Skip to content

Concept List

Total concepts: 300

This list feeds the learning graph dependency DAG. Review before proceeding.

Prerequisites

  1. Matrix Multiplication
  2. Matrix Transpose
  3. Eigenvalue Decomposition
  4. Eigenvector
  5. Symmetric Matrix
  6. Positive Semi-Definite Matrix
  7. Singular Value Decomp (SVD)
  8. Matrix Rank
  9. Dot Product
  10. Cosine Similarity
  11. Gradient Descent
  12. Backpropagation
  13. Chain Rule (Calculus)
  14. Automatic Differentiation
  15. PyTorch Tensor
  16. PyTorch Autograd
  17. Neural Network Layer
  18. Softmax Function
  19. Cross-Entropy Loss
  20. Adam Optimizer

Graph Fundamentals

  1. Graph (Undirected)
  2. Graph (Directed)
  3. Node (Vertex)
  4. Edge (Link)
  5. Adjacency Matrix
  6. Node Degree
  7. In-Degree
  8. Out-Degree
  9. Degree Distribution
  10. Power-Law Degree Distribution
  11. Graph Path
  12. Shortest Path
  13. Graph Diameter
  14. Connected Component
  15. Strongly Connected Component
  16. Weakly Connected Component
  17. Bipartite Graph
  18. Heterogeneous Graph
  19. Multigraph
  20. Weighted Graph
  21. Attribute Graph
  22. Subgraph
  23. Ego Network
  24. Clique
  25. Cycle
  26. Tree (Graph Theory)
  27. Spanning Tree
  28. Planar Graph
  29. Graph Isomorphism
  30. Graph Homomorphism
  31. Small-World Network
  32. Scale-Free Network
  33. Erdős–Rényi Random Graph
  34. Barabási–Albert Model
  35. Preferential Attachment
  36. Giant Component
  37. Transitivity

Classical Graph Algorithms

  1. Local Clustering Coefficient
  2. Betweenness Centrality
  3. Closeness Centrality
  4. Eigenvector Centrality
  5. PageRank
  6. Personalized PageRank
  7. HITS Algorithm
  8. Random Walk
  9. Stationary Distribution
  10. Power Iteration
  11. Teleportation (PageRank)
  12. Community Detection
  13. Modularity (Network)
  14. Louvain Algorithm
  15. Girvan-Newman Algorithm
  16. Spectral Clustering
  17. Normalized Cut
  18. Overlapping Community
  19. BigCLAM Model
  20. Network Motif
  21. Graphlet
  22. Graphlet Degree Vector
  23. Graph Kernel
  24. Weisfeiler-Lehman Kernel
  25. Label Propagation
  26. Belief Propagation
  27. Influence Maximization
  28. Linear Threshold Model
  29. Independent Cascade Model
  30. SIR Epidemic Model
  31. Breadth-First Search
  32. Depth-First Search
  33. Katz Similarity

Node Embeddings

  1. Node Embedding
  2. Embedding Space
  3. Encoder-Decoder Framework
  4. Shallow Embedding
  5. Matrix Factorization (Graph)
  6. DeepWalk
  7. node2vec
  8. Biased Random Walk
  9. BFS Strategy (node2vec)
  10. DFS Strategy (node2vec)
  11. Skip-Gram Model
  12. Negative Sampling
  13. LINE Embedding
  14. Transductive Learning
  15. Inductive Learning
  16. Structural Equivalence
  17. Homophily

GNN Architecture

  1. Graph Neural Network (GNN)
  2. Message Passing Neural Net
  3. Message Function
  4. Aggregation Function
  5. Update Function
  6. Graph Convolutional Network
  7. GraphSAGE
  8. Graph Attention Network (GAT)
  9. Attention Mechanism (Graph)
  10. Multi-Head Attention (Graph)
  11. Graph Isomorphism Network
  12. Sum Aggregation
  13. Mean Aggregation
  14. Max Aggregation
  15. Neighborhood Aggregation
  16. K-Hop Neighborhood
  17. Receptive Field (GNN)
  18. Layer Depth (GNN)
  19. Skip Connection (GNN)
  20. Residual Connection (GNN)
  21. Jumping Knowledge Network
  22. Graph-Level Readout
  23. Global Mean Pooling
  24. Global Sum Pooling
  25. DiffPool
  26. MinCutPool
  27. Node-Level Task
  28. Edge-Level Task
  29. Graph-Level Task
  30. Link Prediction
  31. Node Classification
  32. Graph Classification
  33. Graph Regression
  34. Spectral Graph Convolution
  35. Chebyshev Polynomial Conv
  36. Graph Laplacian
  37. Normalized Graph Laplacian
  38. Spectral Domain (Graph)
  39. Spatial Domain (Graph)
  40. Virtual Node Augmentation
  41. Virtual Edge Augmentation

