一、基本信息
论文题目：《Neural Collaborative Filtering》
发表时间：WWW 2017
作者及单位：
二、摘要
In recent years, deep neural networks have yielded immense success on speech recognition, computer vision and natural language processing. However, the exploration of deep neu-ral networks on recommender systems has received relatively less scrutiny. In this work, we strive to develop techniques based on neural networks to tackle the key problem in rec-ommendation — collaborative filtering — on the basis of implicit feedback.
Although some recent work has employed deep learning for recommendation, they primarily used it to model auxil-iary information, such as textual descriptions of items and acoustic features of musics. When it comes to model the key factor in collaborative filtering — the interaction between user and item features, they still resorted to matrix factor-ization and applied an inner product on the latent features of users and items.
By replacing the inner product with a neural architecture that can learn an arbitrary function from data, we present a general framework named NCF, short for Neural network-based Collaborative Filtering. NCF is generic and can ex-press and generalize matrix factorization under its frame-work. To supercharge NCF modelling with non-linearities, we propose to leverage a multi-layer perceptron to learn the user–item interaction function. Extensive experiments on two real-world datasets show significant improvements of our proposed NCF framework over the state-of-the-art methods. Empirical evidence shows that using deeper layers of neural networks offers better recommendation performance.
三、主要内容与工作
1、Although some recent advances [37, 38, 45] have applied DNNs to recommendation tasks and shown promising results, they mostly used DNNs to model auxil-iary information, such as textual description of items, audio features of musics, and visual content of images. With re-gards to modelling the key collaborative filtering effect, they still resorted to MF, combining user and item latent features using an inner product.
2、
- We present a neural network architecture to model latent features of users and items and devise a gen-eral framework NCF for collaborative filtering based on neural networks.
- We show that MF can be interpreted as a specialization of NCF and utilize a multi-layer perceptron to endow NCF modelling with a high level of non-linearities.
- We perform extensive experiments on two real-world datasets to demonstrate the effectiveness of our NCF approaches and the promise of deep learning for col-laborative filtering.
3、矩阵分解方法的不足：
本文提出的NCF模型：
NMF模型
四、总结
As the focus of the paper is on the neural network modelling part, we leave the extension to pairwise learning of NCF as a future work.
在这项工作中，我们探索了协同过滤的神经网络架构。我们设计了一个通用框架NCF，并提出了三个实例——GMF、MLP和NEUMF——它们以不同的方式对用户-项目交互进行建模。我们的框架简单而通用；它不仅限于本文中提出的模型，而且被设计为开发推荐的深度学习方法的指导方针。这项工作补充了主流的浅层合作过滤模式，为基于深度学习的推荐提供了一条新的研究途径。
在未来，我们将研究NCF模型的成对学习者，并将NCF扩展到模型辅助信息，如用户评论[11]、知识库[45]和时间信号[1]。虽然现有的个性化模型主要集中在个人身上，但为用户群体开发模型很有意思，这有助于社会群体的决策[15，42]。此外，我们对为多媒体项目构建推荐系统特别感兴趣，这是一项有趣的任务，但在推荐界受到的审查相对较少[3]。多媒体项目，如图像和视频，包含更丰富的视觉语义[16，41]，可以反映用户的兴趣。为了建立一个多媒体推荐系统，我们需要开发有效的方法来从多视图和多模式数据中学习[13，40]。另一个新兴的方向是探索重复租用神经网络和散列方法的潜力[46]以提供有效的在线推荐[14，1]。