SlideShare una empresa de Scribd logo
1 de 27
Descargar para leer sin conexión
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
June 17, 2017 ICLR @DeNA
Eiji Sekiya
AI Research and Development Gr.
AI System Dept. 

DeNA Co., Ltd.
1
h"ps://openreview.net/pdf?id=SJU4ayYgl
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
•
• (@eratostennis)
•
• Master
• DeNA (2014)
• : (~2016)
• Hadoop, Vertica
• : (2016~)
•
• GameAI
2
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Abstract
• Semi-supervised learning on graph-structured data
• Localized first-order approximation of spectral graph
• :
•
•
3
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Agenda
• Introduction
• Related Work
• Fast Approximate Convolutions on Graphs
• Semi-Supervised Node Classification
• Experiments
• Results
• Conclusion
4
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Relation to Weisfeiler-Lehman Algorithm
• WL-1
• Hash Neural Network
5
hash
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Node Embeddings with Random Weights
6
output 2
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Semi-Supervised Node Embeddings
• 4 1
7
:	h"p://tkipf.github.io/graph-convoluDonal-networks/
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Related Work
• Graph-Based Semi-Supervised Learning
• Graph Laplacian regularization
• Label Propagation (Zhu et al., 2003)
• Manifold Regularization (Belkin et al., 2006)
• Graph embedding-based
• DeepWalk (Perozzi et al., 2014)
• Planetoid (Yang et al., 2016)
8
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Related Work (DeepWalk: Perozzi et al., 2014)
•
• SkipGram embedding
• Random Walk
9
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Related Work
• Graph-Based Semi-Supervised Learning
• Graph Laplacian regularization
• Label Propagation (Zhu et al., 2003)
• Manifold Regularization (Belkin et al., 2006)
• Graph embedding-based
• DeepWalk (Perozzi et al., 2014)
• Planetoid (Yang et al., 2016)
• Neural Networks on Graphs ( )
• Spectral graph convolutional neural network (Bruna et al., 2014)
• Fast localized convolution (Defferrard et al., 2016)
10
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Graph-Based Semi-Supervised Learning
• (citation network ) (documents)
•
•
•
• encode
•
11
Neural Networks on Graph
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Multi-layer Graph Convolutional Network (GCN)
•
•
•
•
12
Contribution
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Spectral Graph Convolutions
• Convolution with filter
• :
•
• …(Hammond at el., 2011)
•
• ( )
13
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Spectral Graph Convolutions (Defferrad at el., 2016)
• Graph Convolution ( , )
• K K
• :
•
14
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Layer-Wise Linear Model (Contribution)
• K=1 …
• k k
•
• Renormalization Trick ( )
• Input C, F …
•
15
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Semi-Supervised Node Classification
• Forward Model ( )
• Cross-Entropy:
16
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Experiments (Dataset)
• (Citeseer, Cora, Pubmed)
• Sparse bag-of-words feature vectors for each document
• a list of citation links between documents
• (NELL)
• A set of entities connected with directed, labeled edges
• Random Graph
• A dataset with N nodes we create a random graph assigning 2N edges
uniformly at random
17
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Experiments (Setup)
•
• 2 GCN
•
• Prediction Accuracy
• 1000
•
• 500
• Dropout rate, L2 regularization factor, Number of hidden units
• Cora Citeseer Pubmed
18
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Experiments (Baseline)
• Baseline
• Label Propagation (LP)
• Semi-supervised embedding (SemiEmb)
• Manifold regularization (ManiReg)
• Skip-gram based graph embeddings (DeepWalk)
• Iterative classification algorithm (ICA)
• Planetoid
19
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Results (Semi-Supervised Node Classification)
• Results for all other baseline methods are taken from the Planetoid paper
• Environment
• The same hardware as planetoid
20
Training	Dme		
in	seconds		
unDl	convergence
• Compare different variants of our proposed per-layer propagation model
on the citation network datasets
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Results (Evaluation Propagation Model)
21
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Results (Training Time per Epoch)
• The mean training time per epoch for 100 epochs on simulated random
graphs
22
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Experiments on Model Depth
• Residual connections
• 2, 3
• 7 …
• residual connections
•
23
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Discussion
• Keypoints
• Overcome both limitations
• Graph-Laplacian regularization
• Edges encode mere similarity of nodes
• Skip-gram based methods
• Limited by the fact that they are based on a multi-step pipeline
which difficult to optimize
• Findings
• Propagation from neighboring nodes improves classification
performance
• Proposed renormalized propagation model offers both improved
efficiency
24
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Future Work
• Memory Requirement
• Full-batch gradient descent
• Grows linearly in the size of the dataset
• Mini-batch stochastic gradient descent can alleviate this issue
• Directed edges and edge features
• Limited to undirected graph
• NELL show it is possible to handle
• By representing the original directed graph as an undirected bipartite
graph
• Limiting assumptions
• Locality
• dependence on the Kth-order neighborhood for a GCN with K layers
• Equal importance of self-connections vs. edges to neighboring nodes 25
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Reference
• Graph Semi-Supervised Learning
• Xiaojin Zhu, Zoubin Ghahramani, and John Lafferty. Semi-supervised learning using
gaussian fields and harmonic functions. In International Conference on Machine Learning
(ICML), volume 3, pp. 912–919, 2003.
• Mikhail Belkin, Partha Niyogi, and Vikas Sindhwani. Manifold regularization: A geometric
frame- work for learning from labeled and unlabeled examples. Journal of machine learning
research (JMLR), 7(Nov):2399–2434, 2006.
• JasonWeston,Fre ́de ́ricRatle,HosseinMobahi,andRonanCollobert. Deeplearningviasemi-
supervised embedding. In Neural Networks: Tricks of the Trade, pp. 639–655. Springer,
2012.
• Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S. Corrado, and Jeff Dean. Distributed
repre- sentations of words and phrases and their compositionality. In Advances in neural
information processing systems (NIPS), pp. 3111–3119, 2013.
• Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. Deepwalk: Online learning of social
repre- sentations. In Proceedings of the 20th ACM SIGKDD international conference on
Knowledge discovery and data mining, pp. 701–710. ACM, 2014.
• Zhilin Yang, William Cohen, and Ruslan Salakhutdinov. Revisiting semi-supervised learning
with graph embeddings. In International Conference on Machine Learning (ICML), 2016.
26
Copyright (C) DeNA Co.,Ltd. All Rights Reserved.
Reference
• Dataset & Pre-Processing
• Prithviraj Sen, Galileo Namata, Mustafa Bilgic, Lise Getoor, Brian Galligher, and Tina
Eliassi-Rad. Collective classification in network data. AI magazine, 29(3):93, 2008.
• Andrew Carlson, Justin Betteridge, Bryan Kisiel, Burr Settles, Estevam R. Hruschka Jr, and
Tom M. Mitchell. Toward an architecture for never-ending language learning. In AAAI,
volume 5, pp. 3, 2010.
• Zhilin Yang, William Cohen, and Ruslan Salakhutdinov. Revisiting semi-supervised learning
with graph embeddings. In International Conference on Machine Learning (ICML), 2016.
• Website
• http://tkipf.github.io/graph-convolutional-networks/
• Implementation
• https://github.com/tkipf/gcn
27

