SlideShare ist ein Scribd-Unternehmen logo
1 von 24
Attention Models in Graphs: A Survey
John B. Lee, Ryan A. Rossi, Sungchul Kim, Nesreen K. Ahmed, Eunyee Koh
Adobe Research
TKDD’2018
Contents
• Definition of basic keywords
• Overview
• Model description
• Criticisms/benefits
Definition of Basic keywords
2
Definition of Basic keywords
3
Definition of Basic keywords
4
Overview
5
• Three different taxonomies based on
 Problem setting – especially, based on
input/output format
 Type of attention
 Task/problem
Overview
6
AttentionWalks
• Input: Homogeneous graph
• Output: Node embedding
• Mechanism: Learn attention weights + Attention-guided walk
• DeepWalk + Attention
• Performance of DeepWalk is sensitive to context window size c
7
Sami Abu-El-Haija, Bryan Perozzi, Rami Al-Rfou, and Alex Alemi. 2017. Watch Your Step: Learning Graph
Embeddings Through Attention. In arXiv:1710.09599v1
GAKE
• Input: Homogeneous graph(knowledge graph)
• Output: Node embedding
• Mechanism: Learn attention weights
• Node context 계산 시 edge 정보도 사용
• 최종 node embedding 계산에 attention 사용
8
Jun Feng, Minlie Huang, Yang Yang, and Xiaoyan Zhu. 2016. GAKE: Graph Aware Knowledge
Embedding. In Proc. of COLING. 641–651
GAT
• Input: Homogeneous graph
• Output: Node embedding
• Mechanism: Learn attention weights
• GCN(Graph-ConvNet) + Attention
• Using multi-head attention
9Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua
Bengio. 2018. Graph Attention Networks. In Proc. of ICLR. 1–12.
AGNN
• Input: Homogeneous graph
• Output: Node embedding
• Mechanism: Similarity-based attention
• GCN + Attention
• Similar to GAT, but using cosine similarity to calculate attention
• No multi-head attention
10Kiran K. Thekumparampil, Chong Wang, Sewoong Oh, and Li-Jia Li. 2018. Attention-based Graph
Neural Network for Semi-supervised Learning. In arXiv:1803.03735v1.
PRML
• Input: Homogeneous graph
• Output: Edge embedding
• Mechanism: Learn attention weights
• Path-based feature learning 이후에
 1) 각 path마다 attention(중요 노드 선정)
 2) path끼리 attention을 통해 최종 embedding 생성
11Zhou Zhao, Ben Gao, Vicent W. Zheng, Deng Cai, Xiaofei He, and Yueting Zhuang. 2017. Link
Prediction via Ranking Metric Dual-level Attention Network Learning. In Proc. of IJCAI. 3525–3531.
EAGCN
• Input: Heterogeneous graph
• Output: Graph embedding/Node embedding
• Mechanism: Learn attention weights
• GCN + Attention
• Multi attention to handle heterogeneous graph
12Chao Shang, Qinqing Liu, Ko-Shin Chen, Jiangwen Sun, Jin Lu, Jinfeng Yi, and Jinbo Bi. 2018. Edge
Attention-based Multi-Relational Graph Convolutional Networks. In arXiv:1802.04944v1.
Modified-GAT
• Input: Homogeneous graph
• Output: Graph embedding
• Mechanism: Similarity-based attention
• GAT+FCN, attention 계산이 약간 변함
• GAT를 통해 만들어진 Node embedding을 FCN을 통해 graph embedding
으로 변환
13Seongok Ryu, Jaechang Lim, and Woo Youn Kim. 2018. Deeply learning molecular structure-
property relationships using graph attention neural network. In arXiv:1805.10988v2.
graph2seq
• Input: Homogeneous graph
• Output: Graph embedding
• Mechanism: Similarity-based attention
• In node embedding, they consider both forward/backward neighbor
• In attention, they use node embedding
14Kun Xu, Lingfei Wu, Zhiguo Wang, Yansong Feng, Michael Witbrock, and Vadim Sheinin. 2018. Graph2Seq:
Graph to Sequence Learning with Attention-based Neural Networks. In arXiv:1804.00823v3.
GAM
• Input: Homogeneous graph
• Output: Graph embedding
• Mechanism: Learn attention weights + Attention-guided walk
• Use RNN in attention-guided walk
• Use multi agent
15John Boaz Lee, Ryan Rossi, and Xiangnan Kong. 2018. Graph Classification using Structural Attention. In Proc. of
KDD. 1–9.
RNNSearch, Att-NMT
• Input: Path
• Output: Graph embedding
• Mechanism: Similarity-based attention
• Use hidden as embedding, calculate attention on every hidden, with
similarity between target hidden and hiddens
• In Att-NMT, there are local attention
16
Dzmitry Bahdanau, KyungHyun Cho, and Yoshua Bengio. 2015. Neural Machine
Translation by Jointly Learning to Align and Translate. In Proc. of ICLR. 1–15
Thang Luong, Hieu Pham, and Christopher D. Manning. 2015. Effective Approaches to
Attention-based Neural Machine Translation. In Proc. of EMNLP. 1412–1421.
Hao Zhou, Tom Yang, Minlie Huang, Haizhou Zhao, Jingfang Xu, and Xiaoyan Zhu. 2018. Commonsense
Knowledge Aware Conversation Generation with Graph Attention. In Proc. of IJCAI-ECAI. 1–7
CCM
• Input: Homogeneous Graph
• Output: Graph embedding/Hybrid embedding
• Mechanism: Learn attention weights
• Get input sequence and knowledge graph
• Use two graph attention/one seq2seq attention
15
JointD/E+SATT
• Input: Homogeneous graph
• Output: Hybrid embedding
• Mechanism: Similarity-based attention
15Xu Han, Zhiyuan Liu, and Maosong Sun. 2018. Neural Knowledge Acquisition via Mutual Attention Between
Knowledge Graph and Text. In Proc. of AAAI. 1–8
GRAM
• Input: Directed acyclic graph
• Output: Hybrid embedding
• Mechanism: Learn attention weights
• DAG의 ancestor node를 모두 사용해서 attention
15Edward Choi, Mohammad Taha Bahadori, Le Song, Walter F. Stewart, and Jimeng Sun. 2017. GRAM: Graph-
based Attention Model for Healthcare Representation Learning. In Proc. of KDD. 787–795
Criticisms
• Embedding을 나누는 기준이 모호함
• Input을 Homogeneous 등을 나누려는 시도는 좋았으나, survey한 논문
이 special case와 Homogeneous밖에 없음
• Problem setting기준 구분에서 전체 모델 소개가 끝나고,
mechanism/task기준 구분에 내용이 없음  Taxonomy 자체가 필요한
지를 잘 모르겠음
15
Criticisms
• Embedding을 나누는 기준이 모호함
• Input을 Homogeneous 등을 나누려는 시도는 좋았으나, survey한 논문
이 special case와 Homogeneous밖에 없음
• Problem setting기준 구분에서 전체 모델 소개가 끝나고,
mechanism/task기준 구분에 내용이 없음  Taxonomy 자체가 필요한
지를 잘 모르겠음
15
Benefits
• Trajectory data 다룰 때 CCM은 써볼 수 있을 듯함
• Cora dataset을 사용한 논문(e.g. GAT)은 현재 진행중인 task에 도움이 될
듯  다시 읽어볼 듯
15
Thanks You
Any Questions?

