AlphaFree: Recommendation Free from Users, IDs, and GNNs

2026-03-03

AI Summary

Traditional recommender systems, which rely on user embeddings, raw IDs, and graph neural networks (GNNs), suffer from high memory consumption, cold-start issues, over-smoothing, and limited generalization. This work proposes AlphaFree, the first recommendation paradigm that operates without user embeddings, raw IDs, or GNNs. AlphaFree leverages a pre-trained language model to map items into semantic representations and integrates online preference inference, similar-item augmentation, and contrastive learning to effectively capture collaborative signals. Evaluated across multiple real-world datasets, AlphaFree substantially outperforms existing approaches, achieving up to a 40% performance gain over non-language baselines and a 5.7% improvement over language-based baselines, while reducing GPU memory usage by as much as 69%.

Technology Category

• Natural Language Processing: (Large) Language Models
• Data Mining & Knowledge Management: Recommender Systems
• Machine Learning: Learning Preferences or Rankings

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Can we design effective recommender systems free from users, IDs, and GNNs? Recommender systems are central to personalized content delivery across domains, with top-K item recommendation being a fundamental task to retrieve the most relevant items from historical interactions. Existing methods rely on entrenched design conventions, often adopted without reconsideration, such as storing per-user embeddings (user-dependent), initializing features from raw IDs (ID-dependent), and employing graph neural networks (GNN-dependent). These dependencies incur several limitations, including high memory costs, cold-start and over-smoothing issues, and poor generalization to unseen interactions. In this work, we propose AlphaFree, a novel recommendation method free from users, IDs, and GNNs. Our main ideas are to infer preferences on-the-fly without user embeddings (user-free), replace raw IDs with language representations (LRs) from pre-trained language models (ID-free), and capture collaborative signals through augmentation with similar items and contrastive learning, without GNNs (GNN-free). Extensive experiments on various real-world datasets show that AlphaFree consistently outperforms its competitors, achieving up to around 40% improvements over non-LR-based methods and up to 5.7% improvements over LR-based methods, while significantly reducing GPU memory usage by up to 69% under high-dimensional LRs.

Problem

• recommender systems
• user embeddings
• cold-start
• over-smoothing
• generalization

Innovation

• user-free recommendation
• ID-free representation
• GNN-free collaboration
• language representations
• contrastive learning