Más contenido relacionado

La actualidad más candente

Convolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningConvolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningMohamed Loey
 
[DL輪読会]Relational inductive biases, deep learning, and graph networks
[DL輪読会]Relational inductive biases, deep learning, and graph networks[DL輪読会]Relational inductive biases, deep learning, and graph networks
[DL輪読会]Relational inductive biases, deep learning, and graph networksDeep Learning JP
 
polynomial linear regression
polynomial linear regressionpolynomial linear regression
polynomial linear regressionAkhilesh Joshi
 
Random Forest による分類
Random Forest による分類Random Forest による分類
Random Forest による分類Ken'ichi Matsui
 
Fishers linear discriminant for dimensionality reduction.
Fishers linear discriminant for dimensionality reduction.Fishers linear discriminant for dimensionality reduction.
Fishers linear discriminant for dimensionality reduction.Nurul Amin Choudhury
 
Overcoming Catastrophic Forgetting in Neural Networks読んだ
Overcoming Catastrophic Forgetting in Neural Networks読んだOvercoming Catastrophic Forgetting in Neural Networks読んだ
Overcoming Catastrophic Forgetting in Neural Networks読んだYusuke Uchida
 
[DL輪読会]When Does Label Smoothing Help?
[DL輪読会]When Does Label Smoothing Help?[DL輪読会]When Does Label Smoothing Help?
[DL輪読会]When Does Label Smoothing Help?Deep Learning JP
 
Neural networks and deep learning
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learningJörgen Sandig
 
Semi supervised classification with graph convolutional networks
Semi supervised classification with graph convolutional networksSemi supervised classification with graph convolutional networks
Semi supervised classification with graph convolutional networks哲东 郑
 
ベイジアンディープニューラルネット
ベイジアンディープニューラルネットベイジアンディープニューラルネット
ベイジアンディープニューラルネットYuta Kashino
 
深層学習とベイズ統計
深層学習とベイズ統計深層学習とベイズ統計
深層学習とベイズ統計Yuta Kashino
 
システム制御とディープラーニング
システム制御とディープラーニングシステム制御とディープラーニング
システム制御とディープラーニングKeio Robotics Association
 
【DL輪読会】Free Lunch for Few-shot Learning: Distribution Calibration
【DL輪読会】Free Lunch for Few-shot Learning: Distribution Calibration【DL輪読会】Free Lunch for Few-shot Learning: Distribution Calibration
【DL輪読会】Free Lunch for Few-shot Learning: Distribution CalibrationDeep Learning JP
 
機械学習による統計的実験計画(ベイズ最適化を中心に)
機械学習による統計的実験計画(ベイズ最適化を中心に)機械学習による統計的実験計画(ベイズ最適化を中心に)
機械学習による統計的実験計画(ベイズ最適化を中心に)Kota Matsui
 