Weitere ähnliche Inhalte

Ähnlich wie [0114]hyun wook

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
 
Novel Graph Modeling Framework for Feature Importance Determination in Unsupe...
Novel Graph Modeling Framework for Feature Importance Determination in Unsupe...Novel Graph Modeling Framework for Feature Importance Determination in Unsupe...
Novel Graph Modeling Framework for Feature Importance Determination in Unsupe...Neo4j
 
Sun_MAPL_GNN.pptx
Sun_MAPL_GNN.pptxSun_MAPL_GNN.pptx
Sun_MAPL_GNN.pptxssuser1760c0
 
Graph Attention Networks.pptx
Graph Attention Networks.pptxGraph Attention Networks.pptx
Graph Attention Networks.pptxssuser2624f71
 
Machine learning with graph
Machine learning with graphMachine learning with graph
Machine learning with graphDing Li
 
A New Algorithm Model for Massive-Scale Streaming Graph Analysis
A New Algorithm Model for Massive-Scale Streaming Graph AnalysisA New Algorithm Model for Massive-Scale Streaming Graph Analysis
A New Algorithm Model for Massive-Scale Streaming Graph AnalysisJason Riedy
 
[20240318_LabSeminar_Huy]GSTNet: Global Spatial-Temporal Network for Traffic ...
[20240318_LabSeminar_Huy]GSTNet: Global Spatial-Temporal Network for Traffic ...[20240318_LabSeminar_Huy]GSTNet: Global Spatial-Temporal Network for Traffic ...
[20240318_LabSeminar_Huy]GSTNet: Global Spatial-Temporal Network for Traffic ...thanhdowork
 
Deep learning 1.0 and Beyond, Part 1
Deep learning 1.0 and Beyond, Part 1Deep learning 1.0 and Beyond, Part 1
Deep learning 1.0 and Beyond, Part 1Deakin University
 
Using technology to support mathematics education and research
Using technology to support mathematics education and researchUsing technology to support mathematics education and research
Using technology to support mathematics education and research Christian Bokhove
 
