Matching Novelty While Training: Novel Recommendation Based on Personalized Pairwise Loss Weighting
Matching Novelty While Training: Novel Recommendation Based on Personalized Pairwise Loss Weighting
复制标题
DOI：
10.1109/icdm.2019.00057
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Kachun Lo;Tsukasa Ishigaki
中科院分区：
文献类型：
--
作者：
Kachun Lo;Tsukasa Ishigaki
大多数推荐系统都试图提供高精度的商品预测，但对热门商品却有很大的偏向。如果用户的系统对单调的热门商品有强烈的偏好，那么用户和商品的供应商都将蒙受损失。一个更好的系统还应该考虑项目的新颖性。以往的新推荐工作主要集中在对基于精确度的基本模型生成的TOP-N列表进行重新排序。因此，这些框架是两阶段的，基本上局限于基本模型。此外，在训练基本模型时，公共BRP损失函数以相同的方式对待所有对，一致地抑制应该推荐的有趣的负面项。在本文中，我们提出了一种针对业务流程再造损失函数的个性化成对新颖性加权方法，弥补了业务流程再造的局限性，在不降低精确度的情况下有效地提高了新颖性。基本模型将以损失权重为指导，学习用户偏好，分一步生成新的推荐列表。在3个公开数据集上的综合实验表明，我们的方法在几乎不降低准确率的情况下有效地提高了新颖性。
Most works of recommender system seek to provide highly accurate item prediction while having potentially great bias to popular items. Both users and items' providers will suffer if their system has strong preference for monotonous popular items. A better system should consider also item novelty. Previous works of novel recommendation focus mainly on re-ranking a top-N list generated by an accuracy-focused base model. As a result, these frameworks are 2-stage and essentially limited to the base model. In addition, when training the base model, the common BRP loss function treats all pairs in the same manner, consistently suppresses interesting negative items which should have been recommended. In this work, we propose a personalized pairwise novelty weighting for BPR loss function, which covers the limitations of BPR and effectively improves novelty with marginal loss in accuracy. Base model will be guided by the loss weights to learn user preference and to generate novel suggestion list in 1 stage. Comprehensive experiments on 3 public datasets show that our approach effectively promotes novelty with almost no decrease in accuracy.