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
Four Keysから始める信頼性の改善 - SRE NEXT 2025
ozakikota
0
420
伴走から自律へ: 形式知へと導くSREイネーブリングによる プロダクトチームの信頼性オーナーシップ向上 / SRE NEXT 2025
visional_engineering_and_design
3
460
SREの次のキャリアの道しるべ 〜SREがマネジメントレイヤーに挑戦して、 気づいたこととTips〜
coconala_engineer
1
4.4k
SRE with AI:実践から学ぶ、運用課題解決と未来への展望
yoshiiryo1
0
320
60以上のプロダクトを持つ組織における開発者体験向上への取り組み - チームAPIとBackstageで構築する組織の可視化基盤 - / sre next 2025 Efforts to Improve Developer Experience in an Organization with Over 60 Products
vtryo
3
1.9k
アクセスピークを制するオートスケール再設計: 障害を乗り越えKEDAで実現したリソース管理の最適化
myamashii
1
670
研究開発部メンバーの働き⽅ / Sansan R&D Profile
sansan33
PRO
3
18k
How Do I Contact Jetblue Airlines® Reservation Number: Fast Support Guide
thejetblueairhelpsupport
0
150
Microsoft Defender XDRで疲弊しないためのインシデント対応
sophiakunii
1
320
無理しない AI 活用サービス / #jazug
koudaiii
0
100
全部AI、全員Cursor、ドキュメント駆動開発 〜DevinやGeminiも添えて〜
rinchsan
10
5.1k
ビジネス職が分析も担う事業部制組織でのデータ活用の仕組みづくり / Enabling Data Analytics in Business-Led Divisional Organizations
zaimy
1
390
Featured
See All Featured
What’s in a name? Adding method to the madness
productmarketing
PRO
23
3.5k
Scaling GitHub
holman
460
140k
Into the Great Unknown - MozCon
thekraken
40
1.9k
YesSQL, Process and Tooling at Scale
rocio
173
14k
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
29
9.6k
A Modern Web Designer's Workflow
chriscoyier
695
190k
The MySQL Ecosystem @ GitHub 2015
samlambert
251
13k
It's Worth the Effort
3n
185
28k
Docker and Python
trallard
45
3.5k
Designing Experiences People Love
moore
142
24k
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
48
2.9k
Building Applications with DynamoDB
mza
95
6.5k
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.