English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Plug-In Diffusion Model for Sequential Recommendation (AAAI 2024)

Forum topic · 小凯 · 2026-07-05

Summary

This AAAI 2024 paper introduces a plug-in diffusion model for sequential recommendation. Rather than replacing an existing recommender end-to-end, the approach uses a pretrained diffusion model as a plug-in module that refines or augments the top-K items produced by a base sequential recommender, leveraging diffusion-based guidance to better capture user intent and improve ranking quality. Sequential recommendation models predict a user's next interactions from behavior histories, but they often struggle with noisy signals and imprecise ranking of candidate items. By applying diffusion model sampling guided by the user's representation and the base model's outputs, the method denoises and enhances the candidate distribution, yielding better top-K recommendations. Experiments on public sequential recommendation benchmarks show consistent improvements over strong Transformer-based baselines while remaining model-agnostic and easy to integrate. The work demonstrates that generative diffusion models can serve as effective, lightweight enhancement modules for recommendation systems, complementing the broader trend of applying generative models (including LLMs) to search, recommendation, and personalization.

Plug-In Diffusion Model for Sequential Recommendation (AAAI 2024)

Overview

This paper, published at AAAI 2024, proposes a plug-in diffusion model for sequential recommendation. The key idea is not to build a standalone generative recommender, but to attach a pretrained diffusion model on top of an existing sequential recommendation model as a plug-in enhancement module.

Background and Motivation

Sequential recommendation predicts a user's next interaction based on their historical behavior sequence. Mainstream approaches (e.g., GRU4Rec, SASRec, BERT4Rec) encode behavior sequences and score candidate items, but they commonly suffer from:

  • Noisy or ambiguous behavioral signals, where clicked items do not necessarily reflect true intent;
  • Imprecise top-K ranking, especially for items just outside the user's immediate affinity boundary;
  • Limited ability to model the *distribution* over plausible next items rather than a point estimate.
  • Diffusion models have shown strong capability in generative modeling by learning to iteratively denoise data. The authors leverage this to refine the item distribution implied by a base recommender.

    Method

    The proposed framework operates as a plug-in stage after a base sequential recommender:

    1. Base recommender: an off-the-shelf sequential model produces user representations and a set of top-K candidate items. 2. Diffusion-based augmentation: a diffusion model, conditioned on the user representation and behavior sequence, refines/augments the top-K items by sampling from a denoised distribution over items, guided by the user's intent. 3. Final ranking: the enhanced item set improves the final top-K recommendation quality.

    Because the diffusion module is trained to complement rather than replace the base model, the approach is model-agnostic and can be combined with different underlying recommenders.

    Contributions

  • A plug-in architecture that treats a pretrained diffusion model as an enhancement module for existing sequential recommenders.
  • A diffusion-based mechanism that denoises and augments the top-K candidates using guidance from user representations.
  • Empirical results on standard sequential recommendation benchmarks showing improvements over strong baselines, with the plug-in design transferring across different base models.
  • Position in the Field

    This work sits within the growing line of research applying generative models to recommendation:

  • Generative recommenders (e.g., EAGER, P5/item-ID indexing work) treat generation itself as the recommendation mechanism.
  • Sequence encoders (BERT4Rec, Mamba4Rec) improve behavioral sequence modeling efficiency and accuracy.
  • This paper instead shows that diffusion models can serve as a complementary refinement stage, bridging discriminative sequential models and generative modeling, with practical benefits of reusability and low integration cost.
  • Related Entries

  • BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations
  • EAGER: Two-Stream Generative Recommender with Behavior-Semantic Collaboration
  • Mamba4Rec: Efficient Sequential Recommendation with Selective State Space Models
  • How to Index Item IDs for Recommendation Foundation Models (P5, SIGIR)
  • References

  • Original paper: https://ojs.aaai.org/index.php/AAAI/article/view/28736
> Note: Quantitative results should be verified against the original PDF; this page is based on the paper's abstract and public metadata.

Tags

#diffusion-models#sequential-recommendation#recommender-systems#generative-models#aaai-2024#personalization#deep-learning

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208993