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
220
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
340
Firebase-React-App
izuna385
0
240
React+FastAPIを用いた簡単なWebアプリ作製
izuna385
0
1.6k
UseCase of Entity Linking
izuna385
0
550
Unofficial slides: From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains (ACL 2020)
izuna385
1
650
Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
izuna385
0
840
Zero-shot Entity Linking with Dense Entity Retrieval (Unofficial slides) and Entity Linking future directions
izuna385
3
1k
Entity representation with relational attention
izuna385
0
80
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
540
Other Decks in Technology
See All in Technology
ここはMCPの夜明けまえ
nwiizo
15
6.5k
Would you THINK such a demonstration interesting ?
shumpei3
1
220
4/17/25 - CIJUG - Java Meets AI: Build LLM-Powered Apps with LangChain4j (part 2)
edeandrea
PRO
0
110
AI Agentを「期待通り」に動かすために:設計アプローチの模索と現在地
kworkdev
PRO
2
450
SREの視点で考えるSIEM活用術 〜AWS環境でのセキュリティ強化〜
coconala_engineer
1
290
PagerDuty×ポストモーテムで築く障害対応文化/Building a culture of incident response with PagerDuty and postmortems
aeonpeople
1
110
CloudWatch 大好きなSAが語る CloudWatch キホンのキ
o11yfes2023
0
180
Creating Awesome Change in SmartNews
martin_lover
1
280
30代からでも遅くない! 内製開発の世界に飛び込み、最前線で戦うLLMアプリ開発エンジニアになろう
minorun365
PRO
6
490
生成AIによるCloud Native基盤構築の可能性と実践的ガードレールの敷設について
nwiizo
7
730
CBになったのでEKSのこともっと知ってもらいたい!
daitak
1
160
Cross Data Platforms Meetup LT 20250422
tarotaro0129
1
590
Featured
See All Featured
Why Our Code Smells
bkeepers
PRO
336
57k
Put a Button on it: Removing Barriers to Going Fast.
kastner
60
3.8k
Intergalactic Javascript Robots from Outer Space
tanoku
270
27k
The Art of Programming - Codeland 2020
erikaheidi
53
13k
Designing for Performance
lara
608
69k
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
9
750
Music & Morning Musume
bryan
47
6.5k
Building Better People: How to give real-time feedback that sticks.
wjessup
367
19k
Learning to Love Humans: Emotional Interface Design
aarron
273
40k
A designer walks into a library…
pauljervisheath
205
24k
Large-scale JavaScript Application Architecture
addyosmani
512
110k
Become a Pro
speakerdeck
PRO
27
5.3k
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.