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 ist ein Lidar-Inertial-SLAM-Framework und eine eng gekoppelte Sensor-Fusion-Pipeline. Es fungiert als Factor-Graph-Optimierungs-Engine, die Lidar-Scans und Daten der Inertial Measurement Unit (IMU) kombiniert, um 3D-Punktwolkenkarten zu erstellen und Roboter-Trajektorien zu schätzen. Das System integriert globale Positionsfaktoren, um lokale Koordinaten mit realen Daten abzugleichen. Es verwendet Loop-Closure-Erkennung, um bereits besuchte Orte zu identifizieren und Einschränkungen im Optimierungsgraphen zu erstellen, um akkumulierte globale Drift zu korrigieren. Das Framework deckt Lidar-Inertial-Odometrie, Punktwolkenverarbeitung und Trajektorienoptimierung ab. Es nutzt Sliding-Window-Smoothing für Echtzeit-Odometrie, während es im Hintergrund Kartenoptimierung und inertial-basierte Punkt-Deskewing zur Korrektur von Bewegungsverzerrungen durchführt. Das Toolset enthält Utilities, um generierte 3D-Punktwolkenkarten für die Offline-Analyse in Standard-PCD-Dateiformate zu exportieren.

KnowledgeGraphCourse ist eine strukturierte Sammlung von akademischen Materialien auf Graduiertenniveau, Vorlesungsskripten und einem umfassenden Lehrplan, der sich auf die Theorie und Anwendung von Wissensgraphen konzentriert. Es dient als Markdown-basierte Bildungsressource, die navigierbare Kursmodule und Studienführer bereitstellt. Das Material deckt spezialisierte Forschung zur Integration von Wissensgraphen mit Large Language Models ab, um Halluzinationen zu reduzieren. Es enthält detaillierte Anleitungen zur Verwendung der SPARQL-Sprache zum Speichern groß angelegter Graph-Datensätze und zur Ausführung optimierter Abfragen. Der Lehrplan umfasst ein breites Spektrum an Fähigkeiten, einschließlich Wissensextraktion, Entitätsverknüpfung, Repräsentationslernen und semantischer Datenintegration. Er befasst sich zudem mit Wissensmodellierung, Schlussfolgerungen (Reasoning) und der Zusammenführung heterogener Datenquellen.

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 ist ein Framework für Knowledge-Graph-Embeddings, das entwickelt wurde, um strukturierte Wissensgraphen in niedrigdimensionale Vektordarstellungen zu transformieren. Es fungiert als Bibliothek für Repräsentationslernen und als Toolset zur Konvertierung von Entitäten und Beziehungen in numerische Embeddings. Das Projekt enthält eine Link-Prediction-Engine, um die Wahrscheinlichkeit von Beziehungen zwischen Entitäten zu bewerten und fehlende Fakten in groß angelegten Graphen zu identifizieren. Es bietet ein dediziertes Vorverarbeitungstool, um rohe Entitäts- und Beziehungs-Strings für das Machine-Learning-Training in numerische Identifikatoren abzubilden. Die Funktionen des Frameworks decken den gesamten Lebenszyklus von Graph-Embeddings ab, einschließlich Datenvorverarbeitung, Repräsentationslernen und Link-Prediction-Analyse.

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)

Cnn_graph is a graph convolutional network framework and graph signal processing library designed for machine learning research. It provides computational notebooks and code to process and classify graph-structured data by combining node features with an underlying adjacency matrix representation. The framework performs spectral graph convolutions through localized filters and accelerates filtering operations using truncated Chebyshev polynomials to avoid explicit graph Laplacian diagonalization. It includes a graph-structured data pipeline and sparse adjacency representations to handle irreg

Graph Nets is a graph neural network library and educational toolkit implemented in PyTorch, providing implementations of popular graph representation learning algorithms and research papers. The project covers core graph machine learning tasks including semi-supervised node classification, inductive and unsupervised node embedding generation, and neighborhood feature aggregation. The library supports diverse algorithmic approaches for processing network structures, ranging from shared-parameter graph convolutions and attention-weighted neighborhood aggregation to spectral Chebyshev filtering

GraphTransformerNetworks is a graph neural network framework implemented in PyTorch for learning structural representations and performing classification tasks on complex heterogeneous graphs and relational networks. The project provides automated preprocessing pipelines to transform raw graph datasets into standardized formats, alongside model training, forward passes, and gradient backpropagation executed through dynamic tensor operations. The architecture incorporates self-attention mechanisms applied directly to graph structures to learn contextual representations of nodes and edges ac

Dieses Repository dient als Bildungsressource für die Implementierung von Graph Neural Networks mit Python. Es bietet eine Sammlung strukturierter Codebeispiele und Tutorials, die Entwickler durch den Prozess des Aufbaus und Trainings von Machine-Learning-Modellen führen, die auf komplexen, miteinander verbundenen Datensätzen operieren. Das Projekt deckt die Kernmechaniken des graphbasierten Deep Learnings ab, einschließlich Message-Passing-Architekturen, Feature-Aggregation und dem Stapeln von Convolutional Layers. Es demonstriert, wie man nicht-euklidische Daten als statische Graphen darstellt und wie man den Speicher während des Trainings durch Mini-Batch-Sampling-Techniken verwaltet. Die enthaltenen Implementierungen adressieren gängige analytische Aufgaben wie Knotenklassifizierung, Graph-Strukturvorhersage und die Integration heterogener Datenquellen in einheitliche Modelle. Das Repository ist als eine Reihe praktischer Übungen organisiert, die theoretische Graph-Konzepte in funktionale Machine-Learning-Workflows übersetzen.