Unleashing the Potential of Neighbors: Diffusion-based Latent Neighbor Generation for Session-based Recommendation

TL;DR

This work tackles data sparsity in session-based recommendation by generating latent neighbors that extend beyond observed user interactions. It introduces DiffSBR, a diffusion-based framework with a retrieval-augmented module to guide generation and a self-augmented module to fuse multi-modal signals, enabling high-quality latent neighbors that enrich session representations. Empirical results across four public datasets show consistent gains over state-of-the-art baselines, driven by the ability to explore the full interest space and align multi-modal semantics. The approach offers a scalable pathway to more accurate and robust SBR, with potential applications in any domain where anonymous session data and multi-modal item content are available.

Abstract

Session-based recommendation aims to predict the next item that anonymous users may be interested in, based on their current session interactions. Recent studies have demonstrated that retrieving neighbor sessions to augment the current session can effectively alleviate the data sparsity issue and improve recommendation performance. However, existing methods typically rely on explicitly observed session data, neglecting latent neighbors - not directly observed but potentially relevant within the interest space - thereby failing to fully exploit the potential of neighbor sessions in recommendation. To address the above limitation, we propose a novel model of diffusion-based latent neighbor generation for session-based recommendation, named DiffSBR. Specifically, DiffSBR leverages two diffusion modules, including retrieval-augmented diffusion and self-augmented diffusion, to generate high-quality latent neighbors. In the retrieval-augmented diffusion module, we leverage retrieved neighbors as guiding signals to constrain and reconstruct the distribution of latent neighbors. Meanwhile, we adopt a training strategy that enables the retriever to learn from the feedback provided by the generator. In the self-augmented diffusion module, we explicitly guide the generation of latent neighbors by injecting the current session's multi-modal signals through contrastive learning. After obtaining the generated latent neighbors, we utilize them to enhance session representations for improving session-based recommendation. Extensive experiments on four public datasets show that DiffSBR generates effective latent neighbors and improves recommendation performance against state-of-the-art baselines.

Figures (7)

• Figure 1: Retrieval-based method vs. generative method. The blue region represents the distribution of the dataset, while the green region denotes the full interest space of the current session. Retrieval-based method can only access interest-aligned neighbors within the intersection of these regions, thus being constrained by observed data. In contrast, the generative method overcomes this limitation by exploring the entire interest space, enabling the generation of potentially relevant but unobserved latent neighbors.
• Figure 2: The overall framework of DiffSBR. The left part is the overall framework, and the right part represents the two main components of our diffusion module: (1) the retrieval-augmented diffusion module, which generates latent neighbors guided by retrieved priors; (2) the self-augmented diffusion module, which leverages the session's own multi-modal information to improve the quality of latent neighbors.
• Figure 3: Effect of retrieval-augmented diffusion module.
• Figure 4: Comparison results of the Latent-Neighbors vs. Observable-Neighbors.
• Figure 5: Qualitative visualization of the Latent-Neighbors and Observable-Neighbors.