1,045 technical terms and definitions
graph neural network node classification prediction, graph neural network, neural network node, network node classification, node classification prediction, graph neural
Graph Neural Network Node Classification Prediction with Machine Learning Introduction & Motivation Graph Neural Network Node Classification Prediction with Machine Learning…
Graph Neural Network Training Optimization Introduction & Motivation Graph Neural Network Training Optimization addresses a central problem in graph network representation…
101241 graph, graph neural, gin gnn ogb rnn update, activation functions & non-linearity, activation functions non-linearity, activation functions, functions non-linearity
graph neural network is a neural architecture that learns from nodes, edges, attributes, and graph structure through neighborhood message passing. GNNs model molecules, circuits…
graph neural networks engineering systems, graph neural, networks engineering systems, gnn ogb, graph neural networks, neural networks engineering, neural networks, networks engineering
Graph Neural Networks for Engineering Systems Introduction & Motivation Many engineering systems naturally represent as graphs: molecular structures, process flowcharts, power…
graph neural, networks gnn message, 2d f1 gat gcn gnn lstm, graph neural networks gnn message passing & node classification, graph neural networks, neural networks gnn
Graph Neural Networks: GNN Message Passing & Node Classification Introduction & Motivation GNNs learn on graph-structured data via message passing. Nodes aggregate neighbor…
Graph Neural Networks and Advanced Graph Machine Learning 1. Executive Summary & Graph-Structured Data Primitives Graph Neural Networks (GNNs) extend deep-learning primitives…
hierarchical pooling methods, graph coarsening
Hierarchical Pooling is a multilevel graph coarsening approach that learns cluster assignments and supernode abstractions - It enables graph representation learning across scales…
graph neural, networks message passing, gat gcn gnn ogb passed sgd, graph neural networks message passing & graph convolutions, graph neural networks, neural networks message
Graph Neural Networks: Message Passing & Graph Convolutions Introduction & Motivation Graph neural networks: operate on graph-structured data. Message passing: aggregate neighbor…
gnn circuit analysis, graph learning eda, message passing timing prediction, circuit graph representation
Graph Neural Networks for Timing Analysis are deep learning models that represent circuits as graphs and use message passing to predict timing metrics 100-1000× faster than…
graph neural networks
Graph Neural ODEs combine Graph Neural Networks (GNNs) with Neural ODEs — defining continuous-time dynamics on graph-structured data where node features evolve according to an ODE…
Graph Neural Ordinary Differential Equations Introduction & Motivation Graph Neural Ordinary Differential Equations addresses a central problem in graph network representation…
graph neural networks
Graph Neural Operators (GNO) are a class of operator learning models that use graph neural networks to discretize the physical domain — allowing for learning resolution-invariant…
Graph Normalization and Standardization Introduction & Motivation Graph Normalization and Standardization addresses a central problem in graph network representation…
prompting techniques
Graph of Thoughts is a reasoning framework that models intermediate thoughts as graph nodes with merge and revisit operations - It is a core method in modern LLM workflow…
fusion, fold
Graph Optimization is the set of compiler techniques that transform a neural network's computation graph to minimize execution time and memory usage before runtime — performing…
optimization
Graph optimization is the compiler-driven transformation of computation graphs to improve runtime efficiency without changing semantics - it rewrites operator graphs through…
model optimization
Graph Optimization is systematic rewriting of computational graphs to improve execution efficiency - It improves runtime without changing model semantics. What Is Graph…
graph optimization and dead code elimination, graph optimization dead, optimization dead code, dead code elimination, graph optimization, optimization dead, dead code, code elimination
Graph Optimization and Dead Code Elimination Introduction & Motivation Graph Optimization and Dead Code Elimination addresses a central problem in ml-compiler process control…
graph algorithms
Graph Partitioning is the combinatorial optimization problem of dividing a graph's nodes into roughly equal-sized groups while minimizing the total number (or weight) of edges…
graph neural networks
Graph Pooling is a class of operations in graph neural networks that reduce the number of nodes in a graph to produce a coarser representation, analogous to spatial pooling…
Graph Pooling and Aggregation Strategy Introduction & Motivation Graph Pooling and Aggregation Strategy addresses a central problem in graph network representation…
Graph Pooling and Readout Functions Introduction & Motivation Graph Pooling and Readout Functions addresses a central problem in graph network representation…
