App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 11

Cnp-diff: conditional neighborhood perturbation diffusion for recommendation

Ling Fei1,2
Wen Xilin2
Ma Gangfeng3
Yang Xuhua2
1. School of Digital Technology, Zhejiang Technical Institute of Economics, Hangzhou 310018, China
2. College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, China
3. School of Computer Science and Technology, Zhejiang Normal University, Jinhua Zhejiang 321004, China
DOI: 10.19734/j.issn.1001-3695.2026.04.0066

Abstract

Existing conditional diffusion recommendation models easily suffer from neighbor noise interference under sparse data. To address this issue, this paper proposed a Conditional Neighborhood Perturbation Diffusion (CNP-Diff) model. Specifically, an Adaptive Neighborhood Perturbation (ANP) module is designed, which employs a distribution-aware mechanism to adaptively compute dynamic similarity thresholds for discriminating neighbor quality. It preserves the features of high-confidence strong neighbors to maintain signal fidelity, while applying selective noise perturbations to low-confidence weak neighbors. Subsequently, a gating mechanism fuses the original aggregated features with the perturbed features to generate robust collaborative conditions that guide the reverse denoising process of the diffusion model. Furthermore, consistency regularization is introduced during the training phase to enhance the model's adaptability to dynamic perturbations. Extensive experiments on three public benchmark datasets demonstrate the superiority of the proposed model over state-of-the-art baselines. Especially on the extremely sparse Yelp dataset, the NDCG@10 and Recall@10 metrics are improved by 25.13% and 10.82%, respectively, compared with the best baseline. The proposed model effectively mitigates noise interference caused by static neighborhood aggregation through the adaptive perturbation strategy, significantly enhancing the denoising capability and robustness of generative recommendation systems in sparse scenarios.

Foundation Support

国家自然科学基金资助项目(62503425)
浙江省2025年度高校国内访问学者教师专业发展项目(FX2025174)
浙江经济职业技术学院高层次培育项目(X2025004)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.04.0066
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 11

Publish History

[2026-07-02] Accepted Paper

Cite This Article

凌非, 文茜琳, 马钢峰, 等. CNP-Diff:面向推荐的条件邻域扰动扩散模型 [J]. 计算机应用研究, 2026, 43 (11). (2026-07-31). https://doi.org/10.19734/j.issn.1001-3695.2026.04.0066. (Ling Fei, Wen Xilin, Ma Gangfeng, et al. Cnp-diff: conditional neighborhood perturbation diffusion for recommendation [J]. Application Research of Computers, 2026, 43 (11). (2026-07-31). https://doi.org/10.19734/j.issn.1001-3695.2026.04.0066. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)