INTERNSHIP presentation on machiine learning
INTERNSHIP presentation  on machiine learningINTERNSHIP presentation  on machiine learning
INTERNSHIP presentation on machiine learningrushikeshgarkal23ve
 
From deep learning to deep reasoning
From deep learning to deep reasoningFrom deep learning to deep reasoning
From deep learning to deep reasoningDeakin University
 
240401_Thuy_Labseminar[Train Once and Explain Everywhere: Pre-training Interp...
240401_Thuy_Labseminar[Train Once and Explain Everywhere: Pre-training Interp...240401_Thuy_Labseminar[Train Once and Explain Everywhere: Pre-training Interp...
240401_Thuy_Labseminar[Train Once and Explain Everywhere: Pre-training Interp...thanhdowork
 
Graph convolutional neural networks for web-scale recommender systems.pptx
Graph convolutional neural networks for web-scale recommender systems.pptxGraph convolutional neural networks for web-scale recommender systems.pptx
Graph convolutional neural networks for web-scale recommender systems.pptxssuser2624f71
 
NS-CUK Seminar: H.B.Kim, Review on "Sequential Recommendation with Graph Neu...
NS-CUK Seminar: H.B.Kim,  Review on "Sequential Recommendation with Graph Neu...NS-CUK Seminar: H.B.Kim,  Review on "Sequential Recommendation with Graph Neu...
NS-CUK Seminar: H.B.Kim, Review on "Sequential Recommendation with Graph Neu...ssuser4b1f48
 
NS-CUK Seminar: J.H.Lee, Review on "GCC: Graph Contrastive Coding for Graph ...
NS-CUK Seminar: J.H.Lee,  Review on "GCC: Graph Contrastive Coding for Graph ...NS-CUK Seminar: J.H.Lee,  Review on "GCC: Graph Contrastive Coding for Graph ...
NS-CUK Seminar: J.H.Lee, Review on "GCC: Graph Contrastive Coding for Graph ...ssuser4b1f48
 
AI, Knowledge Representation and Graph Databases -
 Key Trends in Data Science
AI, Knowledge Representation and Graph Databases -
 Key Trends in Data ScienceAI, Knowledge Representation and Graph Databases -
 Key Trends in Data Science
AI, Knowledge Representation and Graph Databases -
 Key Trends in Data ScienceOptum
 
20191107 deeplearningapproachesfornetworks
20191107 deeplearningapproachesfornetworks20191107 deeplearningapproachesfornetworks
20191107 deeplearningapproachesfornetworkstm1966
 

Ähnlich wie [0114]hyun wook (20)

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...
 
Novel Graph Modeling Framework for Feature Importance Determination in Unsupe...
Novel Graph Modeling Framework for Feature Importance Determination in Unsupe...Novel Graph Modeling Framework for Feature Importance Determination in Unsupe...
Novel Graph Modeling Framework for Feature Importance Determination in Unsupe...
 
Sun_MAPL_GNN.pptx
Sun_MAPL_GNN.pptxSun_MAPL_GNN.pptx
Sun_MAPL_GNN.pptx
 
Graph Attention Networks.pptx
Graph Attention Networks.pptxGraph Attention Networks.pptx
Graph Attention Networks.pptx
 
Machine learning with graph
Machine learning with graphMachine learning with graph
Machine learning with graph
 
Cikm 2018
Cikm 2018Cikm 2018
Cikm 2018
 
A New Algorithm Model for Massive-Scale Streaming Graph Analysis
A New Algorithm Model for Massive-Scale Streaming Graph AnalysisA New Algorithm Model for Massive-Scale Streaming Graph Analysis
A New Algorithm Model for Massive-Scale Streaming Graph Analysis
 
[20240318_LabSeminar_Huy]GSTNet: Global Spatial-Temporal Network for Traffic ...
[20240318_LabSeminar_Huy]GSTNet: Global Spatial-Temporal Network for Traffic ...[20240318_LabSeminar_Huy]GSTNet: Global Spatial-Temporal Network for Traffic ...
[20240318_LabSeminar_Huy]GSTNet: Global Spatial-Temporal Network for Traffic ...
 
Deep learning 1.0 and Beyond, Part 1
Deep learning 1.0 and Beyond, Part 1Deep learning 1.0 and Beyond, Part 1
Deep learning 1.0 and Beyond, Part 1
 
A Benchmark of PDF Information Extraction Tools using a Multi-Task and Multi-...
A Benchmark of PDF Information Extraction Tools using a Multi-Task and Multi-...A Benchmark of PDF Information Extraction Tools using a Multi-Task and Multi-...
A Benchmark of PDF Information Extraction Tools using a Multi-Task and Multi-...
 