Privacy-Preserving Graph Learning Introduction & Motivation Privacy-Preserving Graph Learning addresses a central problem in graph network representation…
rag
Graph RAG combines knowledge graphs with retrieval to surface connected entities and relationships. Standard RAG limitation: Retrieves independent chunks, misses relationships…
knowledge graph retrieval, graph based retrieval, graphrag, structured retrieval
Graph RAG (Graph-based Retrieval Augmented Generation) is the advanced retrieval paradigm that organizes external knowledge as a graph structure rather than flat document chunks…
Graph Reconstruction and Loss Functions Introduction & Motivation Graph Reconstruction and Loss Functions addresses a central problem in graph network representation…
graph neural networks
Graph Recurrence is a recurrent modeling pattern that propagates graph state across time for long-horizon dependencies - It combines structural message passing with temporal…
Graph Regularization and Constraints Introduction & Motivation Graph Regularization and Constraints addresses a central problem in graph network representation…
Graph Representation Learning Quality Introduction & Motivation Graph Representation Learning Quality addresses a central problem in graph network representation…
rag
Graph Retrieval is retrieval over graph-structured knowledge where entities and relations are traversed to collect evidence - It is a core method in modern RAG and retrieval…
Graph Rewiring and Spectral Gap Optimization Introduction & Motivation Graph Rewiring and Spectral Gap Optimization addresses a central problem in graph network representation…
Graph Sampling and Neighborhood Strategy Introduction & Motivation Graph Sampling and Neighborhood Strategy addresses a central problem in graph network representation…
Graph Self-Supervised Learning Introduction & Motivation Graph Self-Supervised Learning addresses a central problem in selfsupervised and graph-augmentation-strategy architecture…
Semi-Supervised Learning on Graphs Introduction & Motivation Semi-Supervised Learning on Graphs addresses a central problem in graph network representation…
model optimization
Graph Serialization is encoding computational graphs into persistent formats for storage, transfer, and deployment - It enables reproducible model packaging across environments.…
Soft Attention Mechanisms in Graphs Introduction & Motivation Soft Attention Mechanisms in Graphs addresses a central problem in graph network representation…
Graph Sparsification and Pruning Introduction & Motivation Graph Sparsification and Pruning addresses a central problem in graph network representation and sparsity-preservation…
Graph Structure Learning from Data Introduction & Motivation Graph Structure Learning from Data addresses a central problem in graph network representation and structure-discovery…
discrete mathematics graphs, vertices and edges, graph traversal, graph connectivity, shortest path algorithms, graph coloring, network flow, graph theory semiconductor
Graph theory studies systems by separating the things that exist from the relationships that connect them. A graph can represent nets joined by components, process steps…
Graph Theory, Network Flow, and Spectral Laplacians 1. Networks as mathematical objects A graph represents objects and pairwise relationships. The objects are vertices and…
Graph-Based Time Series Models Introduction & Motivation Graph-Based Time Series Models addresses a central problem in timeseries forecasting and graph-structure-learning…
Graph-to-Text Generation Introduction & Motivation Graph-to-Text Generation addresses a central problem in generative generation and graph-coverage-accuracy synthesis: how…
graph traversal bfs, graph traversal, traversal bfs
Graph Traversal BFS Introduction & Motivation Graph Traversal BFS addresses a central problem in algorithms process control and traversal-latency-linear prediction: how to Predict…
graph traversal dfs, graph traversal, traversal dfs
Graph Traversal DFS Introduction & Motivation Graph Traversal DFS addresses a central problem in algorithms process control and traversal-time-linear prediction: how to Predict…
graph neural networks
Graph U-Net is an encoder-decoder graph architecture with learned pooling and unpooling across hierarchical resolutions - It captures global context through coarsening while…
gnn upsampling, graph generation
Graph unpooling is a graph neural network operation that reconstructs higher-resolution graphs from pooled representations — the inverse of pooling, used in graph autoencoders…
graph neural networks
GraphVAE is a Variational Autoencoder designed for graph-structured data that generates entire molecular graphs in a single forward pass — simultaneously producing the adjacency…
Graph Random Walk Generation Introduction & Motivation Graph Random Walk Generation addresses a central problem in graph network representation and walk-diversity learning: how…
graph neural networks
Graph Wavelets are localized, multi-scale basis functions defined on graphs that enable simultaneous localization in both the vertex (spatial) domain and the spectral (frequency)…
graph neural networks
GraphAF is autoregressive flow-based molecular graph generation with exact likelihood optimization. - It sequentially constructs molecules while maintaining tractable probability…