On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenders

• URL: http://arxiv.org/abs/2510.17245v3
• Date: Wed, 22 Oct 2025 12:40:23 GMT
• Title: On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenders
• Authors: Wenyu Mao, Jiancan Wu, Guoqing Hu, Zhengyi Yang, Wei Ji, Xiang Wang,
• Abstract summary: We propose TA-Rec, a two-stage framework that achieves one-step generation by smoothing the denoising function during pretraining.<n>We also introduce Adaptive Preference Alignment (APA) that aligns the denoising process with user preference adaptively based on preference pair similarity and timesteps.<n>Experiments prove that TA-Rec's two-stage objective effectively mitigates the discretization errors-induced trade-off, enhancing both efficiency and effectiveness of diffusion-based recommenders.
• Score: 21.07658297352006
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion models have emerged as a powerful paradigm for generative sequential recommendation, which typically generate next items to recommend guided by user interaction histories with a multi-step denoising process. However, the multi-step process relies on discrete approximations, introducing discretization error that creates a trade-off between computational efficiency and recommendation effectiveness. To address this trade-off, we propose TA-Rec, a two-stage framework that achieves one-step generation by smoothing the denoising function during pretraining while alleviating trajectory deviation by aligning with user preferences during fine-tuning. Specifically, to improve the efficiency without sacrificing the recommendation performance, TA-Rec pretrains the denoising model with Temporal Consistency Regularization (TCR), enforcing the consistency between the denoising results across adjacent steps. Thus, we can smooth the denoising function to map the noise as oracle items in one step with bounded error. To further enhance effectiveness, TA-Rec introduces Adaptive Preference Alignment (APA) that aligns the denoising process with user preference adaptively based on preference pair similarity and timesteps. Extensive experiments prove that TA-Rec's two-stage objective effectively mitigates the discretization errors-induced trade-off, enhancing both efficiency and effectiveness of diffusion-based recommenders.

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)
• Empowering Denoising Sequential Recommendation with Large Language Model Embeddings [18.84444501128626]
  Sequential recommendation aims to capture user preferences by modeling sequential patterns in user-item interactions.<n>To reduce the effect of noise, some works propose explicitly identifying and removing noisy items.<n>We propose a novel framework: Interest Alignment for Denoising Sequential Recommendation (IADSR) which integrates both collaborative and semantic information.
  arXiv  Detail & Related papers  (2025-10-05T15:10:51Z)
• Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization [31.741110625305186]
  We propose using the paradigm of preference optimization to solve the modality bias problem.<n>Specifically, we first construct the dataset by introducing perturbations to reduce the informational content of certain modalities.<n>To address the inevitable noise in automatically constructed data, we combine the noise robust Mean Absolute Error with the Binary Cross Entropy in Direct Preference Optimization.
  arXiv  Detail & Related papers  (2025-03-23T04:00:11Z)
• Dynamic Noise Preference Optimization for LLM Self-Improvement via Synthetic Data [51.62162460809116]
  We introduce Dynamic Noise Preference Optimization (DNPO) to ensure consistent improvements across iterations.<n>In experiments with Zephyr-7B, DNPO consistently outperforms existing methods, showing an average performance boost of 2.6%.<n> DNPO shows a significant improvement in model-generated data quality, with a 29.4% win-loss rate gap compared to the baseline in GPT-4 evaluations.
  arXiv  Detail & Related papers  (2025-02-08T01:20:09Z)
• Dual Conditional Diffusion Models for Sequential Recommendation [63.82152785755723]
  We propose Dual Conditional Diffusion Models for Sequential Recommendation (DCRec)<n>DCRec integrates implicit and explicit information by embedding dual conditions into both the forward and reverse diffusion processes.<n>This allows the model to retain valuable sequential and contextual information while leveraging explicit user-item interactions to guide the recommendation process.
  arXiv  Detail & Related papers  (2024-10-29T11:51:06Z)
• Faster WIND: Accelerating Iterative Best-of-$N$ Distillation for LLM Alignment [81.84950252537618]
  This paper reveals a unified game-theoretic connection between iterative BOND and self-play alignment.<n>We establish a novel framework, WIN rate Dominance (WIND), with a series of efficient algorithms for regularized win rate dominance optimization.
  arXiv  Detail & Related papers  (2024-10-28T04:47:39Z)
• Denoising Pre-Training and Customized Prompt Learning for Efficient Multi-Behavior Sequential Recommendation [69.60321475454843]
  We propose DPCPL, the first pre-training and prompt-tuning paradigm tailored for Multi-Behavior Sequential Recommendation. In the pre-training stage, we propose a novel Efficient Behavior Miner (EBM) to filter out the noise at multiple time scales. Subsequently, we propose to tune the pre-trained model in a highly efficient manner with the proposed Customized Prompt Learning (CPL) module.
  arXiv  Detail & Related papers  (2024-08-21T06:48:38Z)
• Erasing Undesirable Influence in Diffusion Models [51.225365010401006]
  Diffusion models are highly effective at generating high-quality images but pose risks, such as the unintentional generation of NSFW (not safe for work) content. In this work, we introduce EraseDiff, an algorithm designed to preserve the utility of the diffusion model on retained data while removing the unwanted information associated with the data to be forgotten.
  arXiv  Detail & Related papers  (2024-01-11T09:30:36Z)
• Conditional Denoising Diffusion for Sequential Recommendation [62.127862728308045]
  Two prominent generative models, Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs) GANs suffer from unstable optimization, while VAEs are prone to posterior collapse and over-smoothed generations. We present a conditional denoising diffusion model, which includes a sequence encoder, a cross-attentive denoising decoder, and a step-wise diffuser.
  arXiv  Detail & Related papers  (2023-04-22T15:32:59Z)

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.