《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (8): 2432-2439.DOI: 10.11772/j.issn.1001-9081.2021061086

• 人工智能 • 上一篇    

融合多模态深度游走与偏差校准因子的推荐模型

武子腾, 宋承云()   

  1. 重庆理工大学 计算机科学与工程学院,重庆 400054
  • 收稿日期:2021-06-25 修回日期:2021-09-14 接受日期:2021-10-15 发布日期:2021-12-27 出版日期:2022-08-10
  • 通讯作者: 宋承云
  • 作者简介:武子腾(1996—),女,河北邯郸人,硕士研究生,主要研究方向:推荐系统、信息检索、数据挖掘;
    宋承云(1988—),男,甘肃靖远人,副教授,博士,CCF会员,主要研究方向:机器学习、图算法、数据挖掘。
  • 基金资助:
    国家自然科学基金资助项目(41804112);重庆理工大学研究生创新项目(clgycx20202093)

Recommendation model incorporating multimodal DeepWalk and bias calibration factor

Ziteng WU, Chengyun SONG()   

  1. College of Computer Science and Engineering,Chongqing University of Technology,Chongqing 400054,China
  • Received:2021-06-25 Revised:2021-09-14 Accepted:2021-10-15 Online:2021-12-27 Published:2022-08-10
  • Contact: Chengyun SONG
  • About author:WU Ziteng, born in 1996, M. S. candidate. Her research interests include recommender system, information retrieval, data mining.
    SONG Chengyun, born in 1988, Ph. D., associate professor. His research interests include machine learning, graph algorithm, data mining.
  • Supported by:
    National Natural Science Foundation of China(41804112);Chongqing University of Technology Graduate Innovation Program(clgycx 20202093)

摘要:

曝光偏差严重影响协同过滤模型的推荐精度,导致预测结果偏离用户的真实兴趣,而现有模型对曝光偏差的建模能力有限,甚至放大偏差。为此,提出融合多模态深度游走与偏差校准因子(MmDW-BC)的推荐模型。首先,引入项目多模态属性特征作为项目图的连接边,从而缓解低曝光项目交互数据稀疏的问题;在此基础上,构建图嵌入模块——多模态深度游走(MmDW)将项目多模态信息融入嵌入向量,以获取丰富的节点表示;最后,基于校准策略设计新的偏差校准推荐算法进行用户偏好预测。将提出的模型应用于Amazon和ML-1M数据集上,实验结果验证所提模型明确考虑曝光偏差来提升推荐精度的必要性和有效性。

关键词: 推荐模型, 曝光偏差, 偏差校准, 项目曝光度, 用户活跃度

Abstract:

Exposure bias seriously affects the recommendation accuracy of collaborative filtering model, resulting in the prediction results deviating from the real interests of users. However, the modeling ability of the existing models for exposure bias is limited, and these models even magnify the bias. Therefore, a recommendation model that integrates Multimodal DeepWalk and Bias Calibration factor (MmDW-BC) was proposed. Firstly, the multimodal attribute features of items were introduced as the connected edges in item graph to alleviate the problem of interactive data sparsity of low-exposure items. On this basis, the graph embedding module, Multimodal DeepWalk (MmDW), was constructed to obtain rich node representation by integrating item multimodal information into the embedding vectors. Finally, a new bias calibration algorithm was designed based on the calibration strategy to predict user preferences. Experimental results on Amazon and ML-1M datasets show that definitely considering exposure bias to improve the recommendation accuracy in MmDW-BC recommendation model is necessary and effective.

Key words: recommender model, exposure bias, bias calibration, item exposure, user activity

中图分类号: