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 Hierarchical Graph Perspective(WWW19)
Search
izuna385
May 28, 2019
Technology
0
170
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
280
Firebase-React-App
izuna385
0
210
React+FastAPIを用いた簡単なWebアプリ作製
izuna385
0
1.3k
UseCase of Entity Linking
izuna385
0
390
Unofficial slides: From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains (ACL 2020)
izuna385
1
570
Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
izuna385
0
620
Zero-shot Entity Linking with Dense Entity Retrieval (Unofficial slides) and Entity Linking future directions
izuna385
3
840
Entity representation with relational attention
izuna385
0
69
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
440
Other Decks in Technology
See All in Technology
The CloudCompare project by Dr. Daniel Girardeau-Montaut
kentaitakura
0
510
Data and AI Governance: Existing Challenges and Emerging Trends
scotthsieh825
0
160
SPI原点回帰論:事業課題とFour Keysの結節点を見出す実践的ソフトウェアプロセス改善 / DevOpsDays Tokyo 2024
visional_engineering_and_design
4
1.6k
Janus
bkuhlmann
1
490
Delivering Millions of Messages within seconds @ Duolingo
pelelgrino
0
340
WebアプリケーションにおけるPDOの使い方入門 / phpcon odawara 2024
meihei3
2
430
検証を通して見えてきたTiDBの性能特性
lycorptech_jp
PRO
6
3.4k
Databricksを活用してDELISH KITCHENのレシピレコメンドを開発した話
furu8
0
250
プロトタイピングによる不確実性の低減 / Reducing Uncertainty through Prototyping
ohbarye
4
290
Autonomous Database Cloud 技術詳細 / adb-s_technical_detail_jp
oracle4engineer
PRO
14
35k
テストプロセスで大事にしていること #jasstnano
makky_tyuyan
0
130
4年前、あるじゃん老害エンジニアLT合戦に登壇、米国西海岸コンピュータ歴史博物館体験記の続編
toshi_atsumi
0
200
Featured
See All Featured
The Power of CSS Pseudo Elements
geoffreycrofte
59
5k
From Idea to $5000 a Month in 5 Months
shpigford
377
45k
Mobile First: as difficult as doing things right
swwweet
216
8.6k
A designer walks into a library…
pauljervisheath
199
23k
The Language of Interfaces
destraynor
151
23k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
240
1.2M
Fontdeck: Realign not Redesign
paulrobertlloyd
76
4.9k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
124
32k
Git: the NoSQL Database
bkeepers
PRO
422
63k
GraphQLとの向き合い方2022年版
quramy
31
12k
[RailsConf 2023] Rails as a piece of cake
palkan
22
3.9k
Large-scale JavaScript Application Architecture
addyosmani
503
110k
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.