Learning Convolutional Neural Networks for Graphs
Learning Convolutional Neural Networks for GraphsLearning Convolutional Neural Networks for Graphs
Learning Convolutional Neural Networks for GraphsTakuya Akiba
 

La actualidad más candente (20)

Convolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningConvolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep Learning
 
[DL輪読会]Relational inductive biases, deep learning, and graph networks
[DL輪読会]Relational inductive biases, deep learning, and graph networks[DL輪読会]Relational inductive biases, deep learning, and graph networks
[DL輪読会]Relational inductive biases, deep learning, and graph networks
 
polynomial linear regression
polynomial linear regressionpolynomial linear regression
polynomial linear regression
 
Random Forest による分類
Random Forest による分類Random Forest による分類
Random Forest による分類
 
Fishers linear discriminant for dimensionality reduction.
Fishers linear discriminant for dimensionality reduction.Fishers linear discriminant for dimensionality reduction.
Fishers linear discriminant for dimensionality reduction.
 
CNN Tutorial
CNN TutorialCNN Tutorial
CNN Tutorial
 
Overcoming Catastrophic Forgetting in Neural Networks読んだ
Overcoming Catastrophic Forgetting in Neural Networks読んだOvercoming Catastrophic Forgetting in Neural Networks読んだ
Overcoming Catastrophic Forgetting in Neural Networks読んだ
 
[DL輪読会]When Does Label Smoothing Help?
[DL輪読会]When Does Label Smoothing Help?[DL輪読会]When Does Label Smoothing Help?
[DL輪読会]When Does Label Smoothing Help?
 
Neural networks and deep learning
Neural networks and deep learningNeural networks and deep learning
Neural networks and deep learning
 
Deep walk について
Deep walk についてDeep walk について
Deep walk について
 
Semi supervised classification with graph convolutional networks
Semi supervised classification with graph convolutional networksSemi supervised classification with graph convolutional networks
Semi supervised classification with graph convolutional networks
 
ベイジアンディープニューラルネット
ベイジアンディープニューラルネットベイジアンディープニューラルネット
ベイジアンディープニューラルネット
 
深層学習とベイズ統計
深層学習とベイズ統計深層学習とベイズ統計
深層学習とベイズ統計
 
システム制御とディープラーニング
システム制御とディープラーニングシステム制御とディープラーニング
システム制御とディープラーニング
 
【DL輪読会】Free Lunch for Few-shot Learning: Distribution Calibration
【DL輪読会】Free Lunch for Few-shot Learning: Distribution Calibration【DL輪読会】Free Lunch for Few-shot Learning: Distribution Calibration
【DL輪読会】Free Lunch for Few-shot Learning: Distribution Calibration
 
GoogLeNet Insights
GoogLeNet InsightsGoogLeNet Insights
GoogLeNet Insights
 
CIFAR-10
CIFAR-10CIFAR-10
CIFAR-10
 
機械学習による統計的実験計画(ベイズ最適化を中心に)
機械学習による統計的実験計画(ベイズ最適化を中心に)機械学習による統計的実験計画(ベイズ最適化を中心に)
機械学習による統計的実験計画(ベイズ最適化を中心に)
 
リプシッツ連続性に基づく勾配法・ニュートン型手法の計算量解析
リプシッツ連続性に基づく勾配法・ニュートン型手法の計算量解析リプシッツ連続性に基づく勾配法・ニュートン型手法の計算量解析
リプシッツ連続性に基づく勾配法・ニュートン型手法の計算量解析
 
Learning Convolutional Neural Networks for Graphs
Learning Convolutional Neural Networks for GraphsLearning Convolutional Neural Networks for Graphs
Learning Convolutional Neural Networks for Graphs
 

Destacado

言葉のもつ広がりを、モデルの学習に活かそう -one-hot to distribution in language modeling-
言葉のもつ広がりを、モデルの学習に活かそう -one-hot to distribution in language modeling-言葉のもつ広がりを、モデルの学習に活かそう -one-hot to distribution in language modeling-
言葉のもつ広がりを、モデルの学習に活かそう -one-hot to distribution in language modeling-Takahiro Kubo
 
ICLR2017読み会 Data Noising as Smoothing in Neural Network Language Models @Dena
ICLR2017読み会 Data Noising as Smoothing in Neural Network Language Models @DenaICLR2017読み会 Data Noising as Smoothing in Neural Network Language Models @Dena
ICLR2017読み会 Data Noising as Smoothing in Neural Network Language Models @DenaTakanori Nakai
 
ICLR読み会 奥村純 20170617
ICLR読み会 奥村純 20170617ICLR読み会 奥村純 20170617
ICLR読み会 奥村純 20170617Jun Okumura
 
