当前位置:网站首页>论文笔记: 极限多标签学习 GalaXC (暂存, 还没学完)
论文笔记: 极限多标签学习 GalaXC (暂存, 还没学完)
2022-07-06 02:00:00 【闵帆】
摘要: 分享对论文的理解. 原文见 D. Saini, A. K. Jain, K. Dave, J. Jiao, A. Singh, R. Zhang and M. Varma, GalaXC: Graph neural networks with labelwise attention for extreme classification, in WWW 2021. 7 位作者中 6 位是微软研究院的人, 跟他们杠, 我觉得自己简直脑袋秀逗了.
1. 论文贡献
- 处理标签存在于文档内的情况: labels and documents cohabit the same space.
- 利用标签文本与标签相关性: label text and label correlations, label metadata.
- 标签级注意力机制: label-wise attention mechanism.
- 热启动 (部分标签已知) 时效果好: warm-start scenarios where predictions need to be made on data points with partially revealed label sets,
- 能处理几百万个标签.
- 又快又好.
2. 动机
- 已有工作表明,与使用与应用程序无关的特征(例如传统的词袋特征)相比,学习密集的特定于应用程序的文档表示可以带来更好的预测。These works have demonstrated that learning dense application-specific document representations can lead to better predictions than using application-agnostic features such as the traditional bag-of-words features.
- 5-10 个标记的短文本. 如使用标题进行相关网页或广告的预测. Short textual descriptions with typically only 5-10 tokens. Examples include applications such as predicting related webpages or related products using only the title of a given webpage/product and predicting relevant ads/keywords/searches for
user queries. - 使用多种元数据如标签文本、标签相关性、标签层次结构, 更好地服务于尾部标签. XC applications often make available label metadata in various forms such as label text, label correlations or label hierarchies.
- 标签特征. Contemporary XC algorithms have explored utilizing label features.
- 热启动与辅助数据源. Warm-start and auxiliary sources of data.
- 已有工作多数使用文档图而不是文档-标签图 (见 Table 1). existing works mostly use document-document graphs and not joint document-label graphs at extreme scales.
2. 基本符号
符号 | 含义 | 备注 |
---|---|---|
G \mathbb{G} G | 二部图 | G = ( D ∪ L , E ) \mathbb{G} = (\mathbb{D} \cup \mathbb{L}, \mathbb{E}) G=(D∪L,E) |
D \mathbb{D} D | 文本节点集合 | 元素记作 d d d, 基数为 N N N |
L \mathbb{L} L | 标签节点集合 | 元素记作 l l l, 基数为 L L L |
y i \mathbf{y}_i yi | 第 i i i 个文本的真实标签向量 | 取值范围为 { − 1 , + 1 } L \{-1, +1\}^L { −1,+1}L |
x ^ i 0 \hat{\mathbf{x}}_i^0 x^i0 | 第 i i i 个文档的特征向量 | D D D 维 |
z ^ l 0 \hat{\mathbf{z}}_l^0 z^l0 | 第 l l l 个标签的特征向量 | D D D 维 |
v ^ n 0 \hat{\mathbf{v}}_n^0 v^n0 | x ^ i 0 \hat{\mathbf{x}}_i^0 x^i0 与 z ^ l 0 \hat{\mathbf{z}}_l^0 z^l0 的统一表示 | D D D 维 |
N \mathcal{N} N | 求邻居操作 | V → 2 V \mathbb{V} \to 2^\mathbb{V} V→2V |
C \mathcal{C} C | 卷积操作 | |
T \mathcal{T} T | 转型操作 | transformation |
a ^ n k \hat{\mathbf{a}}_n^k a^nk | C k ( { v ^ m k − 1 , a ^ m k − 1 : m ∈ N ( n ) } ) \mathcal{C}_k(\{\hat{\mathbf{v}}_m^{k-1}, \hat{\mathbf{a}}_m^{k-1}: m \in \mathcal{N}(n)\}) Ck({ v^mk−1,a^mk−1:m∈N(n)}) | GNN 操作 |
v ^ n k \hat{\mathbf{v}}_n^k v^nk | T k ( { v ^ n k − 1 , a ^ n k − 1 } ) \mathcal{T}_k(\{\hat{\mathbf{v}}_n^{k-1}, \hat{\mathbf{a}}_n^{k-1}\}) Tk({ v^nk−1,a^nk−1}) | GNN 操作 |
W \mathbf{W} W | 系数矩阵 | D × L D \times L D×L 维 |
K K K | hop 数 | |
e l k e_{lk} elk | 标签 l l l 在第 k k k 个 hop 的标量 |
3. 方案
Graph convolution block 的具体操作是
a ^ n k = C k ( a ^ n k − 1 ) = ( 1 + ϵ k ) ⋅ a ^ n k − 1 + ∑ m ∈ N ( n ) a ^ m k − 1 \hat{\mathbf{a}}_n^k = \mathcal{C}_k(\hat{\mathbf{a}}_n^{k-1}) = (1 + \epsilon_k) \cdot \hat{\mathbf{a}}_n^{k-1} + \sum_{m \in \mathcal{N}(n)}\hat{\mathbf{a}}_m^{k-1} a^nk=Ck(a^nk−1)=(1+ϵk)⋅a^nk−1+m∈N(n)∑a^mk−1
Embedding 的具体操作是
v ^ n k = T k ( a ^ n k ) \hat{\mathbf{v}}_n^k = \mathcal{T}_k(\hat{\mathbf{a}}_n^k) v^nk=Tk(a^nk)
令
α l k = exp ( e l k ) / ∑ k ′ ∈ [ K ] exp e l k ′ \alpha_{lk} = \exp(e_{lk}) / \sum_{k' \in [K]} \exp e_{lk'} αlk=exp(elk)/k′∈[K]∑expelk′
它表示第 k k k 个 hop 时的占比.
