Multi-Modal Adversarial Autoencoders for Recommendations of Citations and Subject Labels

Multi-Modal Adversarial Autoencoders for Recommendations of Citations and Subject Labels
复制标题

用于推荐引文和主题标签的多模态对抗自动编码器

DOI:
10.1145/3209219.3209236
复制
发表时间:
2018
期刊:
Proceedings of the 26th Conference on User Modeling, Adaptation and Personalization
影响因子:
--
通讯作者:
Ansgar
Ansgar
中科院分区:
--
文献类型:
--
作者:
Florian;Vagliano;Iacopo;Scherp;Ansgar

文献摘要

参考文献

被引文献

相似文献

我们提出了用于推荐的多模态对抗自动编码器,并在两个不同的任务上对它们进行了评估:引用推荐和主题标签推荐。我们分析了对抗正则化,稀疏性和不同输入方式的影响。通过进行408个实验,我们证明了对抗正则化始终提高了自动编码器的推荐性能。然而,我们证明,这两个任务在项目同现的语义上有所不同,因为在引用的情况下,项目同现类似于相关性,但在主题标签的情况下意味着多样性。我们的研究结果表明,提供部分项目集作为输入是有帮助的,当项目同现相似的相关性。因此,当面对一个新的推荐任务时,考虑项目共现的语义对于选择合适的模型是至关重要的。
We present multi-modal adversarial autoencoders for recommendation and evaluate them on two different tasks: citation recommendation and subject label recommendation. We analyze the effects of adversarial regularization, sparsity, and different input modalities. By conducting 408 experiments, we show that adversarial regularization consistently improves the performance of autoencoders for recommendation. We demonstrate, however, that the two tasks differ in the semantics of item co-occurrence in the sense that item co-occurrence resembles relatedness in case of citations, yet implies diversity in case of subject labels. Our results reveal that supplying the partial item set as input is only helpful, when item co-occurrence resembles relatedness. When facing a new recommendation task it is therefore crucial to consider the semantics of item co-occurrence for the choice of an appropriate model.
用于实用信息检索的词嵌入
DOI: --
发表时间: 2017
期刊: GI-Jahrestagung
影响因子: --
作者:
Lukas Galke;Ahmed Saleh;A. Scherp
通讯作者: A. Scherp
根据观察到的用户行为为虚拟大学提供建议
DOI: --
发表时间: 2002
期刊:
影响因子: --
作者:
A. Geyer;Michael Hahsler;Maximillian Jahn
通讯作者: Maximillian Jahn
集体使用的意义:预测 Twitter 上的语义主题标签类别
DOI: --
发表时间: 2013
期刊: The Web Conference
影响因子: --
作者:
Lisa Posch;Claudia Wagner;Philipp Singer;M. Strohmaier
通讯作者: M. Strohmaier
用于自动主题索引的描述符不变融合架构
DOI: --
发表时间: 2017
期刊: ACM/IEEE Joint Conference on Digital Libraries
影响因子: --
作者:
Martin Toepfer;C. Seifert
通讯作者: C. Seifert