一、基本信息
論文題目：《Neural Collaborative Filtering》
發表時間：WWW 2017
作者及單位：
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、主要內容與工作
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、矩陣分解方法的不足：
本文提出的NCF模型：
NMF模型
四、總結
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.
在這項工作中，我們探索了協同過濾的神經網絡架構。我們設計了一個通用框架NCF，並提出了三個實例——GMF、MLP和NEUMF——它們以不同的方式對用戶-項目交互進行建模。我們的框架簡單而通用；它不僅限於本文中提出的模型，而且被設計爲開發推薦的深度學習方法的指導方針。這項工作補充了主流的淺層合作過濾模式，爲基於深度學習的推薦提供了一條新的研究途徑。
在未來，我們將研究NCF模型的成對學習者，並將NCF擴展到模型輔助信息，如用戶評論[11]、知識庫[45]和時間信號[1]。雖然現有的個性化模型主要集中在個人身上，但爲用戶羣體開發模型很有意思，這有助於社會羣體的決策[15，42]。此外，我們對爲多媒體項目構建推薦系統特別感興趣，這是一項有趣的任務，但在推薦界受到的審查相對較少[3]。多媒體項目，如圖像和視頻，包含更豐富的視覺語義[16，41]，可以反映用戶的興趣。爲了建立一個多媒體推薦系統，我們需要開發有效的方法來從多視圖和多模式數據中學習[13，40]。另一個新興的方向是探索重複租用神經網絡和散列方法的潛力[46]以提供有效的在線推薦[14，1]。