[ICLR2017読み会 @ DeNA] ICLR2017紹介
[ICLR2017読み会 @ DeNA] ICLR2017紹介[ICLR2017読み会 @ DeNA] ICLR2017紹介
[ICLR2017読み会 @ DeNA] ICLR2017紹介Takeru Miyato
 
エフェクト用 Shader 機能紹介
エフェクト用 Shader 機能紹介エフェクト用 Shader 機能紹介
エフェクト用 Shader 機能紹介Hajime Sanno
 
エンジニアがデザインやってみた @ Aimning MeetUp 2017/10
エンジニアがデザインやってみた @ Aimning MeetUp 2017/10エンジニアがデザインやってみた @ Aimning MeetUp 2017/10
エンジニアがデザインやってみた @ Aimning MeetUp 2017/10Hidenori Doi
 
エフェクトにしっかり色を付ける方法
エフェクトにしっかり色を付ける方法エフェクトにしっかり色を付ける方法
エフェクトにしっかり色を付ける方法kmasaki
 
当たり前を当たり前に:Agile2017レポート
当たり前を当たり前に:Agile2017レポート当たり前を当たり前に:Agile2017レポート
当たり前を当たり前に:Agile2017レポートLINE Corporation
 
共変戻り値型って知ってますか?
共変戻り値型って知ってますか?共変戻り値型って知ってますか?
共変戻り値型って知ってますか?Ryota Murohoshi
 
Node and Micro-Services at IBM
Node and Micro-Services at IBMNode and Micro-Services at IBM
Node and Micro-Services at IBMDejan Glozic
 
Effective web performance tuning for smartphone
Effective web performance tuning for smartphoneEffective web performance tuning for smartphone
Effective web performance tuning for smartphonedena_study
 
RのffでGLMしてみたけど...
RのffでGLMしてみたけど...RのffでGLMしてみたけど...
RのffでGLMしてみたけど...Kazuya Wada
 
Googleのインフラ技術から考える理想のDevOps
Googleのインフラ技術から考える理想のDevOpsGoogleのインフラ技術から考える理想のDevOps
Googleのインフラ技術から考える理想のDevOpsEtsuji Nakai
 
ディープボルツマンマシン入門
ディープボルツマンマシン入門ディープボルツマンマシン入門
ディープボルツマンマシン入門Saya Katafuchi
 
PRML上巻勉強会 at 東京大学 資料 第4章4.3.1 〜 4.5.2
PRML上巻勉強会 at 東京大学 資料 第4章4.3.1 〜 4.5.2PRML上巻勉強会 at 東京大学 資料 第4章4.3.1 〜 4.5.2
PRML上巻勉強会 at 東京大学 資料 第4章4.3.1 〜 4.5.2Hiroyuki Kato
 
FINAL FANTASY Record Keeper の作り方
FINAL FANTASY Record Keeper の作り方FINAL FANTASY Record Keeper の作り方
FINAL FANTASY Record Keeper の作り方dena_study
 

Destacado (20)

言葉のもつ広がりを、モデルの学習に活かそう -one-hot to distribution in language modeling-
言葉のもつ広がりを、モデルの学習に活かそう -one-hot to distribution in language modeling-言葉のもつ広がりを、モデルの学習に活かそう -one-hot to distribution in language modeling-
言葉のもつ広がりを、モデルの学習に活かそう -one-hot to distribution in language modeling-
 
医療データ解析界隈から見たICLR2017
医療データ解析界隈から見たICLR2017医療データ解析界隈から見たICLR2017
医療データ解析界隈から見たICLR2017
 
ICLR2017読み会 Data Noising as Smoothing in Neural Network Language Models @Dena
ICLR2017読み会 Data Noising as Smoothing in Neural Network Language Models @DenaICLR2017読み会 Data Noising as Smoothing in Neural Network Language Models @Dena
ICLR2017読み会 Data Noising as Smoothing in Neural Network Language Models @Dena
 
170614 iclr reading-public
170614 iclr reading-public170614 iclr reading-public
170614 iclr reading-public
 
Q prop
Q propQ prop
Q prop
 
ICLR読み会 奥村純 20170617
ICLR読み会 奥村純 20170617ICLR読み会 奥村純 20170617
ICLR読み会 奥村純 20170617
 
[ICLR2017読み会 @ DeNA] ICLR2017紹介
[ICLR2017読み会 @ DeNA] ICLR2017紹介[ICLR2017読み会 @ DeNA] ICLR2017紹介
[ICLR2017読み会 @ DeNA] ICLR2017紹介
 
エフェクト用 Shader 機能紹介
エフェクト用 Shader 機能紹介エフェクト用 Shader 機能紹介
エフェクト用 Shader 機能紹介
 
エンジニアがデザインやってみた @ Aimning MeetUp 2017/10
エンジニアがデザインやってみた @ Aimning MeetUp 2017/10エンジニアがデザインやってみた @ Aimning MeetUp 2017/10
エンジニアがデザインやってみた @ Aimning MeetUp 2017/10
 
エフェクトにしっかり色を付ける方法
エフェクトにしっかり色を付ける方法エフェクトにしっかり色を付ける方法
エフェクトにしっかり色を付ける方法
 
当たり前を当たり前に:Agile2017レポート
当たり前を当たり前に:Agile2017レポート当たり前を当たり前に:Agile2017レポート
当たり前を当たり前に:Agile2017レポート
 
共変戻り値型って知ってますか?
共変戻り値型って知ってますか?共変戻り値型って知ってますか?
共変戻り値型って知ってますか?
 
