11 repositorios
Training approaches that incorporate adversarial objectives to improve classification performance by utilizing both labeled and unlabeled data.
Distinct from Semi-supervised Learning Pipelines: Distinct from Semi-supervised Learning Pipelines: focuses on the classification objective specifically rather than general pipeline configuration.
Explore 11 awesome GitHub repositories matching artificial intelligence & ml · Semi-Supervised Classification. Refine with filters or upvote what's useful.
PyTorch-GAN is a research-oriented framework providing a collection of modular implementations for generative adversarial network architectures. It serves as a toolkit for training and evaluating models that utilize adversarial minimax optimization to produce synthetic data, offering a structured environment for exploring complex generative tasks within the PyTorch ecosystem. The library distinguishes itself through a comprehensive suite of image synthesis and manipulation capabilities, including super-resolution, inpainting, and cross-domain style translation. It supports advanced training m
Leverages unlabeled data alongside small amounts of labeled data to improve classification accuracy by incorporating adversarial training objectives.
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
Predicts labels for individual nodes using semi-supervised or supervised learning techniques on graph-structured data.
Pyannote.audio is a PyTorch toolkit for speaker diarization, speaker identification, and speech activity detection. Its primary purpose is to partition audio recordings into segments and assign each segment to a specific speaker identity to determine who spoke when. The project includes a framework for classifying speaker identities and a pipeline for distinguishing human speech from background noise. It provides specialized tools for handling symmetric-overlap speech, where multiple speakers talk simultaneously, and employs learnable band-pass filters for raw waveform feature extraction. Th
Combines labeled datasets for identity classification with unlabeled audio for representation learning.
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
Predicts labels for unknown nodes in a graph using only a small set of labeled examples.
pygcn es una librería y framework de PyTorch para implementar redes neuronales convolucionales en grafos. Proporciona herramientas para la clasificación de nodos semisupervisada y la generación de embeddings de nodos a partir de datos estructurados en grafos. El sistema convierte los nodos del grafo en vectores de baja dimensión basados en patrones de vecindad y similitudes locales. Permite la predicción de etiquetas de nodos aprovechando tanto un pequeño conjunto de ejemplos etiquetados como la topología general del grafo. La librería cubre el análisis de datos relacionales y el aprendizaje en grafos semisupervisado. Incluye primitivas computacionales para el paso de mensajes, transformación de adyacencia y normalización simétrica.
Predicting labels for specific nodes in a graph by combining known examples with the overall network structure.
Este proyecto es un framework de aprendizaje contrastivo auto-supervisado diseñado para entrenar modelos de aprendizaje profundo para aprender representaciones visuales a partir de imágenes sin utilizar etiquetas proporcionadas por humanos. Proporciona un sistema para desarrollar modelos de representación visual preentrenados que pueden adaptarse para tareas de visión artificial posteriores. El framework incluye herramientas para la clasificación de imágenes semi-supervisada, que combina grandes conjuntos de datos sin etiquetar con pequeños conjuntos etiquetados para mejorar la precisión. También cuenta con una herramienta de evaluación de sonda lineal (linear probe) para evaluar la calidad de las características de imagen aprendidas entrenando un clasificador lineal simple sobre representaciones congeladas. El código base cubre el entrenamiento de aprendizaje profundo distribuido y la aceleración por hardware para manejar grandes tamaños de lote, junto con primitivas de optimización como la programación de tasa de aprendizaje de decaimiento de coseno y regularización de decaimiento de peso. También proporciona utilidades para la gestión de modelos, incluyendo la conversión de checkpoints preentrenados entre diferentes formatos de frameworks de aprendizaje profundo y herramientas para el despliegue de modelos. La implementación se proporciona como una colección de Jupyter Notebooks.
Combines large unlabeled datasets with small labeled sets to improve image classification accuracy.
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
Implements node classification to predict labels for individual nodes using neighbor and structural analysis.
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
Predicts categories or labels for individual network nodes based on their learned numerical representations.
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
Provides capabilities for predicting categorical node classes based on graph structure and attributes.
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
Apply shared filter parameters across graph locations to perform semi-supervised classification on non-euclidean graph data structures.
Este repositorio sirve como recurso educativo para implementar redes neuronales de grafos utilizando Python. Proporciona una colección de ejemplos de código estructurados y tutoriales diseñados para guiar a los desarrolladores a través del proceso de construcción y entrenamiento de modelos de machine learning que operan sobre conjuntos de datos complejos e interconectados. El proyecto cubre la mecánica central del aprendizaje profundo basado en grafos, incluyendo arquitecturas de paso de mensajes, agregación de características y el apilamiento de capas convolucionales. Demuestra cómo representar datos no euclidianos como grafos estáticos y cómo gestionar la memoria durante el entrenamiento mediante técnicas de muestreo por mini-lotes. Las implementaciones incluidas abordan tareas analíticas comunes como la clasificación de nodos, la predicción de estructuras de grafos y la integración de fuentes de datos heterogéneas en modelos unificados. El repositorio está organizado como una serie de ejercicios prácticos que traducen conceptos teóricos de grafos en flujos de trabajo de machine learning funcionales.
Assigns labels to nodes or edges within large datasets to categorize complex network structures for better data organization.