Machine learning with graphs

Теги: machine-learning  graphs 

graph-based-deep-learning-literature

Библиотеки, работающие с графами:

  • [pyg] pytorch geometric
  • Networkx
  • Scikit-Network
  • graph-tool
  • dgl.ai
  • igraph
  • networkit
  • nx-cugraph GPU Accelerated Backend for NetworkX
  • RAPIDS cuGraph is a monorepo that represents a collection of packages focused on GPU-accelerated graph analytics, including support for property graphs, remote (graph as a service) operations, and graph neural (GNNs). cuGraph supports the creation and manipulation of graphs followed by the execution of scalable fast graph algorithms. Включает nx-cugraph, a [networkx] backend that provides GPU acceleration to NetworkX with zero code change.
  • SNAP
  • deep snap
  • GraphGym. GraphGym is a platform for designing and evaluating Graph Neural Networks (GNN)
  • Stellar Graph Machine Learning on Graphs
  • Neo4j Graph Algorithms
  • [apache-spark] Unified engine for large-scale data analytics
  • [apache-tinkertop-and-gremlin] Apache TinkerPop™ is a graph computing framework for both graph databases (OLTP) and graph analytic systems (OLAP)
  • SciGraph Represent ontologies and ontology-encoded knowledge in a [neo4j] graph.
  • GraphRAG s a structured, hierarchical approach to Retrieval Augmented Generation (RAG), as opposed to naive semantic-search approaches using plain text snippets. The GraphRAG process involves extracting a knowledge graph out of raw text, building a community hierarchy, generating summaries for these communities, and then leveraging these structures when perform RAG-based tasks.
  • PyTorch-BigGraph Generate embeddings from large-scale graph-structured data.

  • pykeen a Python package for reproducible, facile knowledge graph embeddings

  • Бенчмарк
  • Community detection for NetworkX Louvain Community Detection
  • CSRGraphs - Fast and memory efficient library for large read-only graphs
  • nodevectors some alghoritms, depends on CSRGraphs
  • torchpr (Personalized) Page-Rank computation using PyTorch
  • karateclub is an unsupervised machine learning extension library for NetworkX
  • GraphWorld toolbox for graph learning researchers to systematically test new models on synthetic graph datasets. More info
  • GraphGalery GraphGallery is a gallery for benchmarking Graph Neural Networks (GNNs)

  • Leaderboards allow researchers to keep track of state-of-the-art methods and encourage reproducible research.

  • Tools created by the OSoMe team

  • PySceneDetect Python and OpenCV-based scene cut/transition detection program & library.

Datasets

  • Network Repository. An Interactive Scientific Network Data Repository
  • MovieGraphs A Dataset & Benchmark for Understanding Human-Centric Situations
  • MovieNet A holistic dataset for movie understanding
  • Large graphs datasets
  • konect.cc/networks большая коллекция графовых датасетов с их описанием и подсчитанными метриками (может быть недоступен, смотри репозитории)
    • KONECT Extraction - collection of network extraction tools is part of the KONECT project, i.e., the Koblenz Network Collection, a network analysis project by Jérôme Kunegis. This package contains code for generating the network datasets
    • konect-handbook contains all definitions used by the KONECT projects, covering many aspects of network analysis and corresponding parts of graph theory, as well as definitions of plots, statistics and internal data structures used in KONECT arxiv
    • konect-www kode to generate the website of the KONECT project, by Jérôme Kunegis
    • project maintainer blog

Books, cources

Graph [bd]

Смотри еще: