Can Recommender Systems Teach Themselves? A Recursive Self-Improving Framework with Fidelity Control

2026-02-17

AI Summary

This work addresses the challenge of optimizing recommender systems under scarce high-quality training data, which often leads to poor generalization. To this end, we propose the Recursive Self-Improving Recommender (RSIR) framework, which enables a model to recursively generate user interaction sequences and iteratively augment its own training set without external supervision or a teacher model. RSIR incorporates a fidelity control mechanism to filter synthetically generated interactions that align with the underlying user preference manifold, thereby ensuring data quality. This approach achieves the first unsupervised recursive self-improvement paradigm for recommendation systems, offering implicit regularization benefits and compatibility with diverse model architectures. Extensive experiments demonstrate consistent cumulative performance gains across multiple benchmarks, with notable effectiveness in mitigating data sparsity—enabling even small or weak models to produce meaningful training signals.

Technology Category

• Machine Learning: Unsupervised & Self-Supervised Learning
• Data Mining & Knowledge Management: Recommender Systems
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

The scarcity of high-quality training data presents a fundamental bottleneck to scaling machine learning models. This challenge is particularly acute in recommendation systems, where extreme sparsity in user interactions leads to rugged optimization landscapes and poor generalization. We propose the Recursive Self-Improving Recommendation (RSIR) framework, a paradigm in which a model bootstraps its own performance without reliance on external data or teacher models. RSIR operates in a closed loop: the current model generates plausible user interaction sequences, a fidelity-based quality control mechanism filters them for consistency with user's approximate preference manifold, and a successor model is augmented on the enriched dataset. Our theoretical analysis shows that RSIR acts as a data-driven implicit regularizer, smoothing the optimization landscape and guiding models toward more robust solutions. Empirically, RSIR yields consistent, cumulative gains across multiple benchmarks and architectures. Notably, even smaller models benefit, and weak models can generate effective training curricula for stronger ones. These results demonstrate that recursive self-improvement is a general, model-agnostic approach to overcoming data sparsity, suggesting a scalable path forward for recommender systems and beyond. Our anonymized code is available at https://anonymous.4open.science/r/RSIR-7C5B .

Problem

• recommender systems
• data sparsity
• training data scarcity
• user interactions
• model generalization

Innovation

• Recursive Self-Improvement
• Fidelity Control
• Data Sparsity
• Implicit Regularization
• Model-Agnostic