SlideShare a Scribd company logo
1 of 17
Download to read offline
Joo-Ho Lee
Network Science Lab
Dept. of Artificial Intelligence
The Catholic University of Korea
E-mail: jooho414@gmail.com
1
➢ Introduction
• Limitations
• Contributions
• Background
➢ Method
• Model description
➢ Experiment
• Datasets
• Baselines
• Results
➢ Conclusion
2
1. Introduction
Limitation of previous study
• Input node features are usually Euclidean, and it is not clear how to optimally use as inputs to hyperbolic
neural networks
• It is not clear how to perform set aggregation, a key step in message passing, in hyperbolic space
• one needs to choose hyperbolic spaces with the right curvature at every layer of GCN
3
1. Introduction
Contributions
• Improved performance on graph-based tasks
→ Hyperbolic space is better suited for modeling hierarchical structures that are common in many real-
world graphs
• Interpretability
→ HGCNs can learn hierarchical representations of graph-structured data that are more interpretable
than those learned by Euclidean GCNs.
• Novelty
→ Paper introduces a hyperbolic attention-based aggregation scheme that captures hierarchical
structure of networks
4
1. Introduction
Background
• Hyperboloid manifold
ℍ𝑑,𝐾 ≔ 𝑥 ∈ ℝ𝑑+1: 𝑥, 𝑥 ℒ = −𝐾, 𝑥𝑜 > 0
𝒯
𝑥ℍ𝑑,𝐾 ≔ 𝑣 ∈ ℝ𝑑+1: 𝑣, 𝑥 ℒ = 0
𝐾: 𝑐𝑢𝑟𝑣𝑎𝑡𝑢𝑟𝑒
𝒯
𝑥ℍ𝑑,𝐾
: 𝐸𝑢𝑐𝑙𝑖𝑑𝑒𝑎𝑛 𝑇𝑎𝑛𝑔𝑒𝑛𝑡 𝑆𝑝𝑎𝑐𝑒
ℍ𝑑,𝐾
: ℎ𝑦𝑝𝑒𝑟𝑏𝑜𝑙𝑜𝑖𝑑 𝑚𝑎𝑛𝑖𝑓𝑜𝑙𝑑 𝑖𝑛 𝑑 𝑑𝑖𝑚𝑒𝑛𝑠𝑖𝑜𝑛 (𝑐𝑢𝑟𝑣𝑎𝑡𝑢𝑟𝑒: −
1
𝐾
)
5
1. Introduction
Background
• Distance
𝑑ℒ
𝐾
𝑥, 𝑦 = 𝐾𝑎𝑟𝑐𝑜𝑠ℎ −
𝑥, 𝑦 ℒ
𝐾
• Exponential and logarithmic maps: for mapping between tangent space and hyperbolic space
exp𝑥
𝐾 𝑣 = cosh
𝑣 2
𝐾
+ 𝐾 sinh
𝑣 ℒ
𝐾
𝑣
𝑣 ℒ
log𝑥
𝐾 𝑦 = 𝑑ℒ
𝐾
𝑥, 𝑦
𝑦 +
1
𝑘
𝑥, 𝑦 ℒ𝑥
𝑦 +
1
𝑘
𝑥, 𝑦 ℒ𝑥
ℒ
6
2. Method
Mapping from Euclidean to hyperbolic spaces
𝑥0,𝐻
= exp𝑜
𝐾
0, 𝑥0,𝐸
= 𝐾 cosh
𝑥0,𝐸
2
𝐾
, 𝐾 sinh
𝑥0,𝐸
2
𝐾
𝑥0,𝐸
𝑥0,𝐸
2
0, 𝑥0,𝐸
: 𝑎 𝑝𝑜𝑖𝑛𝑡 𝑖𝑛 𝑡ℎ𝑒 𝑡𝑎𝑛𝑔𝑒𝑛𝑡 𝑠𝑝𝑎𝑐𝑒 𝑜𝑓 𝑡ℎ𝑒 𝑜𝑟𝑖𝑔𝑖𝑛 𝑝𝑜𝑖𝑛𝑡 0 𝑖𝑛 ℎ𝑦𝑝𝑒𝑟𝑏𝑜𝑙𝑖𝑐 𝑠𝑝𝑎𝑐𝑒
