Awesome GitHub RepositoriesGraph Representation Learning

This project is a comprehensive Chinese translation of a technical deep learning textbook, providing an educational resource on the theory and implementation of neural networks. It functions as a collaborative technical translation project designed to make complex academic AI literature accessible to non-English speakers. The project utilizes a community-driven translation model that integrates external suggestions and pull requests to refine linguistic accuracy and reduce bias. It employs standardized terminology mapping to ensure a uniform vocabulary throughout the translated content. To i

This project is a machine learning algorithm reference and implementation guide that provides theoretical foundations and code for supervised learning, deep learning, and natural language processing. It serves as a comprehensive toolkit for implementing predictive models and a technical reference for algorithm engineering. The project focuses on ensemble learning frameworks, including the construction of decision trees, random forests, and gradient boosting models. It also functions as a probabilistic graphical model library and an NLP algorithm reference, with specific implementations for se

DGL is a Python library for building and training graph neural networks. It functions as a graph message passing framework and a geometric deep learning tool, enabling the development of models that analyze graph-structured data. The library is designed for large-scale graph processing, utilizing distributed training and neighbor sampling to handle datasets with billions of edges. It provides specialized support for heterogeneous graph modeling, allowing for the representation of complex real-world entities with multiple node and edge types. Its capabilities cover a wide range of graph tasks

This is a graph convolutional network library designed for performing node and graph classification on graph-structured data. It functions as a framework for generating graph embeddings and implementing spectral convolutional neural networks to predict labels for nodes and entire graph structures. The library provides specialized tools for spectral graph convolutions, utilizing Chebyshev polynomial approximations to perform feature aggregation. It includes a multi-graph processing framework that manages batches of different graph instances through block-diagonal adjacency matrices and pooling

links to conference publications in graph-based deep learning

LIO-SAM este un framework SLAM lidar-inerțial și un pipeline de fuziune a senzorilor cuplată strâns. Acesta funcționează ca un motor de optimizare a grafului de factori care combină scanările lidar și datele unității de măsură inerțială pentru a construi hărți 3D de nori de puncte și a estima traiectoriile roboților. Sistemul integrează factori de poziție globală pentru a alinia coordonatele locale cu datele din lumea reală. Utilizează detectarea închiderii buclei (loop closure) pentru a identifica locațiile vizitate anterior, creând constrângeri în graful de optimizare pentru a corecta drift-ul global acumulat. Framework-ul acoperă odometria lidar-inerțială, procesarea norilor de puncte și optimizarea traiectoriei. Utilizează netezirea prin fereastră glisantă pentru odometrie în timp real, efectuând în același timp optimizarea hărții în fundal și corectarea distorsiunilor de mișcare bazată pe inerție. Setul de instrumente include utilitare pentru a exporta hărțile 3D de nori de puncte generate în formate de fișiere PCD standard pentru analiză offline.

KnowledgeGraphCourse este o colecție structurată de materiale academice de nivel absolvent, note de curs și un curriculum cuprinzător axat pe teoria și aplicarea grafurilor de cunoștințe. Acesta servește ca o resursă educațională bazată pe markdown care oferă module de curs navigabile și ghiduri de studiu. Materialul acoperă cercetări specializate privind integrarea grafurilor de cunoștințe cu modelele de limbaj mari pentru a reduce halucinațiile. Include ghiduri detaliate despre utilizarea limbajului SPARQL pentru stocarea seturilor de date grafice la scară largă și executarea interogărilor optimizate. Curriculum-ul acoperă o gamă largă de capabilități, inclusiv extracția cunoștințelor, legarea entităților, învățarea reprezentărilor și integrarea semantică a datelor. Acesta abordează în continuare modelarea cunoștințelor, raționamentul și fuziunea surselor de date eterogene.

This project is a technical reference guide and sensor-based robotics manual focused on the theoretical foundations and practical implementation of Simultaneous Localization and Mapping. It serves as a knowledge base for spatial AI, covering the integration of deep learning and semantic rendering to create intelligent systems for open world environments. The resource provides guidance on integrating multi-modal sensor data from cameras, LiDAR, radar, and inertial sensors for localization and mapping. It also establishes a bibliographic standard for robotics research by providing systems for m

Memgraph is an in-memory, distributed graph database designed for high-performance labeled property graph management. It utilizes a Cypher query engine for declarative data retrieval and manipulation, providing a scalable knowledge graph backend that integrates vector search and graph traversals. The system distinguishes itself as a real-time graph analytics platform, employing native C++ and CUDA implementations to execute complex network analysis and dynamic community detection on streaming data. It provides specialized support for AI integration, including GraphRAG capabilities, the constr

OpenKE este un framework de embedding pentru grafuri de cunoștințe conceput pentru a transforma grafurile de cunoștințe structurate în reprezentări vectoriale de dimensiuni reduse. Acesta funcționează ca o bibliotecă pentru învățarea reprezentărilor și un set de instrumente pentru convertirea entităților și relațiilor în embedding-uri numerice. Proiectul include un motor de predicție a legăturilor pentru a evalua probabilitatea relațiilor dintre entități și a identifica faptele lipsă în grafuri la scară largă. Oferă un instrument dedicat de preprocesare pentru a mapa șirurile brute de entități și relații în identificatori numerici pentru antrenarea modelelor de machine learning. Capabilitățile framework-ului acoperă întregul ciclu de viață al embedding-ului de grafuri, inclusiv preprocesarea datelor, învățarea reprezentărilor și analiza predicției legăturilor.

GraphEmbedding is a graph network representation library and node embedding framework. It provides a toolkit for transforming complex network nodes into low-dimensional vector spaces, enabling the integration of relational graph data into machine learning workflows. The library functions as a dimensionality reduction toolkit and network topology analysis tool. It uses matrix-factorization techniques to preserve global connectivity and employs random-walk sampling with skip-gram based vector optimization to learn numerical representations of nodes. The framework covers several domain-specific

GraphSAGE is a graph neural network framework designed for inductive representation learning on large-scale graphs. It functions as an inductive graph embedding tool and neighborhood aggregation engine, enabling the generation of numerical node representations that generalize to previously unseen data. The system distinguishes itself by computing node embeddings through the aggregation of features from local neighborhoods rather than relying on a global lookup table. This approach allows the framework to operate as both a supervised graph classifier for predicting categorical node classes and

FAST-LIVO2 is a LiDAR-inertial odometry framework and factor-graph SLAM implementation designed for real-time robot localization and 3D mapping. It functions as a multi-sensor fusion pipeline and state estimator that integrates LiDAR, inertial, and camera inputs to track a robot's position and orientation. The system employs a tightly-coupled sensor fusion approach to maintain stable navigation, particularly in degraded environments. It utilizes a voxel-based 3D mapping tool to organize point clouds into volumetric grids, which optimizes memory usage and search speed during spatial reconstruc

StellarGraph - Machine Learning on Graphs

A curated list of network embedding techniques.

Must-read papers on knowledge representation learning (KRL) / knowledge embedding (KE)

This repository serves as an educational resource for implementing graph neural networks using Python. It provides a collection of structured code examples and tutorials designed to guide developers through the process of building and training machine learning models that operate on complex, interconnected datasets. The project covers the core mechanics of graph-based deep learning, including message-passing architectures, feature aggregation, and the stacking of convolutional layers. It demonstrates how to represent non-Euclidean data as static graphs and how to manage memory during training

Tutorial: Graph Neural Networks for Natural Language Processing at EMNLP 2019 and CODS-COMAD 2020

SMORe: Modularize Graph Embedding for Recommendation