arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2105.07597cs.IRcs.DB
收藏

混合推荐系统中的变带宽自动编码器

Variational Bandwidth Auto-encoder for Hybrid Recommender Systems

Yaochen Zhu, Zhenzhong Chen

摘要:

混合推荐最近吸引了大量的关注,其中用户特征被用作辅助信息,以解决由用户-项目交互不足引起的稀疏性问题。然而,提取的用户特征通常包含丰富的多模态信息,其中大部分与推荐目的无关。因此,过度依赖这些特征会使模型对噪声过拟合,难以推广。在这篇文章中,我们提出了一个变带宽自动编码器(VBAE)的建议,旨在同时解决稀疏性和噪声问题。VBAE首先通过深度神经网络将用户协作和特征信息编码为高斯潜变量,以捕获非线性用户相似性。此外,通过考虑从信息理论的角度来看,作为一个虚拟的通信通道的协作和功能变量的融合,我们引入了一个用户相关的通道,以动态地控制允许从特征嵌入访问的信息。提出了一种基于量子理论的隐藏评分嵌入不确定性度量方法,将评分中的不确定性信息从语义信息中分离出来,从而推断出信道带宽。通过这种机制,VBAE合并足够的辅助信息,从用户功能,如果合作信息不足,同时避免过度依赖嘈杂的用户功能,以提高其泛化能力,以新用户。在三个真实数据集上进行的大量实验证明了该方法的有效性。代码和数据集在https://github.com/yaochenzhu/vbae上发布。

英文摘要:

Hybrid recommendations have recently attracted a lot of attention where user features are utilized as auxiliary information to address the sparsity problem caused by insufficient user-item interactions. However, extracted user features generally contain rich multimodal information, and most of them are irrelevant to the recommendation purpose. Therefore, excessive reliance on these features will make the model overfit on noise and difficult to generalize. In this article, we propose a variational bandwidth auto-encoder (VBAE) for recommendations, aiming to address the sparsity and noise problems simultaneously. VBAE first encodes user collaborative and feature information into Gaussian latent variables via deep neural networks to capture non-linear user similarities. Moreover, by considering the fusion of collaborative and feature variables as a virtual communication channel from an information-theoretic perspective, we introduce a user-dependent channel to dynamically control the information allowed to be accessed from the feature embeddings. A quantum-inspired uncertainty measurement of the hidden rating embeddings is proposed accordingly to infer the channel bandwidth by disentangling the uncertainty information in the ratings from the semantic information. Through this mechanism, VBAE incorporates adequate auxiliary information from user features if collaborative information is insufficient, while avoiding excessive reliance on noisy user features to improve its generalization ability to new users. Extensive experiments conducted on three real-world datasets demonstrate the effectiveness of the proposed method. Codes and datasets are released at https://github.com/yaochenzhu/vbae.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