Feature transform in hyperbolic space: Linear Transforms
𝑊⨂𝐾𝑥𝐻 ≔ exp𝑜
𝐾 𝑊𝑙𝑜𝑔𝑜
𝐾 𝑥𝐻
𝑥𝐻⨁𝐾𝑏 ≔ exp𝑥𝐻
𝐾
𝑃𝑜→𝑥𝐻
𝐾
𝑏
7
2. Method
Neighborhood aggregation on the hyperboloid manifold
𝑤𝑖𝑗 = 𝑆𝑂𝐹𝑇𝑀𝐴𝑋𝑗∈𝒩 𝑖 (𝑀𝐿𝑃(𝑊𝑙𝑜𝑔𝑜
𝐾
𝑥𝑖
𝐻
||𝑊𝑙𝑜𝑔𝑜
𝐾
𝑥𝑗
𝐻
))
𝐴𝐺𝐺𝐾
𝑥𝐻
𝑖 = exp𝑥𝑖
𝐻
𝐾
෍
𝑗∈𝒩 𝑖
𝑤𝑖𝑗𝑙𝑜𝑔𝑥𝑖
𝐻
𝐾
𝑥𝑗
𝐻
𝜎⨂ 𝐾𝑙−1,𝐾𝑙 = exp𝑜
𝐾𝑙
𝜎 log𝑜
𝐾𝑙−1
𝑥𝐻
8
2. Method
HGCN architecture
ℎ𝑖
𝑙,𝐻
= 𝑊𝑙
⨂𝐾𝑙−1𝑥𝑖
𝑙−1,𝐻
⨁𝐾𝑙−1𝑏𝑙
(ℎ𝑦𝑝𝑒𝑟𝑏𝑜𝑙𝑖𝑐 𝑓𝑒𝑎𝑡𝑢𝑟𝑒 𝑡𝑟𝑎𝑛𝑠𝑓𝑜𝑟𝑚𝑠)
𝑦𝑖
𝑙,𝐻
= 𝐴𝐺𝐺𝐾𝑙−1 ℎ𝑙,𝐻
𝑖
(𝑎𝑡𝑡𝑒𝑛𝑡𝑖𝑜𝑛 − 𝑏𝑎𝑠𝑒𝑑 𝑛𝑒𝑖𝑔ℎ𝑏𝑜𝑟ℎ𝑜𝑜𝑑 𝑎𝑔𝑔𝑟𝑒𝑔𝑎𝑡𝑖𝑜𝑛)
𝑥𝑖
𝑙,𝐻
= 𝜎⨂𝐾𝑙−1,𝐾𝑙
𝑦𝑖
𝑙,𝐻
(𝑛𝑜𝑛 − 𝑙𝑖𝑛𝑒𝑎𝑟 𝑎𝑐𝑡𝑖𝑣𝑎𝑡𝑖𝑜𝑛 𝑤𝑖𝑡ℎ 𝑑𝑖𝑓𝑓𝑒𝑟𝑛𝑒𝑡 𝑐𝑢𝑟𝑣𝑎𝑡𝑢𝑟𝑒𝑠)
9
3. Experiment
• Datasets
1. Citation Networks
2. Disease propagation tree
3. Protein-protein interactions (PPI) networks
4. Flight networks
Experimental Setup
10
3. Experiment
• Baselines
1. Euclidean embeddings (EUC)
2. Poincare embeddings (HYP)
3. EUC-MIXED & HYP-MIXED
4. GCN
5. GraphSAGE (SAGE)
6. Graph Attention Networks (GAT)
7. Simplified Graph Convolution (SGC)
8. MLP and its hyperbolic variant (HNN)
Experimental Setup
11
3. Experiment
Link Prediction & Node Classification (LP, NC)
12
3. Experiment
Trainable Curvature
13
3. Experiment
ROC AUC for link prediction
14
3. Experiment
Visualization (DISEASE-M dataset)
• In HGCN, the center node pays more attention to its (grand)parent.
• In contrast to Euclidean GAT, our aggregation with attention in hyperbolic space allows to pay more
attention to nodes with high hierarchy
→ such attention is crucial to good performance in disease, because only sick parents will propagate the
disease to their children
15
4. Conclusions
• HGCN is a novel architecture that learns hyperbolic embeddings using graph convolution networks.
• In HGCN, the Euclidean input features are successively mapped to embeddings in hyperbolic
spaces with trainable curvatures at every layer
• HGCN achieves new state-of-the-art in learning embeddings for real-world hierarchical and scale-
free graphs
16
Q&A