Using technology to support mathematics education and research
Using technology to support mathematics education and researchUsing technology to support mathematics education and research
Using technology to support mathematics education and research
 
Chapter 3.pptx
Chapter 3.pptxChapter 3.pptx
Chapter 3.pptx
 
INTERNSHIP presentation on machiine learning
INTERNSHIP presentation  on machiine learningINTERNSHIP presentation  on machiine learning
INTERNSHIP presentation on machiine learning
 
From deep learning to deep reasoning
From deep learning to deep reasoningFrom deep learning to deep reasoning
From deep learning to deep reasoning
 
240401_Thuy_Labseminar[Train Once and Explain Everywhere: Pre-training Interp...
240401_Thuy_Labseminar[Train Once and Explain Everywhere: Pre-training Interp...240401_Thuy_Labseminar[Train Once and Explain Everywhere: Pre-training Interp...
240401_Thuy_Labseminar[Train Once and Explain Everywhere: Pre-training Interp...
 
Graph convolutional neural networks for web-scale recommender systems.pptx
Graph convolutional neural networks for web-scale recommender systems.pptxGraph convolutional neural networks for web-scale recommender systems.pptx
Graph convolutional neural networks for web-scale recommender systems.pptx
 
NS-CUK Seminar: H.B.Kim, Review on "Sequential Recommendation with Graph Neu...
NS-CUK Seminar: H.B.Kim,  Review on "Sequential Recommendation with Graph Neu...NS-CUK Seminar: H.B.Kim,  Review on "Sequential Recommendation with Graph Neu...
NS-CUK Seminar: H.B.Kim, Review on "Sequential Recommendation with Graph Neu...
 
NS-CUK Seminar: J.H.Lee, Review on "GCC: Graph Contrastive Coding for Graph ...
NS-CUK Seminar: J.H.Lee,  Review on "GCC: Graph Contrastive Coding for Graph ...NS-CUK Seminar: J.H.Lee,  Review on "GCC: Graph Contrastive Coding for Graph ...
NS-CUK Seminar: J.H.Lee, Review on "GCC: Graph Contrastive Coding for Graph ...
 
AI, Knowledge Representation and Graph Databases -
 Key Trends in Data Science
AI, Knowledge Representation and Graph Databases -
 Key Trends in Data ScienceAI, Knowledge Representation and Graph Databases -
 Key Trends in Data Science
AI, Knowledge Representation and Graph Databases -
 Key Trends in Data Science
 
20191107 deeplearningapproachesfornetworks
20191107 deeplearningapproachesfornetworks20191107 deeplearningapproachesfornetworks
20191107 deeplearningapproachesfornetworks
 

Mehr von ivaderivader

Argument Mining
Argument MiningArgument Mining
Argument Miningivaderivader
 
Papers at CHI23
Papers at CHI23Papers at CHI23
Papers at CHI23ivaderivader
 
DDGK: Learning Graph Representations for Deep Divergence Graph Kernels
DDGK: Learning Graph Representations for Deep Divergence Graph KernelsDDGK: Learning Graph Representations for Deep Divergence Graph Kernels
DDGK: Learning Graph Representations for Deep Divergence Graph Kernelsivaderivader
 
So Predictable! Continuous 3D Hand Trajectory Prediction in Virtual Reality
So Predictable! Continuous 3D Hand Trajectory Prediction in Virtual Reality So Predictable! Continuous 3D Hand Trajectory Prediction in Virtual Reality
So Predictable! Continuous 3D Hand Trajectory Prediction in Virtual Reality ivaderivader
 
Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...
Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...
Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...ivaderivader
 
Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...
Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...
Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...ivaderivader
 
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Orien...
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Orien...Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Orien...
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Orien...ivaderivader
 
A Style-Based Generator Architecture for Generative Adversarial Networks
A Style-Based Generator Architecture for Generative Adversarial NetworksA Style-Based Generator Architecture for Generative Adversarial Networks
A Style-Based Generator Architecture for Generative Adversarial Networksivaderivader
 
CatchLIve: Real-time Summarization of Live Streams with Stream Content and In...
CatchLIve: Real-time Summarization of Live Streams with Stream Content and In...CatchLIve: Real-time Summarization of Live Streams with Stream Content and In...
CatchLIve: Real-time Summarization of Live Streams with Stream Content and In...ivaderivader
 
Perception! Immersion! Empowerment! Superpowers as Inspiration for Visualization
Perception! Immersion! Empowerment! Superpowers as Inspiration for VisualizationPerception! Immersion! Empowerment! Superpowers as Inspiration for Visualization
Perception! Immersion! Empowerment! Superpowers as Inspiration for Visualizationivaderivader
 
Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic F...
Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic F...Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic F...
Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic F...ivaderivader
 
Neural Approximate Dynamic Programming for On-Demand Ride-Pooling
Neural Approximate Dynamic Programming for On-Demand Ride-PoolingNeural Approximate Dynamic Programming for On-Demand Ride-Pooling
Neural Approximate Dynamic Programming for On-Demand Ride-Poolingivaderivader
 
