Useful Links
Computer Science
Artificial Intelligence
Deep Learning
Graph Neural Networks
1. Foundations for Understanding GNNs
2. Core Concepts of Graph Neural Networks
3. Foundational GNN Architectures
4. Advanced GNN Architectures
5. GNN Training and Optimization
6. GNN Applications and Tasks
7. Evaluation and Benchmarking
8. Advanced Topics and Research Frontiers
9. Implementation and Practical Considerations
Advanced GNN Architectures
Higher-order GNNs
Limitations of 1-WL GNNs
k-GNNs
Higher-order Message Passing
Computational Complexity
Subgraph-based Methods
Subgraph Sampling
Subgraph Isomorphism Networks
Simplicial Neural Networks
Simplicial Complexes
Higher-order Structures
Graph Pooling Methods
Hierarchical Pooling
DiffPool
MinCut Pool
Top-K Pooling
Global Pooling
Set2Set
Sort Pooling
Attention-based Pooling
Graph Coarsening
Graph Reduction Techniques
Multi-resolution Analysis
Equivariant and Invariant GNNs
Group Theory Foundations
Equivariant Neural Networks
Invariant Graph Networks
Geometric Deep Learning Principles
Graph Transformers
Graphormer
Structural Encodings
Centrality Encodings
Graph-BERT
Pre-training on Graphs
Masked Node Prediction
Universal Graph Transformer
Previous
3. Foundational GNN Architectures
Go to top
Next
5. GNN Training and Optimization