More Related Content

Similar to NS-CUK Seminar: J.H.Lee, Review on "Hyperbolic graph convolutional neural networks," Advances in neural information processing systems 2019

H.B.Kim, Review on "DeeperGCN: ALL You Need to Train Deeper GCN", arXiv e-pri...
H.B.Kim, Review on "DeeperGCN: ALL You Need to Train Deeper GCN", arXiv e-pri...H.B.Kim, Review on "DeeperGCN: ALL You Need to Train Deeper GCN", arXiv e-pri...
H.B.Kim, Review on "DeeperGCN: ALL You Need to Train Deeper GCN", arXiv e-pri...ssuser2624f71
 
Multi-scale visual analysis of time-varying ECoG data via clustering of brain...
Multi-scale visual analysis of time-varying ECoG data via clustering of brain...Multi-scale visual analysis of time-varying ECoG data via clustering of brain...
Multi-scale visual analysis of time-varying ECoG data via clustering of brain...Sugeerth Murugesan
 
Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks, arXiv e-...
Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks, arXiv e-...Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks, arXiv e-...
Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks, arXiv e-...ssuser2624f71
 
NS-CUK Journal club: HBKim, Review on "Neural Graph Collaborative Filtering",...
NS-CUK Journal club: HBKim, Review on "Neural Graph Collaborative Filtering",...NS-CUK Journal club: HBKim, Review on "Neural Graph Collaborative Filtering",...
NS-CUK Journal club: HBKim, Review on "Neural Graph Collaborative Filtering",...ssuser4b1f48
 
NS-CUK Seminar: S.T.Nguyen, Review on "Improving Graph Neural Network Express...
NS-CUK Seminar: S.T.Nguyen, Review on "Improving Graph Neural Network Express...NS-CUK Seminar: S.T.Nguyen, Review on "Improving Graph Neural Network Express...
NS-CUK Seminar: S.T.Nguyen, Review on "Improving Graph Neural Network Express...ssuser4b1f48
 
NS-CUK Seminar: H.B.Kim, Review on "Inductive Representation Learning on Lar...
NS-CUK Seminar: H.B.Kim,  Review on "Inductive Representation Learning on Lar...NS-CUK Seminar: H.B.Kim,  Review on "Inductive Representation Learning on Lar...
NS-CUK Seminar: H.B.Kim, Review on "Inductive Representation Learning on Lar...ssuser4b1f48
 
NS-CUK Seminar: J.H.Lee, Review on "Self-supervised Heterogeneous Graph Pre-...
NS-CUK Seminar: J.H.Lee,  Review on "Self-supervised Heterogeneous Graph Pre-...NS-CUK Seminar: J.H.Lee,  Review on "Self-supervised Heterogeneous Graph Pre-...
NS-CUK Seminar: J.H.Lee, Review on "Self-supervised Heterogeneous Graph Pre-...ssuser4b1f48
 
Deep learning lecture - part 1 (basics, CNN)
Deep learning lecture - part 1 (basics, CNN)Deep learning lecture - part 1 (basics, CNN)
Deep learning lecture - part 1 (basics, CNN)SungminYou
 
NS-CUK Journal club: H.E.Lee, Review on "Predicting Biomedical Interactions W...
NS-CUK Journal club: H.E.Lee, Review on "Predicting Biomedical Interactions W...NS-CUK Journal club: H.E.Lee, Review on "Predicting Biomedical Interactions W...
NS-CUK Journal club: H.E.Lee, Review on "Predicting Biomedical Interactions W...ssuser4b1f48
 
NS-CUK Journal club: H.E.Lee, Review on "Predicting Biomedical Interactions W...
NS-CUK Journal club: H.E.Lee, Review on "Predicting Biomedical Interactions W...NS-CUK Journal club: H.E.Lee, Review on "Predicting Biomedical Interactions W...
NS-CUK Journal club: H.E.Lee, Review on "Predicting Biomedical Interactions W...ssuser4b1f48
 
Unified Framework for Learning Representation from EEG Data
Unified Framework for Learning Representation from EEG DataUnified Framework for Learning Representation from EEG Data
Unified Framework for Learning Representation from EEG DataFedEx Institute of Technology
 
How To Find Your Friendly Neighborhood: Graph Attention Design With Self-Supe...
How To Find Your Friendly Neighborhood: Graph Attention Design With Self-Supe...How To Find Your Friendly Neighborhood: Graph Attention Design With Self-Supe...
How To Find Your Friendly Neighborhood: Graph Attention Design With Self-Supe...ssuser2624f71
 
