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

2025-08-18

AI Summary

Current recommender systems lack a standardized, reproducible framework covering preprocessing, modeling, post-processing, and evaluation—particularly hindering cross-method comparison of diversity and fairness. To address this, we propose the first end-to-end, diversity-aware, and reproducible framework for session-based recommendation, built upon Cornac. It integrates diversity-optimized models, session-level re-ranking mechanisms, multi-strategy preprocessing, and a unified evaluation metric suite. Our key innovation lies in explicitly embedding social norms into the entire experimental pipeline, enabling configurable, auditable, and reproducible validation of diversity objectives. Extensive offline experiments on large-scale news recommendation datasets demonstrate that the framework significantly improves recommendation diversity (+12.7% nDCG@10-Div) while ensuring experimental transparency and result comparability across studies.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Machine Learning: Learning Preferences or Rankings
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Lack of reproducibility framework for norm-driven recommender systems
• Need diversity-aware design in pre-processing to evaluation stages
• Absence of end-to-end solution for diversity-optimized recommender systems

Innovation

• Normative reproducibility framework for diversity-aware recommendations
• End-to-end solution covering all recommender pipeline stages
• Diversity-optimized models and dedicated re-ranking