Cornac: A Comparative Framework for Multimodal Recommender Systems
Aghiles Salah, Quoc Truong, Hady W. Lauw
Abstract
<table><tr>\n <td><p>Cornac\n is an open-source Python framework for multimodal recommender systems. In\n addition to core utilities for accessing, building, evaluating, and comparing\n recommender models, Cornac is distinctive in putting emphasis on\n recommendation models that leverage auxiliary information in the form of a\n social network, item textual descriptions, product images, etc. Such\n multimodal auxiliary data supplement user-item interactions (e.g., ratings,\n clicks), which tend to be sparse in practice. To facilitate broad adoption\n and community contribution, Cornac is publicly available at\n https://github.com/PreferredAI/cornac, and it can be installed via Anaconda\n or the Python Package Index (pip). Not only is it well-covered by unit tests\n to ensure code quality, but it is also accompanied with a detailed\n documentation, tutorials, examples, and several built-in benchmarking data\n sets.<br></p></td></tr></table>