Beyond Interactions: Node-Level Graph Generation for Knowledge-Free Augmentation in Recommender Systems

TL;DR

NodeDiffRec is a novel knowledge-free graph augmentation framework that uses node-level diffusion to generate pseudo-items and interactions, significantly improving recommendation performance without external knowledge.

Contribution

It introduces a pioneering node-level graph generation method for recommendations that expands augmentation primitives via diffusion, surpassing existing knowledge-free approaches.

Findings

Achieves state-of-the-art performance across multiple datasets.

Maximum 98.6% improvement in Recall@5.

Maximum 84.0% improvement in NDCG@5.

Abstract

Recent advances in recommender systems rely on external resources such as knowledge graphs or large language models to enhance recommendations, which limit applicability in real-world settings due to data dependency and computational overhead. Although knowledge-free models are able to bolster recommendations by direct edge operations as well, the absence of augmentation primitives drives them to fall short in bridging semantic and structural gaps as high-quality paradigm substitutes. Unlike existing diffusion-based works that remodel user-item interactions, this work proposes NodeDiffRec, a pioneering knowledge-free augmentation framework that enables fine-grained node-level graph generation for recommendations and expands the scope of restricted augmentation primitives via diffusion. By synthesizing pseudo-items and corresponding interactions that align with the underlying distribution for injection, and further refining user preferences through a denoising preference modeling process, NodeDiffRec dramatically enhances both semantic diversity and structural connectivity without external knowledge. Extensive experiments across diverse datasets and recommendation algorithms demonstrate the superiority of NodeDiffRec, achieving State-of-the-Art (SOTA) performance, with maximum average performance improvement 98.6% in Recall@5 and 84.0% in NDCG@5 over selected baselines.