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
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
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
OSSのSNSツール「Misskey」をさわってみよう(右下ワイプで私のOSCの20年を振り返ります) / 20250705-osc2025-do
akkiesoft
0
170
AIの全社活用を推進するための安全なレールを敷いた話
shoheimitani
2
540
united airlines ™®️ USA Contact Numbers: Complete 2025 Support Guide
flyunitedhelp
1
370
SEQUENCE object comparison - db tech showcase 2025 LT2
nori_shinoda
0
150
ビズリーチが挑む メトリクスを活用した技術的負債の解消 / dev-productivity-con2025
visional_engineering_and_design
3
7.8k
Should Our Project Join the CNCF? (Japanese Recap)
whywaita
PRO
0
340
Reach American Airlines®️ Instantly: 19 Calling Methods for Fast Support in the USA
flyamerican
1
170
AI専用のリンターを作る #yumemi_patch
bengo4com
6
4.3k
ビズリーチにおけるリアーキテクティング実践事例 / JJUG CCC 2025 Spring
visional_engineering_and_design
1
130
タイミーのデータモデリング事例と今後のチャレンジ
ttccddtoki
6
2.4k
面倒な作業はAIにおまかせ。Flutter開発をスマートに効率化
ruideengineer
0
260
american airlines®️ USA Contact Numbers: Complete 2025 Support Guide
supportflight
1
110
Featured
See All Featured
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
53k
The Pragmatic Product Professional
lauravandoore
35
6.7k
Statistics for Hackers
jakevdp
799
220k
StorybookのUI Testing Handbookを読んだ
zakiyama
30
5.9k
GraphQLの誤解/rethinking-graphql
sonatard
71
11k
Scaling GitHub
holman
460
140k
Music & Morning Musume
bryan
46
6.6k
Practical Orchestrator
shlominoach
189
11k
Automating Front-end Workflow
addyosmani
1370
200k
Optimizing for Happiness
mojombo
379
70k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
26
2.9k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
PRO
20
1.3k
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.