Data driven model optimization [autosaved]
Data driven model optimization [autosaved]Data driven model optimization [autosaved]
Data driven model optimization [autosaved]Russell Jarvis
 
Feed forward back propogation algorithm .pptx
Feed forward back propogation algorithm .pptxFeed forward back propogation algorithm .pptx
Feed forward back propogation algorithm .pptxneelamsanjeevkumar
 
Scaling up genomic analysis with ADAM
Scaling up genomic analysis with ADAMScaling up genomic analysis with ADAM
Scaling up genomic analysis with ADAMfnothaft
 
Adversarial Reinforced Learning for Unsupervised Domain Adaptation
Adversarial Reinforced Learning for Unsupervised Domain AdaptationAdversarial Reinforced Learning for Unsupervised Domain Adaptation
Adversarial Reinforced Learning for Unsupervised Domain Adaptationtaeseon ryu
 
An efficient fuzzy classifier with feature selection based
An efficient fuzzy classifier with feature selection basedAn efficient fuzzy classifier with feature selection based
An efficient fuzzy classifier with feature selection basedssairayousaf
 

Similar to NS-CUK Seminar: J.H.Lee, Review on "Hyperbolic graph convolutional neural networks," Advances in neural information processing systems 2019 (20)

H.B.Kim, Review on "DeeperGCN: ALL You Need to Train Deeper GCN", arXiv e-pri...
H.B.Kim, Review on "DeeperGCN: ALL You Need to Train Deeper GCN", arXiv e-pri...H.B.Kim, Review on "DeeperGCN: ALL You Need to Train Deeper GCN", arXiv e-pri...
H.B.Kim, Review on "DeeperGCN: ALL You Need to Train Deeper GCN", arXiv e-pri...
 
Multi-scale visual analysis of time-varying ECoG data via clustering of brain...
Multi-scale visual analysis of time-varying ECoG data via clustering of brain...Multi-scale visual analysis of time-varying ECoG data via clustering of brain...
Multi-scale visual analysis of time-varying ECoG data via clustering of brain...
 
Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks, arXiv e-...
Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks, arXiv e-...Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks, arXiv e-...
Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks, arXiv e-...
 
NS-CUK Journal club: HBKim, Review on "Neural Graph Collaborative Filtering",...
NS-CUK Journal club: HBKim, Review on "Neural Graph Collaborative Filtering",...NS-CUK Journal club: HBKim, Review on "Neural Graph Collaborative Filtering",...
NS-CUK Journal club: HBKim, Review on "Neural Graph Collaborative Filtering",...
 
NS-CUK Seminar: S.T.Nguyen, Review on "Improving Graph Neural Network Express...
NS-CUK Seminar: S.T.Nguyen, Review on "Improving Graph Neural Network Express...NS-CUK Seminar: S.T.Nguyen, Review on "Improving Graph Neural Network Express...
NS-CUK Seminar: S.T.Nguyen, Review on "Improving Graph Neural Network Express...
 
NS-CUK Seminar: H.B.Kim, Review on "Inductive Representation Learning on Lar...
NS-CUK Seminar: H.B.Kim,  Review on "Inductive Representation Learning on Lar...NS-CUK Seminar: H.B.Kim,  Review on "Inductive Representation Learning on Lar...
NS-CUK Seminar: H.B.Kim, Review on "Inductive Representation Learning on Lar...
 
NS-CUK Seminar: J.H.Lee, Review on "Self-supervised Heterogeneous Graph Pre-...
NS-CUK Seminar: J.H.Lee,  Review on "Self-supervised Heterogeneous Graph Pre-...NS-CUK Seminar: J.H.Lee,  Review on "Self-supervised Heterogeneous Graph Pre-...
NS-CUK Seminar: J.H.Lee, Review on "Self-supervised Heterogeneous Graph Pre-...
 
Deep learning lecture - part 1 (basics, CNN)
Deep learning lecture - part 1 (basics, CNN)Deep learning lecture - part 1 (basics, CNN)
Deep learning lecture - part 1 (basics, CNN)
 
NS-CUK Journal club: H.E.Lee, Review on "Predicting Biomedical Interactions W...
NS-CUK Journal club: H.E.Lee, Review on "Predicting Biomedical Interactions W...NS-CUK Journal club: H.E.Lee, Review on "Predicting Biomedical Interactions W...
NS-CUK Journal club: H.E.Lee, Review on "Predicting Biomedical Interactions W...
 
