基于重复感知与频率增强的动态图推荐研究

吴国栋; 黄雯婧; 鲍宪立; 李景霞; 谢东辰

doi:10.12263/DZXB.20250654

您当前的位置：

首页 >

文章列表页 >

基于重复感知与频率增强的动态图推荐研究

学术论文 | 更新时间：2026-04-24

- 基于重复感知与频率增强的动态图推荐研究
- Research on Dynamic Graph Recommendation Based on Repeat-Aware and Frequency Enhancement
- 电子学报 2025年53卷第12期页码：4429-4443
- 作者机构：
  
  安徽农业大学信息与人工智能学院，安徽合肥 230036
- 作者简介：
  
  [ "吴国栋男，1972年11月出生于安徽省安庆市.现为安徽农业大学副教授、硕士生导师.主要研究方向为人工智能、推荐系统. E-mail: wugd@ahau.edu.cn" ]
  [ "黄雯婧女，2002年12月出生于安徽省合肥市.现为安徽农业大学硕士.主要研究方向为推荐系统.E-mail: 799558789@qq.com" ]
  [ "鲍宪立男，2001年11月出生于安徽省淮南市.现为安徽农业大学硕士.主要研究方向为推荐系统. E-mail: bxl694180128@163.com" ]
  [ "李景霞女，1976年5月出生于安徽省巢湖市.现为安徽农业大学讲师、硕士生导师.主要研究方向为智能推荐、服务计算. E-mail: jxiali@163.com" ]
  [ "谢东辰男，2001年11月出生于江苏省镇江市.现为安徽农业大学硕士.主要研究方向为推荐系统. E-mail: 764361338@qq.com" ]
- 基金信息：
  
  国家自然科学基金(32371993);安徽省高校自然科学研究重点项目(2024AH050443);安徽省自然科学基金(2108085MF209);安徽省科技重大专项(202103b06020013)
- DOI：10.12263/DZXB.20250654
  中图分类号： TP399;
- 收稿：2025-07-28，
  
  录用：2025-12-15，
  
  纸质出版：2025-12-25
- 稿件说明：
移动端阅览
吴国栋, 黄雯婧, 鲍宪立, 等. 基于重复感知与频率增强的动态图推荐研究[J]. 电子学报, 2025, 53(12): 4429-4443.

WU Guo-dong, HUANG Wen-jing, BAO Xian-li, et al. Research on Dynamic Graph Recommendation Based on Repeat-Aware and Frequency Enhancement[J]. Acta Electronica Sinica, 2025, 53(12): 4429-4443.
吴国栋, 黄雯婧, 鲍宪立, 等. 基于重复感知与频率增强的动态图推荐研究[J]. 电子学报, 2025, 53(12): 4429-4443. DOI：10.12263/DZXB.20250654

WU Guo-dong, HUANG Wen-jing, BAO Xian-li, et al. Research on Dynamic Graph Recommendation Based on Repeat-Aware and Frequency Enhancement[J]. Acta Electronica Sinica, 2025, 53(12): 4429-4443. DOI：10.12263/DZXB.20250654