Node and Micro-Services at IBM
Node and Micro-Services at IBMNode and Micro-Services at IBM
Node and Micro-Services at IBM
 
Effective web performance tuning for smartphone
Effective web performance tuning for smartphoneEffective web performance tuning for smartphone
Effective web performance tuning for smartphone
 
RのffでGLMしてみたけど...
RのffでGLMしてみたけど...RのffでGLMしてみたけど...
RのffでGLMしてみたけど...
 
Googleのインフラ技術から考える理想のDevOps
Googleのインフラ技術から考える理想のDevOpsGoogleのインフラ技術から考える理想のDevOps
Googleのインフラ技術から考える理想のDevOps
 
ディープボルツマンマシン入門
ディープボルツマンマシン入門ディープボルツマンマシン入門
ディープボルツマンマシン入門
 
PRML上巻勉強会 at 東京大学 資料 第4章4.3.1 〜 4.5.2
PRML上巻勉強会 at 東京大学 資料 第4章4.3.1 〜 4.5.2PRML上巻勉強会 at 東京大学 資料 第4章4.3.1 〜 4.5.2
PRML上巻勉強会 at 東京大学 資料 第4章4.3.1 〜 4.5.2
 
FINAL FANTASY Record Keeper の作り方
FINAL FANTASY Record Keeper の作り方FINAL FANTASY Record Keeper の作り方
FINAL FANTASY Record Keeper の作り方
 
Prml 4.3
Prml 4.3Prml 4.3
Prml 4.3
 

Similar a Semi-Supervised Classification with Graph Convolutional Networks @ICLR2017読み会

20191107 deeplearningapproachesfornetworks
20191107 deeplearningapproachesfornetworks20191107 deeplearningapproachesfornetworks
20191107 deeplearningapproachesfornetworkstm1966
 
Rack Cluster Deployment for SDSC Supercomputer
Rack Cluster Deployment for SDSC SupercomputerRack Cluster Deployment for SDSC Supercomputer
Rack Cluster Deployment for SDSC SupercomputerRebekah Rodriguez
 
High-Performance Graph Analysis and Modeling
High-Performance Graph Analysis and ModelingHigh-Performance Graph Analysis and Modeling
High-Performance Graph Analysis and ModelingNesreen K. Ahmed
 
PEARC17:A real-time machine learning and visualization framework for scientif...
PEARC17:A real-time machine learning and visualization framework for scientif...PEARC17:A real-time machine learning and visualization framework for scientif...
PEARC17:A real-time machine learning and visualization framework for scientif...Feng Li
 
Azure 機器學習 - 使用Python, R, Spark, CNTK 深度學習
Azure 機器學習 - 使用Python, R, Spark, CNTK 深度學習 Azure 機器學習 - 使用Python, R, Spark, CNTK 深度學習
Azure 機器學習 - 使用Python, R, Spark, CNTK 深度學習 Herman Wu
 
Ling liu part 02:big graph processing
Ling liu part 02:big graph processingLing liu part 02:big graph processing
Ling liu part 02:big graph processingjins0618
 
Grid is Dead ? Nimrod on the Cloud
Grid is Dead ? Nimrod on the CloudGrid is Dead ? Nimrod on the Cloud
Grid is Dead ? Nimrod on the CloudAdianto Wibisono
 
40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facility
40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facility40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facility
40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facilityinside-BigData.com
 
Deep Learning and Automatic Differentiation from Theano to PyTorch
Deep Learning and Automatic Differentiation from Theano to PyTorchDeep Learning and Automatic Differentiation from Theano to PyTorch
Deep Learning and Automatic Differentiation from Theano to PyTorchinside-BigData.com
 
Detection of Related Semantic Datasets Based on Frequent Subgraph Mining
Detection of Related Semantic Datasets Based on Frequent Subgraph MiningDetection of Related Semantic Datasets Based on Frequent Subgraph Mining
Detection of Related Semantic Datasets Based on Frequent Subgraph MiningMikel Emaldi Manrique
 
The Analytics Frontier of the Hadoop Eco-System
The Analytics Frontier of the Hadoop Eco-SystemThe Analytics Frontier of the Hadoop Eco-System
The Analytics Frontier of the Hadoop Eco-Systeminside-BigData.com
 
Deep Learning and What's Next?
Deep Learning and What's Next?Deep Learning and What's Next?
Deep Learning and What's Next?Tao Wang
 
Computing Outside The Box September 2009
Computing Outside The Box September 2009Computing Outside The Box September 2009
Computing Outside The Box September 2009Ian Foster
 
