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
190
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
300
Firebase-React-App
izuna385
0
220
React+FastAPIを用いた簡単なWebアプリ作製
izuna385
0
1.5k
UseCase of Entity Linking
izuna385
0
470
Unofficial slides: From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains (ACL 2020)
izuna385
1
610
Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
izuna385
0
710
Zero-shot Entity Linking with Dense Entity Retrieval (Unofficial slides) and Entity Linking future directions
izuna385
3
930
Entity representation with relational attention
izuna385
0
73
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
480
Other Decks in Technology
See All in Technology
技術的負債解消の取り組みと専門チームのお話
bengo4com
0
330
Developer Experienceを向上させる基盤づくりの取り組み事例集
coconala_engineer
0
150
OR学会2024秋_短期収益と将来のオフ方策評価性能を考慮したクーポン割当方策混合比の決定
recruitengineers
PRO
4
460
JTCや セキュリティチェックリストが夢の跡
nikinusu
1
640
Technical Writing Meetup vol.35
soracom
PRO
2
120
Road to Single Activity
yurihondo
2
240
「家族アルバム みてね」における運用管理・ オブザーバビリティの全貌 / Overview of Operation Management and Observability in FamilyAlbum
isaoshimizu
4
160
Classmethod AI Talks(CATs) #1 司会進行スライド(2024.09.19) / classmethod-ai-talks-aka-cats_moderator-slides_vol1_2024-09-19
shinyaa31
0
110
App Router を実プロダクトで採用して見えてきた勘所をちょっとだけ紹介
marokanatani
1
930
事前準備が肝!AI活用のための業務改革
layerx
PRO
1
380
Oracle Base Database Service 技術詳細
oracle4engineer
PRO
5
46k
QAに対する超個人的な解釈 / Personal Take on QA
toma_sm
1
100
Featured
See All Featured
5 minutes of I Can Smell Your CMS
philhawksworth
202
19k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
36
1.7k
Web development in the modern age
philhawksworth
205
10k
The Invisible Side of Design
smashingmag
296
50k
Documentation Writing (for coders)
carmenintech
65
4.3k
Art, The Web, and Tiny UX
lynnandtonic
294
20k
How To Stay Up To Date on Web Technology
chriscoyier
786
250k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
131
32k
Code Reviewing Like a Champion
maltzj
517
39k
A Tale of Four Properties
chriscoyier
155
22k
Visualization
eitanlees
142
15k
Infographics Made Easy
chrislema
239
18k
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.