标签嵌入计算式为
x ^ ( l ) = ∑ k ∈ [ k ] α l k ⋅ x ^ k \hat{\mathbf{x}}^{(l)} = \sum_{k \in [k]} \alpha_{lk} \cdot \hat{\mathbf{x}}^{k} x^(l)=k∈[k]∑αlk⋅x^k
注意: 这里的 k k k 次方还未理解.
标签得分为
s l = * w l , x ^ ( l ) * s_l = \langle \mathbf{w}_l, \hat{\mathbf{x}}^{(l)} \rangle sl=*wl,x^(l)*
4. 小结
在读懂程序之前, 根本无法理解这篇论文.
边栏推荐
- 通过PHP 获取身份证相关信息 获取生肖,获取星座,获取年龄,获取性别
- 安装Redis
- Campus second-hand transaction based on wechat applet
- Redis-Key的操作
- 【Flask】官方教程(Tutorial)-part3:blog蓝图、项目可安装化
- 【Flask】官方教程(Tutorial)-part2:蓝图-视图、模板、静态文件
- Redis-字符串类型
- Exness: Mercedes Benz's profits exceed expectations, and it is predicted that there will be a supply chain shortage in 2022
- Redis守护进程无法停止解决方案
- Card 4G industrial router charging pile intelligent cabinet private network video monitoring 4G to Ethernet to WiFi wired network speed test software and hardware customization
猜你喜欢
干货!通过软硬件协同设计加速稀疏神经网络
Know MySQL database
Leetcode3, implémenter strstr ()
[solution] every time idea starts, it will build project
【Flask】官方教程(Tutorial)-part2:蓝图-视图、模板、静态文件
Publish your own toolkit notes using NPM
Folio. Ink is a free, fast and easy-to-use image sharing tool
Online reservation system of sports venues based on PHP
The ECU of 21 Audi q5l 45tfsi brushes is upgraded to master special adjustment, and the horsepower is safely and stably increased to 305 horsepower
How to improve the level of pinduoduo store? Dianyingtong came to tell you
随机推荐
Get the relevant information of ID card through PHP, get the zodiac, get the constellation, get the age, and get the gender
Win10 add file extension
FTP server, ssh server (super brief)
Basic operations of databases and tables ----- default constraints
Cadre du Paddle: aperçu du paddlelnp [bibliothèque de développement pour le traitement du langage naturel des rames volantes]
selenium 等待方式
You are using pip version 21.1.1; however, version 22.0.3 is available. You should consider upgradin
Blue Bridge Cup embedded_ STM32 learning_ Key_ Explain in detail
Visualstudio2019 compilation configuration lastools-v2.0.0 under win10 system
MySQL lethal serial question 1 -- are you familiar with MySQL transactions?
Apicloud openframe realizes the transfer and return of parameters to the previous page - basic improvement
Using SA token to solve websocket handshake authentication
How to improve the level of pinduoduo store? Dianyingtong came to tell you
TrueType字体文件提取关键信息
Bidding promotion process
Flowable source code comments (36) process instance migration status job processor, BPMN history cleanup job processor, external worker task completion job processor
[flask] official tutorial -part1: project layout, application settings, definition and database access
使用npm发布自己开发的工具包笔记
National intangible cultural heritage inheritor HD Wang's shadow digital collection of "Four Beauties" made an amazing debut!
Luo Gu P1170 Bugs Bunny and Hunter