NS-CUK Journal club: H.E.Lee, Review on "Predicting Biomedical Interactions W...
NS-CUK Journal club: H.E.Lee, Review on "Predicting Biomedical Interactions W...NS-CUK Journal club: H.E.Lee, Review on "Predicting Biomedical Interactions W...
NS-CUK Journal club: H.E.Lee, Review on "Predicting Biomedical Interactions W...
 
Yeasin
YeasinYeasin
Yeasin
 
Unified Framework for Learning Representation from EEG Data
Unified Framework for Learning Representation from EEG DataUnified Framework for Learning Representation from EEG Data
Unified Framework for Learning Representation from EEG Data
 
How To Find Your Friendly Neighborhood: Graph Attention Design With Self-Supe...
How To Find Your Friendly Neighborhood: Graph Attention Design With Self-Supe...How To Find Your Friendly Neighborhood: Graph Attention Design With Self-Supe...
How To Find Your Friendly Neighborhood: Graph Attention Design With Self-Supe...
 
Data driven model optimization [autosaved]
Data driven model optimization [autosaved]Data driven model optimization [autosaved]
Data driven model optimization [autosaved]
 
Feed forward back propogation algorithm .pptx
Feed forward back propogation algorithm .pptxFeed forward back propogation algorithm .pptx
Feed forward back propogation algorithm .pptx
 
Complex system
Complex systemComplex system
Complex system
 
Scaling up genomic analysis with ADAM
Scaling up genomic analysis with ADAMScaling up genomic analysis with ADAM
Scaling up genomic analysis with ADAM
 
Adversarial Reinforced Learning for Unsupervised Domain Adaptation
Adversarial Reinforced Learning for Unsupervised Domain AdaptationAdversarial Reinforced Learning for Unsupervised Domain Adaptation
Adversarial Reinforced Learning for Unsupervised Domain Adaptation
 
An efficient fuzzy classifier with feature selection based
An efficient fuzzy classifier with feature selection basedAn efficient fuzzy classifier with feature selection based
An efficient fuzzy classifier with feature selection based
 
Alignment Approaches II: Long Reads
Alignment Approaches II: Long ReadsAlignment Approaches II: Long Reads
Alignment Approaches II: Long Reads
 

More from Network Science Lab, The Catholic University of Korea

More from Network Science Lab, The Catholic University of Korea (20)

S.M.Lee, Invited Talk on "Machine Learning-based Anomaly Detection"
S.M.Lee, Invited Talk on "Machine Learning-based Anomaly Detection"S.M.Lee, Invited Talk on "Machine Learning-based Anomaly Detection"
S.M.Lee, Invited Talk on "Machine Learning-based Anomaly Detection"
 
230724_Thuy_Labseminar.pptx
230724_Thuy_Labseminar.pptx230724_Thuy_Labseminar.pptx
230724_Thuy_Labseminar.pptx
 
230724-JH-Lab Seminar.pptx
230724-JH-Lab Seminar.pptx230724-JH-Lab Seminar.pptx
230724-JH-Lab Seminar.pptx
 
5강 - 멀티모달 및 모듈화.pptx
5강 - 멀티모달 및 모듈화.pptx5강 - 멀티모달 및 모듈화.pptx
5강 - 멀티모달 및 모듈화.pptx
 
3강 - CNN 및 이미지 모델.pptx
3강 - CNN 및 이미지 모델.pptx3강 - CNN 및 이미지 모델.pptx
3강 - CNN 및 이미지 모델.pptx
 
4강 - RNN 및 시계열 모델.pptx
4강 - RNN 및 시계열 모델.pptx4강 - RNN 및 시계열 모델.pptx
4강 - RNN 및 시계열 모델.pptx
 
2강 - 실험 흐름과 멀티모달 개요.pptx
2강 - 실험 흐름과 멀티모달 개요.pptx2강 - 실험 흐름과 멀티모달 개요.pptx
2강 - 실험 흐름과 멀티모달 개요.pptx
 
1강 - pytorch와 tensor.pptx
1강 - pytorch와 tensor.pptx1강 - pytorch와 tensor.pptx
1강 - pytorch와 tensor.pptx
 
Technical Report on "Lecture Quality Prediction using Graph Neural Networks"
Technical Report on "Lecture Quality Prediction using Graph Neural Networks"Technical Report on "Lecture Quality Prediction using Graph Neural Networks"
Technical Report on "Lecture Quality Prediction using Graph Neural Networks"
 
Presentation for "Lecture Quality Prediction using Graph Neural Networks"
Presentation for "Lecture Quality Prediction using Graph Neural Networks"Presentation for "Lecture Quality Prediction using Graph Neural Networks"
Presentation for "Lecture Quality Prediction using Graph Neural Networks"
 
NS-CUK Seminar: J.H.Lee, Review on "Graph Neural Networks with convolutional ...
NS-CUK Seminar: J.H.Lee, Review on "Graph Neural Networks with convolutional ...NS-CUK Seminar: J.H.Lee, Review on "Graph Neural Networks with convolutional ...
NS-CUK Seminar: J.H.Lee, Review on "Graph Neural Networks with convolutional ...
 
