Graph Learning

462 papers with code • 1 benchmarks • 8 datasets

Graph learning is a branch of machine learning that focuses on the analysis and interpretation of data represented in graph form. In this context, a graph is a collection of nodes (or vertices) and edges, where nodes represent entities and edges represent the relationships or interactions between these entities. This structure is particularly useful for modeling complex networks found in various domains such as social networks, biological networks, and communication networks.

Graph learning leverages the relationships and structures within the graph to learn and make predictions. It includes techniques like graph neural networks (GNNs), which extend the concept of neural networks to handle graph-structured data. These models are adept at capturing the dependencies and influence of connected nodes, leading to more accurate predictions in scenarios where relationships play a key role.

Key applications of graph learning include recommender systems, drug discovery, social network analysis, and fraud detection. By utilizing the inherent structure of graph data, graph learning algorithms can uncover deep insights and patterns that are not apparent with traditional machine learning approaches.

Libraries

Use these libraries to find Graph Learning models and implementations

Most implemented papers

Learning on Attribute-Missing Graphs

xuChenSJTU/SAT-master-online 3 Nov 2020

Thereby, designing a new GNN for these graphs is a burning issue to the graph learning community.

Bilinear Scoring Function Search for Knowledge Graph Learning

AutoML-Research/AutoSF 1 Jul 2021

We first set up a search space for AutoBLM by analyzing existing scoring functions.

Global Self-Attention as a Replacement for Graph Convolution

shamim-hussain/egt_pytorch 7 Aug 2021

The resultant framework - which we call Edge-augmented Graph Transformer (EGT) - can directly accept, process and output structural information of arbitrary form, which is important for effective learning on graph-structured data.

Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods

cuai/non-homophily-large-scale NeurIPS 2021

Many widely used datasets for graph machine learning tasks have generally been homophilous, where nodes with similar labels connect to each other.

Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs

lfhase/ciga 11 Feb 2022

Despite recent success in using the invariance principle for out-of-distribution (OOD) generalization on Euclidean data (e. g., images), studies on graph data are still limited.

GraphMAE: Self-Supervised Masked Graph Autoencoders

thudm/graphmae 22 May 2022

Despite this, contrastive learning-which heavily relies on structural data augmentation and complicated training strategies-has been the dominant approach in graph SSL, while the progress of generative SSL on graphs, especially graph autoencoders (GAEs), has thus far not reached the potential as promised in other fields.

Topological Deep Learning: Going Beyond Graph Data

pyt-team/topomodelx 1 Jun 2022

Topological deep learning is a rapidly growing field that pertains to the development of deep learning models for data supported on topological domains such as simplicial complexes, cell complexes, and hypergraphs, which generalize many domains encountered in scientific computations.

Graph Matching with Bi-level Noisy Correspondence

Thinklab-SJTU/ThinkMatch ICCV 2023

In this paper, we study a novel and widely existing problem in graph matching (GM), namely, Bi-level Noisy Correspondence (BNC), which refers to node-level noisy correspondence (NNC) and edge-level noisy correspondence (ENC).

Link Prediction without Graph Neural Networks

facebookresearch/SEAL_OGB 23 May 2023

Link prediction, which consists of predicting edges based on graph features, is a fundamental task in many graph applications.