AlphaFree: Recommendation Free from Users, IDs, and GNNs

TL;DR

AlphaFree introduces a novel recommendation approach that eliminates the need for user IDs, embeddings, and GNNs, leveraging language representations and contrastive learning to improve performance and reduce memory costs.

Contribution

It proposes a completely ID-free, user-free, and GNN-free recommendation method using language representations and contrastive learning, addressing limitations of existing systems.

Findings

Outperforms existing methods with up to 40% improvement.

Reduces GPU memory usage by up to 69%.

Achieves up to 5.7% better accuracy over LR-based methods.

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.