NS-CUK Seminar: V.T.Hoang, Review on "Are More Layers Beneficial to Graph Tra...
NS-CUK Seminar: V.T.Hoang, Review on "Are More Layers Beneficial to Graph Tra...NS-CUK Seminar: V.T.Hoang, Review on "Are More Layers Beneficial to Graph Tra...
NS-CUK Seminar: V.T.Hoang, Review on "Are More Layers Beneficial to Graph Tra...
 
NS-CUK Seminar: S.T.Nguyen Review on "Accurate learning of graph representati...
NS-CUK Seminar: S.T.Nguyen Review on "Accurate learning of graph representati...NS-CUK Seminar: S.T.Nguyen Review on "Accurate learning of graph representati...
NS-CUK Seminar: S.T.Nguyen Review on "Accurate learning of graph representati...
 
Joo-Ho Lee: Topographic-aware wind forecasting system using multi-modal spati...
Joo-Ho Lee: Topographic-aware wind forecasting system using multi-modal spati...Joo-Ho Lee: Topographic-aware wind forecasting system using multi-modal spati...
Joo-Ho Lee: Topographic-aware wind forecasting system using multi-modal spati...
 
Ho-Beom Kim: Detection of Influential Unethical Expressions through Construct...
Ho-Beom Kim: Detection of Influential Unethical Expressions through Construct...Ho-Beom Kim: Detection of Influential Unethical Expressions through Construct...
Ho-Beom Kim: Detection of Influential Unethical Expressions through Construct...
 
Sang_Graphormer.pdf
Sang_Graphormer.pdfSang_Graphormer.pdf
Sang_Graphormer.pdf
 
NS-CUK Seminar: S.T.Nguyen, Review on "Do Transformers Really Perform Bad for...
NS-CUK Seminar: S.T.Nguyen, Review on "Do Transformers Really Perform Bad for...NS-CUK Seminar: S.T.Nguyen, Review on "Do Transformers Really Perform Bad for...
NS-CUK Seminar: S.T.Nguyen, Review on "Do Transformers Really Perform Bad for...
 
NS-CUK Seminar: S.T.Nguyen, Review on "DeeperGCN: All You Need to Train Deepe...
NS-CUK Seminar: S.T.Nguyen, Review on "DeeperGCN: All You Need to Train Deepe...NS-CUK Seminar: S.T.Nguyen, Review on "DeeperGCN: All You Need to Train Deepe...
NS-CUK Seminar: S.T.Nguyen, Review on "DeeperGCN: All You Need to Train Deepe...
 
NS-CUK Seminar: V.T.Hoang, Review on "Everything is Connected: Graph Neural N...
NS-CUK Seminar: V.T.Hoang, Review on "Everything is Connected: Graph Neural N...NS-CUK Seminar: V.T.Hoang, Review on "Everything is Connected: Graph Neural N...
NS-CUK Seminar: V.T.Hoang, Review on "Everything is Connected: Graph Neural N...
 
AI-CUK Joint Journal Club: V.T.Hoang, Review on "Global self-attention as a r...
AI-CUK Joint Journal Club: V.T.Hoang, Review on "Global self-attention as a r...AI-CUK Joint Journal Club: V.T.Hoang, Review on "Global self-attention as a r...
AI-CUK Joint Journal Club: V.T.Hoang, Review on "Global self-attention as a r...
 

