The Best PyTorch Geometric Alternatives in 2026

Spektral provides a Python framework for creating graph neural networks with Keras and TensorFlow.

pytorch tabular provides a unified framework for deep learning models on tabular data.

This repository implements YOLOv3 variants in PyTorch for real time object detection, training, validation, inference, and export.

Captum explains model behavior and supports interpretability analysis for PyTorch systems.

PyTorch Frame provides a library for applying deep learning models to tabular data.

GPyTorch provides an efficient implementation of Gaussian processes using PyTorch.

Ultralytics YOLOv5 supports object detection, instance segmentation, classification, training, and export in PyTorch.

Little Ball of Fur provides graph sampling extensions for NetworKit and NetworkX.

Giskard provides open source evaluation and testing tools for LLM agents.

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Minimalist neural network library optimized for sparse data and single machine environments.

NALP covers Natural Adversarial Language Processing through a dedicated library.

neuropredict evaluates predictive performance using neuroimaging features.

Adala automates data labeling through an autonomous agent framework for organizing labeled datasets.

Cornac provides a framework for comparing multimodal recommender systems and recommendation algorithms.

Open-RAG-Eval evaluates retrieval-augmented generation without requiring golden answers.

nilearn provides Python tools for machine learning and neuroimaging analysis.

AutoViz automatically creates visualizations for datasets of different sizes from a single line of code.

A Python package to assess and improve fairness of machine learning models.

WhichLLM tests local language models on a user’s hardware and ranks them using recent benchmarks.

The Featuretools Python library supports automated feature engineering and is published as open source.

tsfresh automatically extracts relevant features from time series data.

Snorkel helps generate training data programmatically through weak supervision.

PySS3 supports interpretable text classification with SS3 and visualization tools for explainable AI.