Xiaoxin_Resume_combined_NCL
Xiaoxin_Resume_combined_NCLXiaoxin_Resume_combined_NCL
Xiaoxin_Resume_combined_NCLXiaoxin Ren
 
g-Social - Enhancing e-Science Tools with Social Networking Functionality
g-Social - Enhancing e-Science Tools with Social Networking Functionalityg-Social - Enhancing e-Science Tools with Social Networking Functionality
g-Social - Enhancing e-Science Tools with Social Networking FunctionalityNicholas Loulloudes
 
Ehtsham Elahi, Senior Research Engineer, Personalization Science and Engineer...
Ehtsham Elahi, Senior Research Engineer, Personalization Science and Engineer...Ehtsham Elahi, Senior Research Engineer, Personalization Science and Engineer...
Ehtsham Elahi, Senior Research Engineer, Personalization Science and Engineer...MLconf
 

Similar a Semi-Supervised Classification with Graph Convolutional Networks @ICLR2017読み会 (20)

20191107 deeplearningapproachesfornetworks
20191107 deeplearningapproachesfornetworks20191107 deeplearningapproachesfornetworks
20191107 deeplearningapproachesfornetworks
 
Rack Cluster Deployment for SDSC Supercomputer
Rack Cluster Deployment for SDSC SupercomputerRack Cluster Deployment for SDSC Supercomputer
Rack Cluster Deployment for SDSC Supercomputer
 
High-Performance Graph Analysis and Modeling
High-Performance Graph Analysis and ModelingHigh-Performance Graph Analysis and Modeling
High-Performance Graph Analysis and Modeling
 
PEARC17:A real-time machine learning and visualization framework for scientif...
PEARC17:A real-time machine learning and visualization framework for scientif...PEARC17:A real-time machine learning and visualization framework for scientif...
PEARC17:A real-time machine learning and visualization framework for scientif...
 
Azure 機器學習 - 使用Python, R, Spark, CNTK 深度學習
Azure 機器學習 - 使用Python, R, Spark, CNTK 深度學習 Azure 機器學習 - 使用Python, R, Spark, CNTK 深度學習
Azure 機器學習 - 使用Python, R, Spark, CNTK 深度學習
 
Big data analytics_7_giants_public_24_sep_2013
Big data analytics_7_giants_public_24_sep_2013Big data analytics_7_giants_public_24_sep_2013
Big data analytics_7_giants_public_24_sep_2013
 
Spark
SparkSpark
Spark
 
Ling liu part 02:big graph processing
Ling liu part 02:big graph processingLing liu part 02:big graph processing
Ling liu part 02:big graph processing
 
Grid is Dead ? Nimrod on the Cloud
Grid is Dead ? Nimrod on the CloudGrid is Dead ? Nimrod on the Cloud
Grid is Dead ? Nimrod on the Cloud
 
40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facility
40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facility40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facility
40 Powers of 10 - Simulating the Universe with the DiRAC HPC Facility
 
Deep Learning and Automatic Differentiation from Theano to PyTorch
Deep Learning and Automatic Differentiation from Theano to PyTorchDeep Learning and Automatic Differentiation from Theano to PyTorch
Deep Learning and Automatic Differentiation from Theano to PyTorch
 
Detection of Related Semantic Datasets Based on Frequent Subgraph Mining
Detection of Related Semantic Datasets Based on Frequent Subgraph MiningDetection of Related Semantic Datasets Based on Frequent Subgraph Mining
Detection of Related Semantic Datasets Based on Frequent Subgraph Mining
 
Chug dl presentation
Chug dl presentationChug dl presentation
Chug dl presentation
 
The Analytics Frontier of the Hadoop Eco-System
The Analytics Frontier of the Hadoop Eco-SystemThe Analytics Frontier of the Hadoop Eco-System
The Analytics Frontier of the Hadoop Eco-System
 
Deeplearning in finance
Deeplearning in financeDeeplearning in finance
Deeplearning in finance
 
Deep Learning and What's Next?
Deep Learning and What's Next?Deep Learning and What's Next?
Deep Learning and What's Next?
 
Computing Outside The Box September 2009
Computing Outside The Box September 2009Computing Outside The Box September 2009
Computing Outside The Box September 2009
 
Xiaoxin_Resume_combined_NCL
Xiaoxin_Resume_combined_NCLXiaoxin_Resume_combined_NCL
Xiaoxin_Resume_combined_NCL
 
g-Social - Enhancing e-Science Tools with Social Networking Functionality
g-Social - Enhancing e-Science Tools with Social Networking Functionalityg-Social - Enhancing e-Science Tools with Social Networking Functionality
g-Social - Enhancing e-Science Tools with Social Networking Functionality
 
Ehtsham Elahi, Senior Research Engineer, Personalization Science and Engineer...
Ehtsham Elahi, Senior Research Engineer, Personalization Science and Engineer...Ehtsham Elahi, Senior Research Engineer, Personalization Science and Engineer...
Ehtsham Elahi, Senior Research Engineer, Personalization Science and Engineer...
 