摘要

针对现有图神经网络推荐研究较少考虑历史交互重复行为模式及其时间维度上的频率特性，难以捕获节点交互随时间演变的“偏移”问题，融合重复感知邻居采样与频率域分析，设计了一种基于重复感知与频率增强的动态图推荐模型（Repetition and Frequency-enhance Dynamic Graph Recommendation，ReFDGRec）.ReFDGRec引入一种重复感知邻居采样策略，不仅考虑单个节点的即时邻域，还能深入挖掘已发生过交互的节点对信息，以更精确地识别并挖掘用户与物品之间的高频交互模式，捕捉用户行为的动态演变，从而为模型提供更丰富的输入特征.同时，结合连续小波变换（Continuous Wavelet Transform，CWT）具有的多分辨率分析特征，可以在不同时间尺度上处理用户行为的非平稳性和动态变化，有效捕捉用户行为中的周期性趋势和突发性偏好.通过CWT将用户行为时间序列转换为频率域，以此捕获长周期趋势和短期波动，有效缓解了现有方法在处理用户行为非平稳性时的不足，提升了模型在处理用户突发性偏好和动态兴趣转移时的性能，以提供更精确的个性化推荐.为全面评估模型性能，分别在Wikipedia、UCI、MOOC和MovieLens四个公开数据集上进行了系统实验，涵盖了直推式预测与归纳式预测两种动态图推荐场景，并采用随机、历史及归纳三类负采样策略以确保评估严谨性与公平性.实验结果表明：在平均精度指标上，ReFDGRec相比DySAT、TGAT、TGN、GraphMixer及RepeatMixer等主流基线模型均取得显著的性能提升，实现了平均2.3%~6.9%的性能增益；消融实验验证了节点交互频率编码方法与连续小波变换增强模块在提升模型性能中的关键作用；时频分析方法对比结果显示，连续小波变换在处理非平稳行为序列方面明显优于离散傅里叶变换与短时傅里叶变换.本文通过理论引导的重复感知机制与信号处理驱动的频域增强技术，为动态图推荐系统研究提供了一种能够有效捕获兴趣演化与行为偏移的解决方案，具有一定的理论创新与实践价值.

Abstract

Current graph neural network-based recommendation studies rarely consider the repetitive behavior patterns of historical interactions and their frequency characteristics in the temporal dimension

making it difficult to capture the “shift” in node interactions over time. To address this

we propose a repetition and frequency-enhanced dynamic graph recommendation model (ReFDGRec) that integrates repetition-aware neighbor sampling with frequency domain analysis. ReFDGRec introduces a repetition-aware neighbor sampling strategy that not only considers the immediate neighborhood of individual nodes but also deeply explores node pairs with prior interactions

leveraging relevant historical information to enhance the understanding of node relationships. This approach enables more precise identification and extraction of high-frequency interaction patterns between users and items

capturing the dynamic evolution of user behavior and providing richer input features for the model. Additionally

considering the multi-resolution analysis capabilities of continuous wavelet transform (CWT)

ReFDGRec effectively handles the non-stationarity and dynamic changes in user behavior across different time scales

capturing periodic trends and abrupt preference shifts. By CWT transforming user behavior time series into the frequency domain

it simultaneously captures long-term trends and short-term fluctuations

effectively addressing the limitations of existing methods in handling non-stationary user behavior. This enhances the model’s performance in managing abrupt user preferences and dynamic interest shifts

delivering more accurate personalized recommendation services. To comprehensively evaluate the performance of the proposed model

systematic experiments are conducted on four public datasets

namely Wikipedia

UCI

MOOC

and MovieLens

covering both transductive and inductive dynamic recommendation scenarios. In addition

three negative sampling strategies

including random

historical

and inductive sampling

are employed to ensure the rigor and fairness of the evaluation. Experimental results demonstrate that ReFDGRec consistently outperforms state-of-the-art baseline models such as DySAT

TGAT

TGN

GraphMixer

and RepeatMixer in terms of average precision metrics

achieving an average performance improvement of 2.3%~6.9%. Ablation studies further confirm the critical contributions of the node interaction frequency encoding scheme and the CWT-based enhancement module to the overall performance gains. Moreover

comparative analyses of time-frequency modeling methods indicate that the continuous wavelet transform is markedly more effective than the discrete Fourier transform and the short-time Fourier transform in modeling non-stationary behavioral sequences. By leveraging a theoretically guided repetition-aware mechanism and signal processing-driven frequency-domain enhancement techniques

this work provides a solution for dynamic graph recommendation that effectively captures interest evolution and behavioral drift

and has certain theoretical innovation and practical value.

关键词

Keywords

references

YU J L , YIN H Z , XIA X , et al . Self-supervised learning for recommender systems: A survey [J ] . IEEE Transactions on Knowledge and Data Engineering , 2024 , 36 ( 1 ): 335 - 355 .

