Cornac: A Comparative Framework for Multimodal Recommender Systems#

Cornac is a comparative framework for multimodal recommender systems. It focuses on making it convenient to work with models leveraging auxiliary data (e.g., item descriptive text and image, social network, etc). Cornac enables fast experiments and straightforward implementations of new models. It is highly compatible with existing machine learning libraries (e.g., TensorFlow, PyTorch).

Quick Links

GitHub | Tutorials | Examples | Models | Datasets | Paper | Preferred.AI

Installation

Start here to get Cornac installed and ready through a step-by-step guide with helpful explanation.

Quickstart Guide

Already got Cornac installed? Start your first experiment by going through this step-by-step guide. This explains the Cornac experiment concept with codes.

Incorporate your Models

Add your own models, datasets and metrics alongside Cornac’s offerings to meet your needs.

This section explains how you can add a new dataset/model/metric so that you can easily run experiments.

Contributing into Cornac

We welcome contributions. Learn how you can contribute to the broader community, including data scientists and engineers using Cornac for research and real-world applications.

Models Available#

Filters