Último

IMA MSN - Medical Students Network (2).pptx
IMA MSN - Medical Students Network (2).pptxIMA MSN - Medical Students Network (2).pptx
IMA MSN - Medical Students Network (2).pptxdolaknnilon
 
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Jack DiGiovanna
 
Multiple time frame trading analysis -brianshannon.pdf
Multiple time frame trading analysis -brianshannon.pdfMultiple time frame trading analysis -brianshannon.pdf
Multiple time frame trading analysis -brianshannon.pdfchwongval
 
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...limedy534
 
Heart Disease Classification Report: A Data Analysis Project
Heart Disease Classification Report: A Data Analysis ProjectHeart Disease Classification Report: A Data Analysis Project
Heart Disease Classification Report: A Data Analysis ProjectBoston Institute of Analytics
 
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一F sss
 
DBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfDBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfJohn Sterrett
 
Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024Colleen Farrelly
 
Top 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In QueensTop 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In Queensdataanalyticsqueen03
 
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdfKantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdfSocial Samosa
 
ASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel CanterASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel Cantervoginip
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxEmmanuel Dauda
 
RadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdfRadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdfgstagge
 
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDINTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDRafezzaman
 
Identifying Appropriate Test Statistics Involving Population Mean
Identifying Appropriate Test Statistics Involving Population MeanIdentifying Appropriate Test Statistics Involving Population Mean
Identifying Appropriate Test Statistics Involving Population MeanMYRABACSAFRA2
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Sapana Sha
 
20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdfHuman37
 
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...dajasot375
 
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...soniya singh
 

Último (20)

IMA MSN - Medical Students Network (2).pptx
IMA MSN - Medical Students Network (2).pptxIMA MSN - Medical Students Network (2).pptx
IMA MSN - Medical Students Network (2).pptx
 
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
 
Multiple time frame trading analysis -brianshannon.pdf
Multiple time frame trading analysis -brianshannon.pdfMultiple time frame trading analysis -brianshannon.pdf
Multiple time frame trading analysis -brianshannon.pdf
 
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
 
Heart Disease Classification Report: A Data Analysis Project
Heart Disease Classification Report: A Data Analysis ProjectHeart Disease Classification Report: A Data Analysis Project
Heart Disease Classification Report: A Data Analysis Project
 
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
 
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
 
DBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfDBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdf
 
Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024
 
Top 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In QueensTop 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In Queens
 
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdfKantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
 
ASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel CanterASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel Canter
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptx
 
RadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdfRadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdf
 
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDINTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
 
Identifying Appropriate Test Statistics Involving Population Mean
Identifying Appropriate Test Statistics Involving Population MeanIdentifying Appropriate Test Statistics Involving Population Mean
Identifying Appropriate Test Statistics Involving Population Mean
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
 
