UsefulLinks
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
4.
Advanced GNN Architectures
4.1.
Higher-order GNNs
4.1.1.
Limitations of 1-WL GNNs
4.1.2.
k-GNNs
4.1.2.1.
Higher-order Message Passing
4.1.2.2.
Computational Complexity
4.1.3.
Subgraph-based Methods
4.1.3.1.
Subgraph Sampling
4.1.3.2.
Subgraph Isomorphism Networks
4.1.4.
Simplicial Neural Networks
4.1.4.1.
Simplicial Complexes
4.1.4.2.
Higher-order Structures
4.2.
Graph Pooling Methods
4.2.1.
Hierarchical Pooling
4.2.1.1.
DiffPool
4.2.1.2.
MinCut Pool
4.2.1.3.
Top-K Pooling
4.2.2.
Global Pooling
4.2.2.1.
Set2Set
4.2.2.2.
Sort Pooling
4.2.2.3.
Attention-based Pooling
4.2.3.
Graph Coarsening
4.2.3.1.
Graph Reduction Techniques
4.2.3.2.
Multi-resolution Analysis
4.3.
Equivariant and Invariant GNNs
4.3.1.
Group Theory Foundations
4.3.2.
Equivariant Neural Networks
4.3.3.
Invariant Graph Networks
4.3.4.
Geometric Deep Learning Principles
4.4.
Graph Transformers
4.4.1.
Graphormer
4.4.1.1.
Structural Encodings
4.4.1.2.
Centrality Encodings
4.4.2.
Graph-BERT
4.4.2.1.
Pre-training on Graphs
4.4.2.2.
Masked Node Prediction
4.4.3.
Universal Graph Transformer
Previous
3. Foundational GNN Architectures
Go to top
Next
5. GNN Training and Optimization