- Should Space Exploration Budget be Increased?
영어 글쓰기 스터디 (2주차)
Read More
- Should Generative AI be Regulated?
영어 글쓰기 스터디 (1주차)
Read More
- [8.2] Training Graph Neural Networks
Learning Objective : GNN Training Pipeline
Read More
- [8.1] Graph Augmentation for GNNs
Graph Augmentation : Feature/Structure Augmentation
Read More
- [7.3] Stacking layers of a GNN
Stacking Layers : Layer Connectivity
Read More
- [7.2] A Single Layer of a GNN
Single Layer : Message Transformation, Message Aggregation
Read More
- [7.1] A general Perspective on GNNs
GNN Framework를 만들기 위해 고려해야할 요소
Read More
- [6.3] Deep Learning for Graphs
Graph를 위한 Deep Learning의 개요
Read More
- [6.2] Basics of Deep Learning
Deep Learning에 대한 설명
Read More
- [5.3] Collective Classification
Loopy Belief Propagation
Read More
- [5.2] Relational and Iterative Classification
Relational Classification vs Iterative Classification
Read More
- [5.1] Message passing and Node Classification
Message passing의 개요
Read More
- [4.4] Matrix Factorization and Node Embeddings
Matrix Factorization을 이용한 Node Embedding 방법
Read More
- [4.3] Random Walk with Restarts
추천 시스템과 Random Walk with Restarts
Read More
- [4.2] PageRank: How to solve?
PageRank를 풀어내는 수학적 방법
Read More
- [4.1] PageRank
PageRank란 무엇인가
Read More
- [3.3] Embedding Entire Graphs
그래프 단위로 embedding 하는 방법
Read More
- [3.2] Random Walk Approaches for Node
Random Walk란?
Read More
- [3.1] Node Embeddings
Node Embedding이란?
Read More
- [2.3] Traditional Feature-based Methods : Graph
전통적인 feature-based 방법들(Graph-Level)
Read More
- [2.2] Traditional Feature-based Methods : Link
전통적인 feature-based 방법들(Link-Level)
Read More
- [2.1] Traditional Feature-based Methods : Node
전통적인 feature-based 방법들(Node-Level)
Read More
- [1.3] Choice of Graph Representation
문제에 따른 그래프 표현 방법
Read More
- [1.2] Applications of Graph ML
그래프 머신러닝 적용 사례
Read More
- [1.1] Why Graphs?
그래프를 사용해야하는 이유
Read More
- 관계형 vs 비관계형 데이터베이스
관계형 DB와 비관계형 DB에 관하여
Read More