GUO Q Y , ZHUANG F Z , QIN C , et al . A survey on knowledge graph-based recommender systems [J ] . IEEE Transactions on Knowledge and Data Engineering , 2022 , 34 ( 8 ): 3549 - 3568 .

WU C , WANG C K , XU J C , et al . Instant representation learning for recommendation over large dynamic graphs [C ] // 2023 IEEE 39th International Conference on Data Engineering . Piscataway : IEEE , 2023 : 82 - 95 .

YUAN H N , SUN Q Y , FU X C , et al . Environment-aware dynamic graph learning for out-of-distribution generalization [EB/OL ] . ( 2023-11-18 )[ 2025-07-24 ] . https://arxiv.org/abs/2311.11114 https://arxiv.org/abs/2311.11114 .

郭向星 , 周魏 , 杨正益 , 等 . 基于自监督图卷积和注意力机制实现隐式反馈降噪的社交推荐 [J ] . 电子学报 , 2025 , 53 ( 1 ): 151 - 162 .

GUO X X , ZHOU W , YANG Z Y , et al . Denoising implicit feedback with self-supervised graph convolution network and attention mechanism for social recommendation [J ] . Acta Electronica Sinica , 2025 , 53 ( 1 ): 151 - 162 . (in Chinese)

FENG Z Z , WANG R , WANG T X , et al . A comprehensive survey of dynamic graph neural networks: Models, frameworks, benchmarks, experiments and challenges [EB/OL ] . ( 2024-05-01 )[ 2025-07-24 ] . https://arXiv.org/abs/2405.00476 https://arXiv.org/abs/2405.00476 .

SHENG Z Z , ZHANG T , ZHANG Y J , et al . Enhanced graph neural network for session-based recommendation [J ] . Expert Systems with Applications , 2023 , 213 : 118887 .

LI J C , WANG Y J , MCAULEY J . Time interval aware self-attention for sequential recommendation [C ] // Proceedings of the 13th International Conference on Web Search and Data Mining . New York : ACM , 2020 : 322 - 330 .

HIDASI B , KARATZOGLOU A . Recurrent neural networks with top-k gains for session-based recommendations [C ] // Proceedings of the 27th ACM International Conference on Information and Knowledge Management . New York : ACM , 2018 : 843 - 852 .

张其 , 陈旭 , 王叔洋 , 等 . 动态图神经网络链接预测综述 [J ] . 计算机工程与应用 , 2024 , 60 ( 20 ): 49 - 67 .

ZHANG Q , CHEN X , WANG S Y , et al . Survey of dynamic graph neural network for link prediction [J ] . Computer Engineering and Applications , 2024 , 60 ( 20 ): 49 - 67 . (in Chinese)

SANKAR A , WU Y H , GOU L , et al . DySAT: Deep neural representation learning on dynamic graphs via self-attention networks [C ] // Proceedings of the 13th International Conference on Web Search and Data Mining . New York : ACM , 2020 : 519 - 527 .

PAREJA A , DOMENICONI G , CHEN J , et al . EvolveGCN: Evolving graph convolutional networks for dynamic graphs [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2020 , 34 ( 4 ): 5363 - 5370 .

SHERSTINSKY A . Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network [J ] . Physica D: Nonlinear Phenomena , 2020 , 404 : 132306 .

TRIVEDI R , FARAJTBABAR M , BISWAL P , et al . Dyrep: Learning representations over dynamic graphs [C ] // Proceedings of the 7th International Conference on Learning Representations , Appleton : ICLR , 2019 .

CHEN Z Y , ZHANG W , YAN J C , et al . Learning dual dynamic representations on time-sliced user-item interaction graphs for sequential recommendation [C ] // Proceedings of the 30th ACM International Conference on Information & Knowledge Management . New York : ACM , 2021 : 231 - 240 .

ZHU Y F , CONG F P , ZHANG D , et al . WinGNN: Dynamic graph neural networks with random gradient aggregation window [C ] // Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining . New York : ACM , 2023 : 3650 - 3662 .

