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
370
Firebase-React-App
izuna385
0
240
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
570
Unofficial slides: From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains (ACL 2020)
izuna385
1
660
Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
izuna385
0
860
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
83
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
560
Other Decks in Technology
See All in Technology
Claude Code Actionを使ったコード品質改善の取り組み
potix2
PRO
2
1.2k
新卒3年目の後悔〜機械学習モデルジョブの運用を頑張った話〜
kameitomohiro
0
370
Uniadex__公開版_20250617-AIxIoTビジネス共創ラボ_ツナガルチカラ_.pdf
iotcomjpadmin
0
140
CSS、JSをHTMLテンプレートにまとめるフロントエンド戦略
d120145
0
200
Snowflake Summit 2025 データエンジニアリング関連新機能紹介 / Snowflake Summit 2025 What's New about Data Engineering
tiltmax3
0
220
本部長の代わりに提案書レビュー! KDDI営業が毎日使うAIエージェント「A-BOSS」開発秘話
minorun365
PRO
14
2.3k
Microsoft Build 2025 技術/製品動向 for Microsoft Startup Tech Community
torumakabe
1
200
本当に使える?AutoUpgrade の新機能を実践検証してみた
oracle4engineer
PRO
1
120
登壇ネタの見つけ方 / How to find talk topics
pinkumohikan
2
200
Snowflake Summit 2025全体振り返り / Snowflake Summit 2025 Overall Review
mtpooh
2
190
ObsidianをMCP連携させてみる
ttnyt8701
2
140
Clineを含めたAIエージェントを 大規模組織に導入し、投資対効果を考える / Introducing AI agents into your organization
i35_267
4
1.3k
Featured
See All Featured
YesSQL, Process and Tooling at Scale
rocio
173
14k
Principles of Awesome APIs and How to Build Them.
keavy
126
17k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
367
26k
The Art of Delivering Value - GDevCon NA Keynote
reverentgeek
15
1.5k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
8
660
jQuery: Nuts, Bolts and Bling
dougneiner
63
7.8k
Building a Modern Day E-commerce SEO Strategy
aleyda
41
7.3k
Become a Pro
speakerdeck
PRO
28
5.4k
Git: the NoSQL Database
bkeepers
PRO
430
65k
GraphQLとの向き合い方2022年版
quramy
46
14k
Optimizing for Happiness
mojombo
379
70k
Documentation Writing (for coders)
carmenintech
71
4.9k
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.