Artificial intelligence and data

Graph rewriting

Graph rewriting is a family of formal methods in computer science that transform graphs by finding a pattern subgraph in a host graph and replacing it with a replacement.

Graph sampling

Graph sampling is a family of algorithms that randomly select nodes, edges, or subgraphs from a large graph to estimate statistics like degree and clustering when full processing is infeasible.

Graph search

Graph search is a family of algorithms that systematically explore the vertices and edges of a graph to find a target node, a path, or a structure.

Graph structure learning

Graph structure learning (GSL) is a machine learning approach that jointly learns a graph's connectivity, as an adjacency matrix, with a downstream task like node classification.

A graph transformer is a neural network that applies transformer-style self-attention to graph-structured data, adding positional and structural encodings or message-passing layers; Graphormer won the 2021 OGB Large-Scale Challenge for molecular property prediction.

Graph traversal

Graph traversal is an algorithmic technique for visiting every vertex of a graph, typically by depth-first search or breadth-first search, used for shortest paths, cycle detection, and reachability.

GeneralOct 22, 2026

GraphAF

GraphAF is a deep generative model that builds molecules one atom at a time on a graph, proposed by Chence Shi and colleagues in 2020 and published at ICLR 2020.

Grapheme-to-phoneme conversion

Grapheme-to-phoneme conversion (G2P) is the natural language processing task of predicting a word's pronunciation from its written form, a core component of text-to-speech synthesis and automatic speech recognition.

GeneralOct 22, 2026

Graphormer

Graphormer is a graph Transformer architecture for graph-level prediction, introduced at NeurIPS 2021 by Microsoft Research Asia, and the first Transformer-based model to outperform graph neural networks on these benchmarks.

GraphQL

GraphQL is a query language and execution engine for APIs, created at Facebook in 2012, open-sourced in 2015, and governed by the GraphQL Foundation since 2019.

GraphSAGE

GraphSAGE (Graph Sample and Aggregate) is an inductive framework introduced by Hamilton, Ying, and Leskovec at Stanford in NIPS 2017 that learns node embeddings by sampling and aggregating neighborhood features.

Grasp detection

Grasp detection is a robotics and computer vision method that predicts feasible poses for a robot gripper to pick up objects, without a known CAD model.

Grasp synthesis

Grasp synthesis is the computational method that produces a stable grasp of a given object for a robotic hand, dividing into analytic and data-driven approaches.

Grasshopper optimization algorithm

The grasshopper optimization algorithm (GOA) is a population-based metaheuristic introduced in 2017 by Saremi, Mirjalili, and Lewis, modeling grasshopper swarming to solve continuous optimization problems.

Gravitational search algorithm

The gravitational search algorithm (GSA) is a population-based metaheuristic introduced by Rashedi, Nezamabadi-pour, and Saryazdi in 2009 that mimics gravitational attraction between masses.

Gray wolf optimizer

The gray wolf optimizer is a swarm intelligence metaheuristic introduced by Mirjalili, Mirjalili, and Lewis in 2014, mimicking wolf pack hierarchy and hunting to minimize continuous optimization problems.

Gray-box model

A gray-box model (also spelled grey-box) is a mathematical model of a dynamical system combining physical structure with data-driven components, offering interpretability and accuracy on limited data.

Grayscale

Grayscale, also spelled greyscale, is a digital image type in which each pixel carries one intensity value rather than separate red, green, and blue components; 8-bit images have 256 levels.

Greedy algorithm

A greedy algorithm is an optimization method that builds a solution step by step, taking the choice of greatest immediate benefit and never reconsidering, optimal for some problems.

GeneralOct 26, 2026

Gretel (company)

Gretel (gretel.ai), founded by Alex Watson, Laszlo Bock, John Myers, and Ali Golshan, was a San Diego synthetic data platform company; Nvidia acquired it in March 2025 for a nine-figure sum above its $320 million valuation.

Grid search

Grid search is an exhaustive hyperparameter tuning method in machine learning: it evaluates every combination of specified parameter values by cross-validation and returns the best-scoring setting.

Grokking (machine learning)

Grokking is a machine learning phenomenon in which a neural network memorizes its training data first, then abruptly achieves perfect generalization long after training accuracy has reached its ceiling.

Grounding DINO

Grounding DINO is an open-set object detection model developed by IDEA Research and introduced on arXiv in 2023, combining the DINO detector with language to detect arbitrary objects described by text prompts.

Group method of data handling

The group method of data handling (GMDH) is a self-organizing algorithm, proposed by A. G. Ivakhnenko in 1968, that builds polynomial networks layer by layer for regression and forecasting.

Group mind (science fiction)

In science fiction, a group mind, or gestalt intelligence, is a consciousness shared by many individuals so the group thinks and decides as one entity.

Group normalization

Group normalization (GN) is a normalization technique for neural networks that divides channels into groups and normalizes within each, keeping accuracy stable regardless of batch size.

Group robustness optimization

Group robustness optimization, or group DRO, is a machine learning training method that minimizes worst-case loss over pre-defined groups rather than average loss, improving worst-group accuracy.

Growth function (VC theory)

The growth function, also called the shatter function or shattering coefficient, is a VC theory quantity counting the maximum distinct labelings a hypothesis class can realize on n points.