QI Q G , CHEN H Y , CHENG M H , et al . Input snapshots fusion for scalable discrete-time dynamic graph neural networks [C ] // Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V . 1 . New York : ACM , 2025 : 1138 - 1149 .

XU D , RUAN C W , KORPEOGLU E , et al . Inductive representation learning on temporal graphs [EB/OL ] . ( 2020-02-19 )[ 2025-07-24 ] . https://arXiv.org/abs/2002.07962 https://arXiv.org/abs/2002.07962 .

ROSSI E , CHAMBERLAIN B , FRASCA F , et al . Temporal graph networks for deep learning on dynamic graphs [EB/OL ] . ( 2020-10-09 )[ 2025-07-24 ] . https://arXiv.org/abs/2006.10637 https://arXiv.org/abs/2006.10637 .

KUMAR S , ZHANG X K , LESKOVEC J . Predicting dynamic embedding trajectory in temporal interaction networks [C ] // Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining . New York : ACM , 2019 : 1269 - 1278 .

FAN Z W , LIU Z W , ZHANG J W , et al . Continuous-time sequential recommendation with temporal graph collaborative transformer [C ] // Proceedings of the 30th ACM International Conference on Information & Knowledge Management . New York : ACM , 2021 : 433 - 442 .

VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [EB/OL ] . ( 2023-08-02 )[ 2025-07-24 ] . https://arxiv.org/abs/1706.03762 https://arxiv.org/abs/1706.03762 .

ZHANG M Q , WU S , YU X L , et al . Dynamic graph neural networks for sequential recommendation [J ] . IEEE Transactions on Knowledge and Data Engineering , 2023 , 35 ( 5 ): 4741 - 4753 .

TANG H R , WU S Q , XU G D , et al . Dynamic graph evolution learning for recommendation [C ] // Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval . New York : ACM , 2023 : 1589 - 1598 .

YU L , SUN L , DU B , et al . Towards better dynamic graph learning: New architecture and unified library [EB/OL ] . ( 2023-10-19 )[ 2025-07-24 ] . https://arxiv.org/abs/2303.13047 https://arxiv.org/abs/2303.13047 .

CONG W L , ZHANG S , KANG J , et al . Do we really need complicated model architectures for temporal networks? [EB/OL ] . ( 2023-02-22 )[ 2025-07-24 ] . https://arXiv.org/abs/2302.11636 https://arXiv.org/abs/2302.11636 .

DESAI M H , SHAH M . An anatomization on breast cancer detection and diagnosis employing multi-layer perceptron neural network (MLP) and Convolutional neural network (CNN) [J ] . Clinical EHealth , 2021 , 4 : 1 - 11 .

WU S , TANG Y Y , ZHU Y Q , et al . Session-based recommendation with graph neural networks [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2019 , 33 ( 1 ): 346 - 353 .

LI Z C , TANG J H , MEI T . Deep collaborative embedding for social image understanding [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2019 , 41 ( 9 ): 2070 - 2083 .

YU H , LIU J . Community-aware temporal walks: Parameter-free representation learning on continuous-time dynamic graphs [EB/OL ] . ( 2025-01-21 )[ 2025-07-24 ] . https://arXiv.org/abs/2501.11880 https://arXiv.org/abs/2501.11880 .

ZOU T , MAO Y H , YE J C , et al . Repeat-aware neighbor sampling for dynamic graph learning [C ] // Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining . New York : ACM , 2024 : 4722 - 4733 .

IVANOVA I , RZADKOWSKI G . Triple Helix synergy and patent dynamics. cross country comparison [J ] . Quality & Quantity , 2025 , 59 ( 3 ): 2891 - 2923 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于小波域的复数卷积和复数Transformer的轻量级MR图像重建方法

基于分频式生成对抗网络的非成对水下图像增强

两步式自适应阈值法滤除心电信号中运动伪迹

多通道盲电磁辐射现场分离方法研究