Informfully Recommenders -- Reproducibility Framework for Diversity-aware Intra-session Recommendations

TL;DR

This paper introduces Informfully Recommenders, a comprehensive reproducibility framework for diversity-aware recommender systems, enabling standardized experimentation across all pipeline stages to improve diversity optimization and benchmarking.

Contribution

It presents the first normative reproducibility framework supporting diversity-aware design in recommender systems, covering pre-processing, modeling, re-ranking, and evaluation stages.

Findings

Framework supports end-to-end diversity-aware experimentation

Demonstrated effectiveness through extensive offline news domain experiments

Enhances reproducibility and benchmarking in diversity optimization

Abstract

Norm-aware recommender systems have gained increased attention, especially for diversity optimization. The recommender systems community has well-established experimentation pipelines that support reproducible evaluations by facilitating models' benchmarking and comparisons against state-of-the-art methods. However, to the best of our knowledge, there is currently no reproducibility framework to support thorough norm-driven experimentation at the pre-processing, in-processing, post-processing, and evaluation stages of the recommender pipeline. To address this gap, we present Informfully Recommenders, a first step towards a normative reproducibility framework that focuses on diversity-aware design built on Cornac. Our extension provides an end-to-end solution for implementing and experimenting with normative and general-purpose diverse recommender systems that cover 1) dataset pre-processing, 2) diversity-optimized models, 3) dedicated intrasession item re-ranking, and 4) an extensive set of diversity metrics. We demonstrate the capabilities of our extension through an extensive offline experiment in the news domain.