StoryMap: Using Social Modeling and Self-Modeling to Support Physical Activit...
StoryMap: Using Social Modeling and Self-Modeling to Support Physical Activit...StoryMap: Using Social Modeling and Self-Modeling to Support Physical Activit...
StoryMap: Using Social Modeling and Self-Modeling to Support Physical Activit...ivaderivader
 
Bad Breakdowns, Useful Seams, and Face Slapping: Analysis of VR Fails on YouTube
Bad Breakdowns, Useful Seams, and Face Slapping: Analysis of VR Fails on YouTubeBad Breakdowns, Useful Seams, and Face Slapping: Analysis of VR Fails on YouTube
Bad Breakdowns, Useful Seams, and Face Slapping: Analysis of VR Fails on YouTubeivaderivader
 
Invertible Denoising Network: A Light Solution for Real Noise Removal
Invertible Denoising Network: A Light Solution for Real Noise RemovalInvertible Denoising Network: A Light Solution for Real Noise Removal
Invertible Denoising Network: A Light Solution for Real Noise Removalivaderivader
 
Traffic Demand Prediction Based Dynamic Transition Convolutional Neural Network
Traffic Demand Prediction Based Dynamic Transition Convolutional Neural NetworkTraffic Demand Prediction Based Dynamic Transition Convolutional Neural Network
Traffic Demand Prediction Based Dynamic Transition Convolutional Neural Networkivaderivader
 
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training  MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training ivaderivader
 
Screen2Vec: Semantic Embedding of GUI Screens and GUI Components
Screen2Vec: Semantic Embedding of GUI Screens and GUI ComponentsScreen2Vec: Semantic Embedding of GUI Screens and GUI Components
Screen2Vec: Semantic Embedding of GUI Screens and GUI Componentsivaderivader
 
Augmenting Decisions of Taxi Drivers through Reinforcement Learning for Impro...
Augmenting Decisions of Taxi Drivers through Reinforcement Learning for Impro...Augmenting Decisions of Taxi Drivers through Reinforcement Learning for Impro...
Augmenting Decisions of Taxi Drivers through Reinforcement Learning for Impro...ivaderivader
 
Natural Language to Visualization by Neural Machine Translation
Natural Language to Visualization by Neural Machine TranslationNatural Language to Visualization by Neural Machine Translation
Natural Language to Visualization by Neural Machine Translationivaderivader
 

Mehr von ivaderivader (20)

Argument Mining
Argument MiningArgument Mining
Argument Mining
 
Papers at CHI23
Papers at CHI23Papers at CHI23
Papers at CHI23
 
DDGK: Learning Graph Representations for Deep Divergence Graph Kernels
DDGK: Learning Graph Representations for Deep Divergence Graph KernelsDDGK: Learning Graph Representations for Deep Divergence Graph Kernels
DDGK: Learning Graph Representations for Deep Divergence Graph Kernels
 
So Predictable! Continuous 3D Hand Trajectory Prediction in Virtual Reality
So Predictable! Continuous 3D Hand Trajectory Prediction in Virtual Reality So Predictable! Continuous 3D Hand Trajectory Prediction in Virtual Reality
So Predictable! Continuous 3D Hand Trajectory Prediction in Virtual Reality
 
Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...
Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...
Reinforcement Learning-based Placement of Charging Stations in Urban Road Net...
 
Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...
Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...
Prediction for Retrospection: Integrating Algorithmic Stress Prediction into ...
 
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Orien...
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Orien...Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Orien...
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Orien...
 
A Style-Based Generator Architecture for Generative Adversarial Networks
A Style-Based Generator Architecture for Generative Adversarial NetworksA Style-Based Generator Architecture for Generative Adversarial Networks
A Style-Based Generator Architecture for Generative Adversarial Networks
 
CatchLIve: Real-time Summarization of Live Streams with Stream Content and In...
CatchLIve: Real-time Summarization of Live Streams with Stream Content and In...CatchLIve: Real-time Summarization of Live Streams with Stream Content and In...
CatchLIve: Real-time Summarization of Live Streams with Stream Content and In...
 
Perception! Immersion! Empowerment! Superpowers as Inspiration for Visualization
Perception! Immersion! Empowerment! Superpowers as Inspiration for VisualizationPerception! Immersion! Empowerment! Superpowers as Inspiration for Visualization
Perception! Immersion! Empowerment! Superpowers as Inspiration for Visualization
 
Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic F...
Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic F...Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic F...
Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic F...
 
