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
330
Firebase-React-App
izuna385
0
230
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
540
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
830
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
78
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
540
Other Decks in Technology
See All in Technology
OPENLOGI Company Profile for engineer
hr01
1
22k
日本MySQLユーザ会ができるまで / making MyNA
tmtms
1
360
バックエンドエンジニアによるフロントエンドテスト拡充の具体的手法
kinosuke01
1
720
技術好きなエンジニアが _リーダーへの進化_ によって得たものと失ったもの / The Gains and Losses of a Tech-Enthusiast Engineer’s “Evolution into Leadership”
kaminashi
0
200
Amazon GuardDuty Malware Protection for Amazon S3を使おう
ryder472
2
100
Road to SRE NEXT@仙台 IVRyの組織の形とSLO運用の現状
abnoumaru
0
390
バクラクでのSystem Risk Records導入による変化と改善の取り組み/Changes and Improvement Initiatives Resulting from the Implementation of System Risk Records
taddy_919
0
220
ウェブアクセシビリティとは
lycorptech_jp
PRO
0
260
Vision Language Modelを活用した メルカリの類似画像レコメンドの性能改善
yadayuki
9
1.2k
LINE Notify互換のボットを作った話
kenichirokimura
0
180
Engineering Managementのグローバルトレンド #emoasis / Engineering Management Global Trend
kyonmm
PRO
6
990
ISUCONにPHPで挑み続けてできるようになっ(てき)たこと / phperkaigi2025
blue_goheimochi
0
140
Featured
See All Featured
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
PRO
16
1.1k
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
marcduiker
28
2k
Measuring & Analyzing Core Web Vitals
bluesmoon
6
320
Visualization
eitanlees
146
16k
Building Flexible Design Systems
yeseniaperezcruz
328
38k
How To Stay Up To Date on Web Technology
chriscoyier
790
250k
RailsConf 2023
tenderlove
29
1k
Agile that works and the tools we love
rasmusluckow
328
21k
Into the Great Unknown - MozCon
thekraken
36
1.7k
GraphQLの誤解/rethinking-graphql
sonatard
70
10k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
28
1.6k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
4
500
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.