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
360
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
560
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
850
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
550
Other Decks in Technology
See All in Technology
カンファレンスのつくりかた / The Conference Code: What Makes It All Work
tomzoh
7
890
データプレーンプログラミングとは? DPU&スイッチASICの開発経験から語る
ebiken
PRO
0
180
コードの考古学 〜労務システムから発掘した成長の糧〜
kenta_smarthr
0
500
人とAIとの共創を夢見た2か月 #共創AIミートアップ / Co-Creation with Keito-chan
kondoyuko
1
650
Introduction to Sansan for Engineers / エンジニア向け会社紹介
sansan33
PRO
5
37k
Redmineの意外と知らない便利機能 (Redmine 6.0対応版)
vividtone
0
1.1k
Okayama WordPress Meetup #12 | そのバックアップ、本当に復元できますか? リストアやってみた!
takeshifurusato
0
110
AIオンボーディングとAIプロセスマイニング
nrryuya
5
1.3k
Streamline Cloud-Native App Development Using CDEs
saeedzf
0
680
VueUseから学ぶ実践TypeScript #TSKaigi #TSKaigi2025
bengo4com
3
5.3k
SmartHRの複数のチームにおけるMCPサーバーの活用事例と課題
yukisnow1823
2
1.1k
Bill One 開発エンジニア 紹介資料
sansan33
PRO
4
12k
Featured
See All Featured
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
irinanazarova
8
740
Building Applications with DynamoDB
mza
95
6.4k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
42
2.3k
Documentation Writing (for coders)
carmenintech
71
4.8k
Learning to Love Humans: Emotional Interface Design
aarron
273
40k
The Cult of Friendly URLs
andyhume
78
6.4k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
194
16k
Rebuilding a faster, lazier Slack
samanthasiow
81
9k
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
29
2.6k
The Art of Delivering Value - GDevCon NA Keynote
reverentgeek
14
1.5k
Large-scale JavaScript Application Architecture
addyosmani
512
110k
A Modern Web Designer's Workflow
chriscoyier
693
190k
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.