Unleashing the Potential of Neighbors: Diffusion-based Latent Neighbor Generation for Session-based Recommendation
- URL: http://arxiv.org/abs/2601.03903v1
- Date: Wed, 07 Jan 2026 13:14:12 GMT
- Title: Unleashing the Potential of Neighbors: Diffusion-based Latent Neighbor Generation for Session-based Recommendation
- Authors: Yuhan Yang, Jie Zou, Guojia An, Jiwei Wei, Yang Yang, Heng Tao Shen,
- Abstract summary: Session-based recommendation aims to predict the next item that anonymous users may be interested in, based on their current session interactions.<n>Recent studies have demonstrated that retrieving neighbor sessions to augment the current session can effectively alleviate the data sparsity issue.<n>We propose a novel model of diffusion-based latent neighbor generation for session-based recommendation, named DiffSBR.
- Score: 51.74332787641956
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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.
Related papers
- Continuous-time Discrete-space Diffusion Model for Recommendation [25.432419904462694]
CDRec is a novel Continuous-time Discrete-space Diffusion Recommendation framework.<n>It is superior in both recommendation accuracy and computational efficiency.<n>Experiments on real-world datasets demonstrate CDRec's superior performance in both recommendation accuracy and computational efficiency.
arXiv Detail & Related papers (2025-11-15T09:06:57Z) - STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning [54.28691219536054]
We introduce STARec, a slow-thinking augmented agent framework that endows recommender systems with autonomous deliberative reasoning capabilities.<n>We develop anchored reinforcement training - a two-stage paradigm combining structured knowledge distillation from advanced reasoning models with preference-aligned reward shaping.<n>Experiments on MovieLens 1M and Amazon CDs benchmarks demonstrate that STARec achieves substantial performance gains compared with state-of-the-art baselines.
arXiv Detail & Related papers (2025-08-26T08:47:58Z) - Hierarchical Intent-guided Optimization with Pluggable LLM-Driven Semantics for Session-based Recommendation [22.653549796453426]
Session-based Recommendation (SBR) aims to predict the next item a user will likely engage with, using their interaction sequence within an anonymous session.<n>Existing SBR models often focus only on single-session information, ignoring inter-session relationships and valuable cross-session insights.<n>We propose a novel hierarchical intent-guided optimization approach with pluggable LLM-driven semantic learning for session-based recommendations, called HIPHOP.
arXiv Detail & Related papers (2025-07-07T02:50:04Z) - SessionRec: Next Session Prediction Paradigm For Generative Sequential Recommendation [20.51953517144625]
We introduce SessionRec, a novel next-session prediction paradigm (NSPP) for generative sequential recommendation.<n>Unlike NIPP's item-level autoregressive generation that contradicts actual session-based user interactions, our framework introduces a session-aware representation learning.<n>We found that incorporating a rank loss for items within the session under the next session prediction paradigm can significantly improve the ranking effectiveness of generative sequence recommendation models.
arXiv Detail & Related papers (2025-02-14T13:36:20Z) - Bridging User Dynamics: Transforming Sequential Recommendations with Schrödinger Bridge and Diffusion Models [49.458914600467324]
We introduce the Schr"odinger Bridge into diffusion-based sequential recommendation models, creating the SdifRec model.
We also propose an extended version of SdifRec called con-SdifRec, which utilizes user clustering information as a guiding condition.
arXiv Detail & Related papers (2024-08-30T09:10:38Z) - RecDiff: Diffusion Model for Social Recommendation [14.514770044236375]
We propose a novel diffusion-based social denoising framework for recommendation (RecDiff)
By performing multi-step noise diffusion and removal, RecDiff possesses a robust ability to identify and eliminate noise from encoded user representations.
The results demonstrate its superiority in terms of recommendation accuracy, training efficiency, and denoising effectiveness.
arXiv Detail & Related papers (2024-06-01T10:20:52Z) - Diffusion Recommender Model [85.9640416600725]
We propose a novel Diffusion Recommender Model (named DiffRec) to learn the generative process in a denoising manner.<n>To retain personalized information in user interactions, DiffRec reduces the added noises and avoids corrupting users' interactions into pure noises like in image synthesis.
arXiv Detail & Related papers (2023-04-11T04:31:00Z) - SimCGNN: Simple Contrastive Graph Neural Network for Session-based
Recommendation [13.335104151715946]
Session-based recommendation problem focuses on next-item prediction for anonymous users.
Existing graph-based SBR methods all lack the ability to differentiate between sessions with the same last item.
This paper presents a Simple Contrastive Graph Neural Network for Session-based Recommendation (SimCGNN)
arXiv Detail & Related papers (2023-02-08T11:13:22Z) - Neighborhood Mixup Experience Replay: Local Convex Interpolation for
Improved Sample Efficiency in Continuous Control Tasks [60.88792564390274]
Neighborhood Mixup Experience Replay (NMER) is a geometrically-grounded replay buffer that interpolates transitions with their closest neighbors in state-action space.
We observe that NMER improves sample efficiency by an average 94% (TD3) and 29% (SAC) over baseline replay buffers.
arXiv Detail & Related papers (2022-05-18T02:44:08Z) - Dynamic Bottleneck for Robust Self-Supervised Exploration [84.78836146128236]
We propose a Dynamic Bottleneck (DB) model, which attains a dynamics-relevant representation based on the information-bottleneck principle.
Based on the DB model, we further propose DB-bonus, which encourages the agent to explore state-action pairs with high information gain.
Our experiments show that exploration with DB bonus outperforms several state-of-the-art exploration methods in noisy environments.
arXiv Detail & Related papers (2021-10-20T19:17:05Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.