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
390
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
580
Unofficial slides: From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains (ACL 2020)
izuna385
1
670
Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
izuna385
0
880
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
84
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
570
Other Decks in Technology
See All in Technology
5分でカオスエンジニアリングを分かった気になろう
pandayumi
0
260
プラットフォーム転換期におけるGitHub Copilot活用〜Coding agentがそれを加速するか〜 / Leveraging GitHub Copilot During Platform Transition Periods
aeonpeople
1
230
未経験者・初心者に贈る!40分でわかるAndroidアプリ開発の今と大事なポイント
operando
5
750
バイブスに「型」を!Kent Beckに学ぶ、AI時代のテスト駆動開発
amixedcolor
2
580
実践!カスタムインストラクション&スラッシュコマンド
puku0x
0
530
Snowflake Intelligence × Document AIで“使いにくいデータ”を“使えるデータ”に
kevinrobot34
1
120
【NoMapsTECH 2025】AI Edge Computing Workshop
akit37
0
230
Codeful Serverless / 一人運用でもやり抜く力
_kensh
7
450
現場で効くClaude Code ─ 最新動向と企業導入
takaakikakei
1
260
新アイテムをどう使っていくか?みんなであーだこーだ言ってみよう / 20250911-rpi-jam-tokyo
akkiesoft
0
340
はじめてのOSS開発からみえたGo言語の強み
shibukazu
3
980
roppongirb_20250911
igaiga
1
240
Featured
See All Featured
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
194
16k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
285
14k
Code Reviewing Like a Champion
maltzj
525
40k
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
358
30k
Rails Girls Zürich Keynote
gr2m
95
14k
Learning to Love Humans: Emotional Interface Design
aarron
273
40k
The World Runs on Bad Software
bkeepers
PRO
70
11k
Fashionably flexible responsive web design (full day workshop)
malarkey
407
66k
Building Applications with DynamoDB
mza
96
6.6k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
26
3k
The Cost Of JavaScript in 2023
addyosmani
53
8.9k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
44
2.5k
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.