20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf
 
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
 
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
 

Semi-Supervised Classification with Graph Convolutional Networks @ICLR2017読み会

  • 1. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. June 17, 2017 ICLR @DeNA Eiji Sekiya AI Research and Development Gr. AI System Dept. 
 DeNA Co., Ltd. 1 h"ps://openreview.net/pdf?id=SJU4ayYgl
  • 2. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. • • (@eratostennis) • • Master • DeNA (2014) • : (~2016) • Hadoop, Vertica • : (2016~) • • GameAI 2
  • 3. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Abstract • Semi-supervised learning on graph-structured data • Localized first-order approximation of spectral graph • : • • 3
  • 4. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Agenda • Introduction • Related Work • Fast Approximate Convolutions on Graphs • Semi-Supervised Node Classification • Experiments • Results • Conclusion 4
  • 5. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Relation to Weisfeiler-Lehman Algorithm • WL-1 • Hash Neural Network 5 hash
  • 6. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Node Embeddings with Random Weights 6 output 2
  • 7. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Semi-Supervised Node Embeddings • 4 1 7 : h"p://tkipf.github.io/graph-convoluDonal-networks/
  • 8. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Related Work • Graph-Based Semi-Supervised Learning • Graph Laplacian regularization • Label Propagation (Zhu et al., 2003) • Manifold Regularization (Belkin et al., 2006) • Graph embedding-based • DeepWalk (Perozzi et al., 2014) • Planetoid (Yang et al., 2016) 8
  • 9. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Related Work (DeepWalk: Perozzi et al., 2014) • • SkipGram embedding • Random Walk 9
  • 10. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Related Work • Graph-Based Semi-Supervised Learning • Graph Laplacian regularization • Label Propagation (Zhu et al., 2003) • Manifold Regularization (Belkin et al., 2006) • Graph embedding-based • DeepWalk (Perozzi et al., 2014) • Planetoid (Yang et al., 2016) • Neural Networks on Graphs ( ) • Spectral graph convolutional neural network (Bruna et al., 2014) • Fast localized convolution (Defferrard et al., 2016) 10
  • 11. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Graph-Based Semi-Supervised Learning • (citation network ) (documents) • • • • encode • 11 Neural Networks on Graph
  • 12. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Multi-layer Graph Convolutional Network (GCN) • • • • 12 Contribution
  • 13. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Spectral Graph Convolutions • Convolution with filter • : • • …(Hammond at el., 2011) • • ( ) 13
  • 14. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Spectral Graph Convolutions (Defferrad at el., 2016) • Graph Convolution ( , ) • K K • : • 14
  • 15. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Layer-Wise Linear Model (Contribution) • K=1 … • k k • • Renormalization Trick ( ) • Input C, F … • 15
  • 16. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Semi-Supervised Node Classification • Forward Model ( ) • Cross-Entropy: 16
  • 17. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Experiments (Dataset) • (Citeseer, Cora, Pubmed) • Sparse bag-of-words feature vectors for each document • a list of citation links between documents • (NELL) • A set of entities connected with directed, labeled edges • Random Graph • A dataset with N nodes we create a random graph assigning 2N edges uniformly at random 17
  • 18. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Experiments (Setup) • • 2 GCN • • Prediction Accuracy • 1000 • • 500 • Dropout rate, L2 regularization factor, Number of hidden units • Cora Citeseer Pubmed 18
  • 19. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Experiments (Baseline) • Baseline • Label Propagation (LP) • Semi-supervised embedding (SemiEmb) • Manifold regularization (ManiReg) • Skip-gram based graph embeddings (DeepWalk) • Iterative classification algorithm (ICA) • Planetoid 19
  • 20. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Results (Semi-Supervised Node Classification) • Results for all other baseline methods are taken from the Planetoid paper • Environment • The same hardware as planetoid 20 Training Dme in seconds unDl convergence
  • 21. • Compare different variants of our proposed per-layer propagation model on the citation network datasets Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Results (Evaluation Propagation Model) 21
  • 22. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Results (Training Time per Epoch) • The mean training time per epoch for 100 epochs on simulated random graphs 22
  • 23. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Experiments on Model Depth • Residual connections • 2, 3 • 7 … • residual connections • 23
  • 24. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Discussion • Keypoints • Overcome both limitations • Graph-Laplacian regularization • Edges encode mere similarity of nodes • Skip-gram based methods • Limited by the fact that they are based on a multi-step pipeline which difficult to optimize • Findings • Propagation from neighboring nodes improves classification performance • Proposed renormalized propagation model offers both improved efficiency 24
  • 25. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Future Work • Memory Requirement • Full-batch gradient descent • Grows linearly in the size of the dataset • Mini-batch stochastic gradient descent can alleviate this issue • Directed edges and edge features • Limited to undirected graph • NELL show it is possible to handle • By representing the original directed graph as an undirected bipartite graph • Limiting assumptions • Locality • dependence on the Kth-order neighborhood for a GCN with K layers • Equal importance of self-connections vs. edges to neighboring nodes 25
  • 26. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Reference • Graph Semi-Supervised Learning • Xiaojin Zhu, Zoubin Ghahramani, and John Lafferty. Semi-supervised learning using gaussian fields and harmonic functions. In International Conference on Machine Learning (ICML), volume 3, pp. 912–919, 2003. • Mikhail Belkin, Partha Niyogi, and Vikas Sindhwani. Manifold regularization: A geometric frame- work for learning from labeled and unlabeled examples. Journal of machine learning research (JMLR), 7(Nov):2399–2434, 2006. • JasonWeston,Fre ́de ́ricRatle,HosseinMobahi,andRonanCollobert. Deeplearningviasemi- supervised embedding. In Neural Networks: Tricks of the Trade, pp. 639–655. Springer, 2012. • Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S. Corrado, and Jeff Dean. Distributed repre- sentations of words and phrases and their compositionality. In Advances in neural information processing systems (NIPS), pp. 3111–3119, 2013. • Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. Deepwalk: Online learning of social repre- sentations. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 701–710. ACM, 2014. • Zhilin Yang, William Cohen, and Ruslan Salakhutdinov. Revisiting semi-supervised learning with graph embeddings. In International Conference on Machine Learning (ICML), 2016. 26
  • 27. Copyright (C) DeNA Co.,Ltd. All Rights Reserved. Reference • Dataset & Pre-Processing • Prithviraj Sen, Galileo Namata, Mustafa Bilgic, Lise Getoor, Brian Galligher, and Tina Eliassi-Rad. Collective classification in network data. AI magazine, 29(3):93, 2008. • Andrew Carlson, Justin Betteridge, Bryan Kisiel, Burr Settles, Estevam R. Hruschka Jr, and Tom M. Mitchell. Toward an architecture for never-ending language learning. In AAAI, volume 5, pp. 3, 2010. • Zhilin Yang, William Cohen, and Ruslan Salakhutdinov. Revisiting semi-supervised learning with graph embeddings. In International Conference on Machine Learning (ICML), 2016. • Website • http://tkipf.github.io/graph-convolutional-networks/ • Implementation • https://github.com/tkipf/gcn 27