Recently uploaded

GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksSoftradix Technologies
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphNeo4j
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonetsnaman860154
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationRidwan Fadjar
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...HostedbyConfluent
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsEnterprise Knowledge
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking MenDelhi Call girls
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationRadu Cotescu
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersThousandEyes
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitecturePixlogix Infotech
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Alan Dix
 

Recently uploaded (20)

GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other Frameworks
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 Presentation
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC Architecture
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping Elbows
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
 

NS-CUK Seminar: J.H.Lee, Review on "Hyperbolic graph convolutional neural networks," Advances in neural information processing systems 2019

  • 1. Joo-Ho Lee Network Science Lab Dept. of Artificial Intelligence The Catholic University of Korea E-mail: jooho414@gmail.com
  • 2. 1 ➢ Introduction • Limitations • Contributions • Background ➢ Method • Model description ➢ Experiment • Datasets • Baselines • Results ➢ Conclusion
  • 3. 2 1. Introduction Limitation of previous study • Input node features are usually Euclidean, and it is not clear how to optimally use as inputs to hyperbolic neural networks • It is not clear how to perform set aggregation, a key step in message passing, in hyperbolic space • one needs to choose hyperbolic spaces with the right curvature at every layer of GCN
  • 4. 3 1. Introduction Contributions • Improved performance on graph-based tasks → Hyperbolic space is better suited for modeling hierarchical structures that are common in many real- world graphs • Interpretability → HGCNs can learn hierarchical representations of graph-structured data that are more interpretable than those learned by Euclidean GCNs. • Novelty → Paper introduces a hyperbolic attention-based aggregation scheme that captures hierarchical structure of networks