Neural Approximate Dynamic Programming for On-Demand Ride-Pooling
Neural Approximate Dynamic Programming for On-Demand Ride-PoolingNeural Approximate Dynamic Programming for On-Demand Ride-Pooling
Neural Approximate Dynamic Programming for On-Demand Ride-Pooling
 
StoryMap: Using Social Modeling and Self-Modeling to Support Physical Activit...
StoryMap: Using Social Modeling and Self-Modeling to Support Physical Activit...StoryMap: Using Social Modeling and Self-Modeling to Support Physical Activit...
StoryMap: Using Social Modeling and Self-Modeling to Support Physical Activit...
 
Bad Breakdowns, Useful Seams, and Face Slapping: Analysis of VR Fails on YouTube
Bad Breakdowns, Useful Seams, and Face Slapping: Analysis of VR Fails on YouTubeBad Breakdowns, Useful Seams, and Face Slapping: Analysis of VR Fails on YouTube
Bad Breakdowns, Useful Seams, and Face Slapping: Analysis of VR Fails on YouTube
 
Invertible Denoising Network: A Light Solution for Real Noise Removal
Invertible Denoising Network: A Light Solution for Real Noise RemovalInvertible Denoising Network: A Light Solution for Real Noise Removal
Invertible Denoising Network: A Light Solution for Real Noise Removal
 
Traffic Demand Prediction Based Dynamic Transition Convolutional Neural Network
Traffic Demand Prediction Based Dynamic Transition Convolutional Neural NetworkTraffic Demand Prediction Based Dynamic Transition Convolutional Neural Network
Traffic Demand Prediction Based Dynamic Transition Convolutional Neural Network
 
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training  MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
 
Screen2Vec: Semantic Embedding of GUI Screens and GUI Components
Screen2Vec: Semantic Embedding of GUI Screens and GUI ComponentsScreen2Vec: Semantic Embedding of GUI Screens and GUI Components
Screen2Vec: Semantic Embedding of GUI Screens and GUI Components
 
Augmenting Decisions of Taxi Drivers through Reinforcement Learning for Impro...
Augmenting Decisions of Taxi Drivers through Reinforcement Learning for Impro...Augmenting Decisions of Taxi Drivers through Reinforcement Learning for Impro...
Augmenting Decisions of Taxi Drivers through Reinforcement Learning for Impro...
 
Natural Language to Visualization by Neural Machine Translation
Natural Language to Visualization by Neural Machine TranslationNatural Language to Visualization by Neural Machine Translation
Natural Language to Visualization by Neural Machine Translation
 

KĂźrzlich hochgeladen

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
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024The Digital Insurer
 
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
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsJoaquim Jorge
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonAnna Loughnan Colquhoun
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
 
A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024Results
 
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
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountPuma Security, LLC
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUK Journal
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘RTylerCroy
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?Antenna Manufacturer Coco
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slidespraypatel2
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Drew Madelung
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Scriptwesley chun
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfEnterprise Knowledge
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Enterprise Knowledge
 
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
 

KĂźrzlich hochgeladen (20)

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
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
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
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024
 
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
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path Mount
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
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
 

