是题目的来源.
增加非线性的优化目标:
min 1 2 ∥ R Ω ( X W ) − Y ~ ∥ F 2 + λ d ( ∑ k = 1 c ∥ f ( X k ) W ∥ ∗ − ∥ f ( X ) W ∥ ∗ ) , (5) \min \frac{1}{2} \|R_{\Omega}(\mathbf{XW}) - \tilde{\mathbf{Y}}\|_F^2 + \lambda_d \left(\sum_{k = 1}^c \|f(\mathbf{X}_k)\mathbf{W}\|_* - \|f(\mathbf{X})\mathbf{W}\|_*\right), \tag{5} min21∥RΩ(XW)−Y~∥F2+λd(k=1∑c∥f(Xk)W∥∗−∥f(X)W∥∗),(5)
其中 f ( ⋅ ) f(\cdot) f(⋅) 为核函数导致的非线性变换.
4. 小结
- 又是一堆理论证明.
边栏推荐
- Simple refraction effect
- 1279_VMWare Player安装VMWare Tools时VSock安装失败解决
- 5g industrial router Gigabit high speed low delay
- Introduction of model compression tool based on distiller
- 51 single chip microcomputer_ External interrupt and timer / Counter interrupt
- Keep one decimal place and two decimal places
- Vulnhub target: boredhackerblog_ CLOUD AV
- Online education fades
- SVN实测常用操作-记录操作大全
- Model effect optimization, try a variety of cross validation methods (system operation)
猜你喜欢

Latest news of awtk: new usage of grid control

Coordinate transformation of graphic technology

Backup and restore SQL Server Databases locally

Introduction to software engineering - Chapter 2 - feasibility study

首次曝光 唯一全域最高等级背后的阿里云云原生安全全景图

OC Extension 检测手机是否安装某个App(源码)

Practice of opengauss database on CentOS, configuration

Gossip: what happened to 3aC?

Configure your own free Internet domain name with ngrok

从 jsonpath 和 xpath 到 SPL
随机推荐
JVM underlying principle analysis
快速读论文----AD-GCL:Adversarial Graph Augmentation to Improve Graph Contrastive Learning
More appropriate development mode under epidemic situation
Unity culling related technologies
工控机防破解
All you know is the test pyramid?
首次曝光 唯一全域最高等级背后的阿里云云原生安全全景图
解决笔记本键盘禁用失败问题
有关iframe锚点,锚点出现上下偏移,锚点出现页面显示问题.iframe的srcdoc问题
Examples of corpus data processing cases (reading multiple text files, reading multiple files specified under a folder, decoding errors, reading multiple subfolder text, batch renaming of multiple fil
C语言_字符串与指针的爱恨情仇
4-操作列表(循环结构)
VsCode主题推荐
These dependencies were not found: * core JS / modules / es6 array. Fill in XXX
Standing at the center of the storm: how to change the engine of Tencent
3-列表简介
Simple refraction effect
Mousse shares listed on Shenzhen Stock Exchange: gross profit margin continued to decline, and marketing failed in the first quarter of 2022
2022 PMP project management examination agile knowledge points (1)
Oracle advanced SQL qualified query