Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Semi-Supervised Graph Classification: A Hierar...
Search
izuna385
May 28, 2019
Technology
0
230
Semi-Supervised Graph Classification: A Hierarchical Graph Perspective(WWW19)
This slide is for supplement of reading paper, so it doesn't hold presentation-slide style, sorry.
izuna385
May 28, 2019
Tweet
Share
More Decks by izuna385
See All by izuna385
jel: japanese entity linker
izuna385
0
380
Firebase-React-App
izuna385
0
250
React+FastAPIを用いた簡単なWebアプリ作製
izuna385
0
1.7k
UseCase of Entity Linking
izuna385
0
580
Unofficial slides: From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains (ACL 2020)
izuna385
1
670
Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
izuna385
0
870
Zero-shot Entity Linking with Dense Entity Retrieval (Unofficial slides) and Entity Linking future directions
izuna385
3
1.1k
Entity representation with relational attention
izuna385
0
84
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
570
Other Decks in Technology
See All in Technology
250905 大吉祥寺.pm 2025 前夜祭 「プログラミングに出会って20年、『今』が1番楽しい」
msykd
PRO
1
280
異業種出身エンジニアが気づいた、転向して十数年経っても変わらない自分の武器とは
macnekoayu
0
280
Oracle Cloud Infrastructure:2025年8月度サービス・アップデート
oracle4engineer
PRO
0
190
衝突して強くなる! BLUE GIANTと アジャイルチームの共通点とは ― いきいきと活気に満ちたグルーヴあるチームを作るコツ ― / BLUE GIANT and Agile Teams
naitosatoshi
0
300
AIエージェントの活用に重要な「MCP (Model Context Protocol)」とは何か
masayamoriofficial
0
280
Kiroと学ぶコンテキストエンジニアリング
oikon48
6
8.2k
BPaaSにおける人と協働する前提のAIエージェント-AWS登壇資料
kentarofujii
0
110
5年目から始める Vue3 サイト改善 #frontendo
tacck
PRO
3
160
「魔法少女まどか☆マギカ Magia Exedra」のグローバル展開を支える、開発チームと翻訳チームの「意識しない協創」を実現するローカライズシステム
gree_tech
PRO
0
500
2025年になってもまだMySQLが好き
yoku0825
8
3.8k
実践AIガバナンス
asei
3
330
実運用で考える PGO
kworkdev
PRO
0
130
Featured
See All Featured
ReactJS: Keep Simple. Everything can be a component!
pedronauck
667
120k
Keith and Marios Guide to Fast Websites
keithpitt
411
22k
Speed Design
sergeychernyshev
32
1.1k
Intergalactic Javascript Robots from Outer Space
tanoku
272
27k
VelocityConf: Rendering Performance Case Studies
addyosmani
332
24k
Build The Right Thing And Hit Your Dates
maggiecrowley
37
2.8k
Building Flexible Design Systems
yeseniaperezcruz
328
39k
Embracing the Ebb and Flow
colly
87
4.8k
Designing for Performance
lara
610
69k
How to Ace a Technical Interview
jacobian
279
23k
Thoughts on Productivity
jonyablonski
69
4.8k
Rebuilding a faster, lazier Slack
samanthasiow
83
9.1k
Transcript
1 (Supplement slides for reading paper) Semi-Supervised Graph Classification: A
Hierarchical Graph Perspective(WWW19) izunan385
Li, Jia, et al. "Semi-Supervised Graph Classification: A Hierarchical Graph
Perspective." (2019).
• Task Collect Class Prediction for unlabeled
• input each graph instance: g labeled graph set and
unlabeled graph set graph instance adjacency matrix
• output IC(graph Instance Classifier) receives graph info and outputs
instance representation matrix predicted class probability vector HC(Hierarchical Graph Classifier) receives all graph instance( ) representation from IC graph-graph adjacency matrix and outputs predicted class prob matrix for all
• Task Collect Class Prediction for unlabeled • Loss function
labeled graph instances unlabeled graph instances
• Supervised Loss (for labeled graphs ) • Disagreement Loss(for
unlabeled graphs ) Disagreement means IC and HC prediction mismatch.
None
GCN W0: learnable parameter
GCN with self loop W0: learnable parameter
GCN(summarized) 0 https://www.experoinc.com/post/node-classification-by-graph-con network Adjacent/co-occurrence matrix has structure information. Propagation
rule is learned during training.
https://docs.dgl.ai/tutorials/models/1_gnn/9_gat.html
Cautious Iteration
Cautious Iteration Here, sampling top confident prediction for each step
Active Iteration Disagreement means IC and HC prediction mismatch. Ask
annotator for annotating class of graphs which HC and IC have top-disagreement with.