  • 5. 4 1. Introduction Background • Hyperboloid manifold ℍ𝑑,𝐾 ≔ 𝑥 ∈ ℝ𝑑+1: 𝑥, 𝑥 ℒ = −𝐾, 𝑥𝑜 > 0 𝒯 𝑥ℍ𝑑,𝐾 ≔ 𝑣 ∈ ℝ𝑑+1: 𝑣, 𝑥 ℒ = 0 𝐾: 𝑐𝑢𝑟𝑣𝑎𝑡𝑢𝑟𝑒 𝒯 𝑥ℍ𝑑,𝐾 : 𝐸𝑢𝑐𝑙𝑖𝑑𝑒𝑎𝑛 𝑇𝑎𝑛𝑔𝑒𝑛𝑡 𝑆𝑝𝑎𝑐𝑒 ℍ𝑑,𝐾 : ℎ𝑦𝑝𝑒𝑟𝑏𝑜𝑙𝑜𝑖𝑑 𝑚𝑎𝑛𝑖𝑓𝑜𝑙𝑑 𝑖𝑛 𝑑 𝑑𝑖𝑚𝑒𝑛𝑠𝑖𝑜𝑛 (𝑐𝑢𝑟𝑣𝑎𝑡𝑢𝑟𝑒: − 1 𝐾 )
  • 6. 5 1. Introduction Background • Distance 𝑑ℒ 𝐾 𝑥, 𝑦 = 𝐾𝑎𝑟𝑐𝑜𝑠ℎ − 𝑥, 𝑦 ℒ 𝐾 • Exponential and logarithmic maps: for mapping between tangent space and hyperbolic space exp𝑥 𝐾 𝑣 = cosh 𝑣 2 𝐾 + 𝐾 sinh 𝑣 ℒ 𝐾 𝑣 𝑣 ℒ log𝑥 𝐾 𝑦 = 𝑑ℒ 𝐾 𝑥, 𝑦 𝑦 + 1 𝑘 𝑥, 𝑦 ℒ𝑥 𝑦 + 1 𝑘 𝑥, 𝑦 ℒ𝑥 ℒ
  • 7. 6 2. Method Mapping from Euclidean to hyperbolic spaces 𝑥0,𝐻 = exp𝑜 𝐾 0, 𝑥0,𝐸 = 𝐾 cosh 𝑥0,𝐸 2 𝐾 , 𝐾 sinh 𝑥0,𝐸 2 𝐾 𝑥0,𝐸 𝑥0,𝐸 2 0, 𝑥0,𝐸 : 𝑎 𝑝𝑜𝑖𝑛𝑡 𝑖𝑛 𝑡ℎ𝑒 𝑡𝑎𝑛𝑔𝑒𝑛𝑡 𝑠𝑝𝑎𝑐𝑒 𝑜𝑓 𝑡ℎ𝑒 𝑜𝑟𝑖𝑔𝑖𝑛 𝑝𝑜𝑖𝑛𝑡 0 𝑖𝑛 ℎ𝑦𝑝𝑒𝑟𝑏𝑜𝑙𝑖𝑐 𝑠𝑝𝑎𝑐𝑒 Feature transform in hyperbolic space: Linear Transforms 𝑊⨂𝐾𝑥𝐻 ≔ exp𝑜 𝐾 𝑊𝑙𝑜𝑔𝑜 𝐾 𝑥𝐻 𝑥𝐻⨁𝐾𝑏 ≔ exp𝑥𝐻 𝐾 𝑃𝑜→𝑥𝐻 𝐾 𝑏
  • 8. 7 2. Method Neighborhood aggregation on the hyperboloid manifold 𝑤𝑖𝑗 = 𝑆𝑂𝐹𝑇𝑀𝐴𝑋𝑗∈𝒩 𝑖 (𝑀𝐿𝑃(𝑊𝑙𝑜𝑔𝑜 𝐾 𝑥𝑖 𝐻 ||𝑊𝑙𝑜𝑔𝑜 𝐾 𝑥𝑗 𝐻 )) 𝐴𝐺𝐺𝐾 𝑥𝐻 𝑖 = exp𝑥𝑖 𝐻 𝐾 ෍ 𝑗∈𝒩 𝑖 𝑤𝑖𝑗𝑙𝑜𝑔𝑥𝑖 𝐻 𝐾 𝑥𝑗 𝐻 𝜎⨂ 𝐾𝑙−1,𝐾𝑙 = exp𝑜 𝐾𝑙 𝜎 log𝑜 𝐾𝑙−1 𝑥𝐻
  • 9. 8 2. Method HGCN architecture ℎ𝑖 𝑙,𝐻 = 𝑊𝑙 ⨂𝐾𝑙−1𝑥𝑖 𝑙−1,𝐻 ⨁𝐾𝑙−1𝑏𝑙 (ℎ𝑦𝑝𝑒𝑟𝑏𝑜𝑙𝑖𝑐 𝑓𝑒𝑎𝑡𝑢𝑟𝑒 𝑡𝑟𝑎𝑛𝑠𝑓𝑜𝑟𝑚𝑠) 𝑦𝑖 𝑙,𝐻 = 𝐴𝐺𝐺𝐾𝑙−1 ℎ𝑙,𝐻 𝑖 (𝑎𝑡𝑡𝑒𝑛𝑡𝑖𝑜𝑛 − 𝑏𝑎𝑠𝑒𝑑 𝑛𝑒𝑖𝑔ℎ𝑏𝑜𝑟ℎ𝑜𝑜𝑑 𝑎𝑔𝑔𝑟𝑒𝑔𝑎𝑡𝑖𝑜𝑛) 𝑥𝑖 𝑙,𝐻 = 𝜎⨂𝐾𝑙−1,𝐾𝑙 𝑦𝑖 𝑙,𝐻 (𝑛𝑜𝑛 − 𝑙𝑖𝑛𝑒𝑎𝑟 𝑎𝑐𝑡𝑖𝑣𝑎𝑡𝑖𝑜𝑛 𝑤𝑖𝑡ℎ 𝑑𝑖𝑓𝑓𝑒𝑟𝑛𝑒𝑡 𝑐𝑢𝑟𝑣𝑎𝑡𝑢𝑟𝑒𝑠)
  • 10. 9 3. Experiment • Datasets 1. Citation Networks 2. Disease propagation tree 3. Protein-protein interactions (PPI) networks 4. Flight networks Experimental Setup
  • 11. 10 3. Experiment • Baselines 1. Euclidean embeddings (EUC) 2. Poincare embeddings (HYP) 3. EUC-MIXED & HYP-MIXED 4. GCN 5. GraphSAGE (SAGE) 6. Graph Attention Networks (GAT) 7. Simplified Graph Convolution (SGC) 8. MLP and its hyperbolic variant (HNN) Experimental Setup
  • 12. 11 3. Experiment Link Prediction & Node Classification (LP, NC)
  • 14. 13 3. Experiment ROC AUC for link prediction
  • 15. 14 3. Experiment Visualization (DISEASE-M dataset) • In HGCN, the center node pays more attention to its (grand)parent. • In contrast to Euclidean GAT, our aggregation with attention in hyperbolic space allows to pay more attention to nodes with high hierarchy → such attention is crucial to good performance in disease, because only sick parents will propagate the disease to their children
  • 16. 15 4. Conclusions • HGCN is a novel architecture that learns hyperbolic embeddings using graph convolution networks. • In HGCN, the Euclidean input features are successively mapped to embeddings in hyperbolic spaces with trainable curvatures at every layer • HGCN achieves new state-of-the-art in learning embeddings for real-world hierarchical and scale- free graphs