相关性视觉对抗贝叶斯个性化排序推荐模型

Correlation Visual Adversarial Bayesian Personalized Ranking Recommendation Model

传统推荐模型存在数据稀疏、鲁棒性较低问题,且未能有效挖掘异构特征间的深层语义。为解决以上问题,提出相关性视觉对抗贝叶斯个性化排序(correlation visual adversarial Bayesian personalized ranking,CVABPR)推荐模型。首先,基于MovieLens数据集中的电影标题,在互联网电影资料库(Internet movie database,IMDB)爬取对应电影海报图像,构建全新多模态数据集MovieLens–100k–WMI和MovieLens–1M–WMI。其次,基于SENet模型提取一组具有互补性的异构特征,准确描述电影海报图像。然后,改进聚类典型相关性分析模型,深入挖掘异构SENet特征间的聚类典型相关性特征;基于该相关性特征优化视觉贝叶斯个性化排序模型,精准刻画待推荐电影。最后,在推荐模型中加入扰动因子,通过对抗学习来增强推荐模型鲁棒性,使推荐更稳定,生成高质量推荐结果。为验证CVABPR模型,在多模态数据集上完成实验,结果表明:CVABPR模型在这两个数据集上都有效,在MovieLens–100k–WMI数据集上,其推荐的平均精度均值(mean average precision,MAP)较最强基线提升3.802%;在MovieLens–1M–WMI数据集上,其推荐的MAP指标较最强基线提升4.609%。CVABPR模型优于主流基线。消融分析实验表明:相比聚类典型相关性,对抗学习在推荐中发挥更重要的作用。此外,在数据稀疏度更高的MovieLens–1M–WMI数据集上,CVABPR模型能获得更大幅度性能提升,数据稀疏问题得到有效缓解且异构特征间的深层语义也得以充分利用,CVABPR模型已具备较强鲁棒性。

In order to solve three problems of traditional recommendation models,i.e.,data sparsity,low robustness and the lack of deep-level semantics among heterogeneous features,a novel correlation visual adversarial Bayesian personalized ranking(CVABPR)recommendation model was proposed.First,based on the movie titles in the original MovieLens datasets,the corresponding movie posters were downloaded from Internet movie database(IMDB)to construct two multimodal datasets named MovieLens−100k−WMI and MovieLens−1M−WMI,respectively.Second,a group of heterogeneous but complementary image features were extracted using the SENet model to describe movie posters accurately.Then,the cluster canonical correlation analysis model was improved to mine the implicit cluster canonical correlation between the heterogeneous features.Afterwards,the correlation was used to optimize the visual Bayesian personalized ranking(VBPR)model to better depict the movies to be recommended.Finally,a perturbation factor was absorbed into the recommendation model to enhance the robustness of the CVABPR model through adversarial learning,making the recommendation model more stable and generating high-quality recommendation results.To veri-fy the proposed CVABPR model,a set of experiments were carried out on two multimodal datasets.Evident performance improvements of the CVABPR model were observed on the two datasets.Specifically,a 3.802%performance improvement of the mean average precision(MAP)met-ric was obtained on the MovieLens−100k−WMI dataset,and a 4.609%performance improvement of the MAP metric was observed on the MovieLens−1M−WMI dataset.The mainstream baseline was defeated by the CVABPR model.Based on ablative analysis experiments,a more important role of the adversarial learning strategy was found compared with the cluster canonical correlation.Additionally,larger performance improvements were observed on the MovieLens−1M−WMI dataset with higher data sparsity.The key challenges of data sparsity and the lack of deep semantic among heterogeneous features were solved to a certain degree.Meanwhile,the CVABPR model has strong robustness.