[0114]hyun wook

  • 1. Attention Models in Graphs: A Survey John B. Lee, Ryan A. Rossi, Sungchul Kim, Nesreen K. Ahmed, Eunyee Koh Adobe Research TKDD’2018
  • 2. Contents • Definition of basic keywords • Overview • Model description • Criticisms/benefits
  • 3. Definition of Basic keywords 2
  • 4. Definition of Basic keywords 3
  • 5. Definition of Basic keywords 4
  • 6. Overview 5 • Three different taxonomies based on  Problem setting – especially, based on input/output format  Type of attention  Task/problem
  • 8. AttentionWalks • Input: Homogeneous graph • Output: Node embedding • Mechanism: Learn attention weights + Attention-guided walk • DeepWalk + Attention • Performance of DeepWalk is sensitive to context window size c 7 Sami Abu-El-Haija, Bryan Perozzi, Rami Al-Rfou, and Alex Alemi. 2017. Watch Your Step: Learning Graph Embeddings Through Attention. In arXiv:1710.09599v1
  • 9. GAKE • Input: Homogeneous graph(knowledge graph) • Output: Node embedding • Mechanism: Learn attention weights • Node context 계산 시 edge 정보도 사용 • 최종 node embedding 계산에 attention 사용 8 Jun Feng, Minlie Huang, Yang Yang, and Xiaoyan Zhu. 2016. GAKE: Graph Aware Knowledge Embedding. In Proc. of COLING. 641–651
  • 10. GAT • Input: Homogeneous graph • Output: Node embedding • Mechanism: Learn attention weights • GCN(Graph-ConvNet) + Attention • Using multi-head attention 9Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2018. Graph Attention Networks. In Proc. of ICLR. 1–12.
  • 11. AGNN • Input: Homogeneous graph • Output: Node embedding • Mechanism: Similarity-based attention • GCN + Attention • Similar to GAT, but using cosine similarity to calculate attention • No multi-head attention 10Kiran K. Thekumparampil, Chong Wang, Sewoong Oh, and Li-Jia Li. 2018. Attention-based Graph Neural Network for Semi-supervised Learning. In arXiv:1803.03735v1.
  • 12. PRML • Input: Homogeneous graph • Output: Edge embedding • Mechanism: Learn attention weights • Path-based feature learning 이후에  1) 각 path마다 attention(중요 노드 선정)  2) path끟댏 attention을 통해 최종 embedding 생성 11Zhou Zhao, Ben Gao, Vicent W. Zheng, Deng Cai, Xiaofei He, and Yueting Zhuang. 2017. Link Prediction via Ranking Metric Dual-level Attention Network Learning. In Proc. of IJCAI. 3525–3531.
  • 13. EAGCN • Input: Heterogeneous graph • Output: Graph embedding/Node embedding • Mechanism: Learn attention weights • GCN + Attention • Multi attention to handle heterogeneous graph 12Chao Shang, Qinqing Liu, Ko-Shin Chen, Jiangwen Sun, Jin Lu, Jinfeng Yi, and Jinbo Bi. 2018. Edge Attention-based Multi-Relational Graph Convolutional Networks. In arXiv:1802.04944v1.
  • 14. Modified-GAT • Input: Homogeneous graph • Output: Graph embedding • Mechanism: Similarity-based attention • GAT+FCN, attention 계산이 약간 변함 • GAT뼟 통해 만들어진 Node embedding을 FCN을 통해 graph embedding 으로 변환 13Seongok Ryu, Jaechang Lim, and Woo Youn Kim. 2018. Deeply learning molecular structure- property relationships using graph attention neural network. In arXiv:1805.10988v2.
  • 15. graph2seq • Input: Homogeneous graph • Output: Graph embedding • Mechanism: Similarity-based attention • In node embedding, they consider both forward/backward neighbor • In attention, they use node embedding 14Kun Xu, Lingfei Wu, Zhiguo Wang, Yansong Feng, Michael Witbrock, and Vadim Sheinin. 2018. Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks. In arXiv:1804.00823v3.
  • 16. GAM • Input: Homogeneous graph • Output: Graph embedding • Mechanism: Learn attention weights + Attention-guided walk • Use RNN in attention-guided walk • Use multi agent 15John Boaz Lee, Ryan Rossi, and Xiangnan Kong. 2018. Graph Classification using Structural Attention. In Proc. of KDD. 1–9.
  • 17. RNNSearch, Att-NMT • Input: Path • Output: Graph embedding • Mechanism: Similarity-based attention • Use hidden as embedding, calculate attention on every hidden, with similarity between target hidden and hiddens • In Att-NMT, there are local attention 16 Dzmitry Bahdanau, KyungHyun Cho, and Yoshua Bengio. 2015. Neural Machine Translation by Jointly Learning to Align and Translate. In Proc. of ICLR. 1–15 Thang Luong, Hieu Pham, and Christopher D. Manning. 2015. Effective Approaches to Attention-based Neural Machine Translation. In Proc. of EMNLP. 1412–1421.
  • 18. Hao Zhou, Tom Yang, Minlie Huang, Haizhou Zhao, Jingfang Xu, and Xiaoyan Zhu. 2018. Commonsense Knowledge Aware Conversation Generation with Graph Attention. In Proc. of IJCAI-ECAI. 1–7 CCM • Input: Homogeneous Graph • Output: Graph embedding/Hybrid embedding • Mechanism: Learn attention weights • Get input sequence and knowledge graph • Use two graph attention/one seq2seq attention 15
  • 19. JointD/E+SATT • Input: Homogeneous graph • Output: Hybrid embedding • Mechanism: Similarity-based attention 15Xu Han, Zhiyuan Liu, and Maosong Sun. 2018. Neural Knowledge Acquisition via Mutual Attention Between Knowledge Graph and Text. In Proc. of AAAI. 1–8
  • 20. GRAM • Input: Directed acyclic graph • Output: Hybrid embedding • Mechanism: Learn attention weights • DAG의 ancestor node뼟 모두 사용해서 attention 15Edward Choi, Mohammad Taha Bahadori, Le Song, Walter F. Stewart, and Jimeng Sun. 2017. GRAM: Graph- based Attention Model for Healthcare Representation Learning. In Proc. of KDD. 787–795
  • 21. Criticisms • Embedding을 나누는 기준이 모호함 • Input을 Homogeneous 등을 나누려는 시도는 좋았으나, survey한 논문 이 special case와 Homogeneous밖에 없음 • Problem setting기준 구분에서 전체 모델 소개가 끝나고, mechanism/task기준 구분에 내용이 없음  Taxonomy 자체가 필요한 지를 잘 모르겠음 15
  • 22. Criticisms • Embedding을 나누는 기준이 모호함 • Input을 Homogeneous 등을 나누려는 시도는 좋았으나, survey한 논문 이 special case와 Homogeneous밖에 없음 • Problem setting기준 구분에서 전체 모델 소개가 끝나고, mechanism/task기준 구분에 내용이 없음  Taxonomy 자체가 필요한 지를 잘 모르겠음 15
  • 23. Benefits • Trajectory data 다룰 때 CCM은 써볼 수 있을 듯함 • Cora dataset을 사용한 논문(e.g. GAT)은 현재 진행중인 task에 도움이 될 듯  다시 읽어볼 듯 15

Hinweis der Redaktion

  1. Homogeneous graph: univariant graph(both edge and node) Heterogeneous graph: multivariant graph(either edge or node) Attributed Graph: 따로 attribute matrix등이 주어지는 경우 – 실질적으로 이 논문에서 다루는 모든 그래프는 attributed graph임. Node type 등도 전부 attribute라고 퉁칠수 있음.
  2. Homogeneous graph: univariant graph(both edge and node) Heterogeneous graph: multivariant graph(either edge or node) Attributed Graph: 따로 attribute matrix등이 주어지는 경우 – 실질적으로 이 논문에서 다루는 모든 그래프는 attributed graph임. Node type 등도 전부 attribute라고 퉁칠수 있음.
  3. DAG: Tree와 매우 흡사함.
  4. 대부분이 입력으로 Homogeneous graph를 받고 있음. 3가지 분류법에 따라 이야기를 하면 겹치는게 너무 많고, taxonomies에 집중해서 읽는 건 큰 의미가 없다고 생각해서 순서대로 모델 소개를 함
  5. Deepwalk는 random walk를 사용하기떄문에 walk의 expectation에 weight가 일정할 수 밖에 없음 – c의 영향을 크게받음 AttentionWalks는 이를 보완하기위해 attention weights를 줘서 walk를 attention-based로 수행하도록 바꿈 – 그래도 기반은 random walk임
  6. Knowledge graph는 (h,t,r)의 tripet으로 구성되어 있는데, 거의 모든 knowledge graph를 쓰는 모델이 h와 t를 구분을 안함 – homogenenous 로 들어감. Missing subjects를 구하는게 목표(Link prediction) ON = objective function, P: context가 주어졌을때, subject si를 예측할 확률
  7. h1~h6은 각 노드의 features를 의미하고, h`은 최종적으로 계산된 node embedding임. 논문에는 homogeneous graph를 다뤘다고 적혀있는데, 실제로는 node feature의 dimension이 F(attribute라고 생각하는듯?)인 그래프를 다루고 있었음.
  8. GAT는 label이 있는 cora dataset을 다뤘는데, AGNN은 semi-supervised learning을 함 – supervised learning이 아니라서, similarity based method를 사용함
  9. Edge embedding이라고 적혀있는 유일한 논문이였음
  10. Multi attention – 각 attribute 마다 attentio을 한다는 뜻 – edge attribute가 많음, node attribute = 1 각각 생성된 edge attention matrix를 GCN을 통해 graph embedding을 생성 Node embedding쪽으로 들어간 이유: graph embedding이 단순 node embedding의 summation 이므로
  11. NLQA를 다룸 – input: sentence graph? Si = hidden on ith, hj = jth node representation  ci==node attention on each time-step
  12. 각 RNN unit은 output walk ui와 다음 walk에 사용될 rank(attention weight)를 출력함. Vector u는 hidden layer h와 attention을 통해 embedding pi가 되고, agent 별로 계산된 이 pi를 attention을 통해 최종 embedding으로 생성
  13. Dipole은 거의 RNNSearch와 똑같아서 다루지 않음.
  14. Knowledge interpreter에서는 input word를 통해 attention이 제일 큰 knowledge graph를 뽑고, 이를 hidden에 넣음 Knowledge aware generator에서는 hidden 및 attention을 통해 graph를 뽑고, 이를 기반으로 단어를 생성함 Graph를 generator 등에 넣을 때 embedding을 해서 graph embedding 쪽에 들어가있는듯.
  15. 서로 옆에 있는걸 사용함 – Text측에서는 attentio할 때 graph embedding을 기준으로 attentio을 하고, text의 최종 output을 변환해서 knowledge graph측에 similarity based attention을 함
  16. 서로 옆에 있는걸 사용함 – Text측에서는 attentio할 때 graph embedding을 기준으로 attentio을 하고, text의 최종 output을 변환해서 knowledge graph측에 similarity based attention을 함 옆에 곱해지는 e는 각 code의 basic embedding임.(GRAM은 사용한게 의학(medical)쪽 데이터)