GNN Theory

  1. Weisfeiler-Lehman (WL) Test
  2. 1-WL Test
  3. k-WL Test
  4. GNN Expressiveness
  5. Graph Isomorphism Problem
  6. GNN Distinguishing Power
  7. Over-Smoothing
  8. Over-Squashing
  9. GNN Bottleneck
  10. Graph Equivariance
  11. Graph Invariance
  12. Permutation Invariance
  13. Permutation Equivariance
  14. Position-Aware GNN
  15. Identity-Aware GNN
  16. Higher-Order GNN
  17. Subgraph GNN

Graph Transformers

  1. Graph Transformer
  2. Graphormer
  3. SAN (Spectral Attention Net)
  4. GPS (General Powerful GNN)
  5. Laplacian Positional Encoding
  6. Random Walk Struct Encoding
  7. Sign-Invariant Network
  8. Basis-Invariant Network
  9. Spatial Bias (Graph Attention)
  10. Centrality Encoding
  11. Edge Encoding (Transformer)
  12. Relative Positional Encoding

Knowledge Graphs

  1. Knowledge Graph
  2. KG Entity
  3. KG Relation
  4. KG Triple
  5. KG Completion
  6. Link Prediction (KG)
  7. TransE
  8. TransR
  9. DistMult
  10. ComplEx
  11. RotatE
  12. KG Embedding Geometry
  13. Bilinear KG Model
  14. Symmetry (Relation Pattern)
  15. Antisymmetry (Relation)
  16. Inversion (Relation)
  17. Composition (Relation)
  18. Query Embedding
  19. Box Embedding (Query2Box)
  20. Multi-Hop Query
  21. Conjunctive Query
  22. Neural Bellman-Ford Net
  23. Inductive KG Reasoning
  24. ULTRA
  25. InGram

Heterogeneous Graphs

  1. Heterogeneous GNN
  2. R-GCN (Relational GCN)
  3. Heterogeneous Graph Trans
  4. HAN (Hetero Attention Net)
  5. Meta-Path
  6. Relation-Specific Weights
  7. Basis Decomposition (R-GCN)
  8. Type-Specific Projection

Applications

  1. Recommender System (Graph)
  2. Collaborative Filtering
  3. Matrix Factorization (Rec)
  4. Neural Collaborative Filter
  5. LightGCN
  6. PinSage
  7. Drug-Drug Interaction
  8. Protein-Protein Interaction
  9. Molecular Graph
  10. Drug Discovery with GNNs
  11. Social Network Analysis
  12. Fraud Detection (Graph)
  13. Traffic Forecasting (Graph)
  14. Scene Graph
  15. Relational Database as Graph
  16. Temporal Graph
  17. Dynamic Graph
  18. Temporal GNN (TGN)
  19. TGAT
  20. Frequent Subgraph Mining
  21. Subgraph Isomorphism
  22. Order Embedding
  23. SPMiner

Scalability

  1. Mini-Batch Training (GNN)
  2. Neighbor Sampling
  3. GraphSAINT
  4. Cluster-GCN
  5. LADIES Sampler
  6. Layer-Wise Sampling
  7. Historical Embeddings (SIGN)
  8. Graph Partitioning

Generative Models

  1. Graph Generative Model
  2. GraphRNN
  3. GCPN
  4. Molecule Generation
  5. Variational Autoencoder (VGAE)
  6. DiGress
  7. Graph Generation Metrics

Advanced Topics

  1. In-Context Learning (Graphs)
  2. Conformalized GNN
  3. Graph Foundation Model
  4. LLM + GNN Integration
  5. Text-Attributed Graph
  6. Graph Instruction Tuning
  7. One-For-All (OFA) Model
  8. Agent Memory as Graph
  9. Tool-Use Graph
  10. Relational Deep Learning
  11. RelBench
  12. RelGNN

Training & Optimization

  1. Cross-Entropy (Node Class)
  2. Binary Cross-Entropy (LP)
  3. Negative Sampling (LP)
  4. Data Augmentation (Graph)
  5. Dropout (GNN)
  6. Batch Normalization (GNN)
  7. Layer Normalization (GNN)
  8. DropEdge
  9. PairNorm
  10. Early Stopping (GNN)
  11. Train/Val/Test Split (Trans)
  12. Train/Val/Test Split (Ind)
  13. Curriculum Learning (Graph)

Tools & Frameworks

  1. PyTorch Geometric (PyG)
  2. NetworkX
  3. Open Graph Benchmark
  4. SNAP
  5. DeepSNAP
  6. DGL
  7. TUDataset
  8. PyKEEN
  9. RelBench (Benchmark)

Self-Supervised & Evaluation

  1. Self-Supervised Learning
  2. Deep Graph Infomax (DGI)
  3. Graph Contrastive Learning
  4. Contrastive Loss
  5. Graph Augmentation (SSL)
  6. APPNP
  7. Simple Graph Conv (SGC)
  8. Principal Neighborhood Agg
  9. Mean Reciprocal Rank (MRR)
  10. Hits@K Metric
  11. ROC-AUC Score
  12. Transfer Learning (Graphs)
  13. Pre-Training (GNN)
  14. Fine-Tuning (GNN)
  15. Node Feature Normalization
  16. Graph Sampling Strategy
  17. Stochastic Depth (GNN)
  18. SIGN Architecture