深度神经网络驱动的协同自动编码器：解决推荐系统挑战

需积分: 13 85 浏览量更新于2024-09-07 收藏 1.27MB PDF 举报

身份认证购VIP最低享 7 折!

30元优惠券

2017年的论文《Collaborative Autoencoder for Recommender Systems》由Qibing Li、Xiaolin Zheng和Xinyue Wu三位来自浙江大学计算机科学学院的研究者共同撰写。该研究关注的是深度学习在推荐系统中的应用，尤其是在解决现有方法存在的三个关键问题。首先，论文指出，尽管近年来深度神经网络在多个任务上表现出卓越性能，但在推荐系统领域，大部分研究倾向于将深度学习与内容特征学习相结合，并依赖矩阵分解技术。这种做法可能无法充分捕捉用户和项目之间复杂且深层次的交互关系，限制了模型对用户行为模式理解的准确性。其次，由于训练深度神经网络的挑战，现有的模型通常采用浅层架构，这意味着它们可能没有充分利用深度学习的强大表达能力。一个深层的模型能够处理更复杂的非线性关系，从而提升推荐的精准度。第三，传统的基于神经网络的推荐模型在处理隐式反馈（如点击或购买行为）时容易过拟合，因为它们往往忽略了负样本（用户未对项目进行的交互）。这可能导致推荐结果偏向于热门商品，而忽视了用户的潜在兴趣。为解决这些问题，作者提出了Neural Collaborative Autoencoder (NCAE)这一通用推荐框架。NCAE旨在通过整合深度学习的优势，同时考虑到用户-项目交互的复杂性以及对负样本的处理，来改进推荐系统的性能。NCAE可能采用了自编码器（Autoencoder）结构，它既能学习内容特征，又能利用神经网络的深层架构，通过重构用户和项目之间的潜在表示来预测用户的兴趣，从而提供更个性化和准确的推荐。总结来说，这篇论文的重点在于提出了一种创新的方法，即利用深度学习的自编码器架构来改进传统推荐系统，以更好地理解和预测用户行为，避免过拟合，并提高推荐质量。这对于理解和优化现代推荐系统具有重要的理论和实践价值。

资源详情

资源推荐

Collaborative Autoencoder for Recommender Systems

Qibing Li

College of Computer Science

Zhejiang University

qblee@zju.edu.cn

Xiaolin Zheng

College of Computer Science

Zhejiang University

xlzheng@zju.edu.cn

Xinyue Wu

College of Computer Science

Zhejiang University

wxinyue@zju.edu.cn

ABSTRACT

In recent years, deep neural networks have yielded state-of-the-art

performance on several tasks. Although some recent works have

focused on combining deep learning with recommendation, we

highlight three issues of existing works. First, most works perform

deep content feature learning and resort to matrix factorization,

which cannot eectively model the highly complex user-item

interaction function. Second, due to the diculty on training deep

neural networks, existing models utilize a shallow architecture, and

thus limit the expressive potential of deep learning. Third, neural

network models are easy to overt on the implicit setting, because

negative interactions are not taken into account. To tackle these

issues, we present a generic recommender framework called Neural

Collaborative Autoencoder (NCAE) to perform collaborative ltering,

which works well for both explicit feedback and implicit feedback.

NCAE can eectively capture the relationship between interactions

via a non-linear matrix factorization process. To optimize the

deep architecture of NCAE, we develop a three-stage pre-training

mechanism that combines supervised and unsupervised feature

learning. Moreover, to prevent overtting on the implicit setting,

we propose an error reweighting module and a sparsity-aware

data-augmentation strategy. Extensive experiments on three real-

world datasets demonstrate that NCAE can signicantly advance

the state-of-the-art.

KEYWORDS

Recommender System, Collaborative Filtering, Neural Network,

Deep Learning

1 INTRODUCTION

In recent years, recommender systems (RS) have played an

signicant role in E-commerce services. A good recommender

system may enhance both satisfaction for users and prot for

content providers. For example, nearly 80% of movies watched on

Netix are recommended by RS [

]. The key to design such a system

is to predict users’ preference on items based on past activities,

which is known as collaborative ltering (CF) [

]. Among the

various CF methods, matrix factorization (MF) [

] is the

most used one, which models the user-item interaction function

as the inner product of user latent vector and item latent vector.

Due to the eectiveness of MF, many integrated models have been

devised, such as CTR [

], HFT [

] and timeSVD [

]. However,

Permission to make digital or hard copies of part or all of this work for personal or

classroom use is granted without fee provided that copies are not made or distributed

for prot or commercial advantage and that copies bear this notice and the full citation

on the rst page. Copyrights for third-party components of this work must be honored.

For all other uses, contact the owner/author(s).

XXX, 2017

ACM ISBN X-XXXXX-XX-X/XX/XX.. . $00.00

https://doi.org/00.0000/0000

MF-based models cannot capture subtle hidden factors, since the

inner product is not sucient for capturing the complex inherent

structure of interaction data [7].

Currently, a trend in the recommendation literature is the

utilization of deep learning to handle the auxiliary information

[

] or directly model the interaction function [

Thus, based on these two usage scenarios, deep learning based

recommender systems can be roughly categorized into integration

models and neural network models [

]. Integration models utilize

deep neural networks to extract the hidden features of auxiliary

information. The features are then integrated into the CF framework

to perform hybrid recommendation. For example, Collaborative

Deep Learning (CDL) [

] integrates Stack Denoising Autoencoder

(SDAE) [

] and PMF [

] into a unied probabilistic graph model

to jointly perform deep content feature learning and collaborative

ltering. Although integration models involve both deep learning

and CF, they actually belong to MF-based models because they use

an inner product to model the interaction data, and thus face the

same issue like MF.

On the other hand, neural network models directly perform

collaborative ltering via utilizing the interaction data. Due to the

eectiveness of deep components, neural network models are able

to discover the non-linear hidden relationships from data [

For example, Collaborative Filtering Network (CFN) [

] is a state-

of-the-art model for explicit feedback, which utilizes DAE [

]

to encode sparse user/item preferences and aims to reconstruct

them in the decoder layer. However, we notice that existing models

do not exploit the representation power of deep architectures,

i.e., generally a shallow network structure is used. This is mainly

caused by two reasons. First, without a proper pre-training strategy,

training deep neural networks is dicult [

]. Second, due to the

sparse nature of RS, conventional layer-wise unsupervised pre-

training [

] does not work in this case

. Besides, existing models

primarily focus on explicit feedback, formulating it as a regression

problem, where negative interactions are not taken into account.

Thus, these models are easy to overt on the implicit setting, since

the models may learn to predict all ratings as 1. Although there

exist implicit neural models like CDAE [

] and NCF [

] that

sample negative feedback from unobserved data, these sample-

based models may fall into poor local optimum due to huge item

space and data sparsity (see Sec. 4.3).

To address the aforementioned issues, we present a new deep

learning based recommender framework called Neural Collaborative

Autoencoder (NCAE) for both explicit feedback and implicit feed-

back. By utilizing a sparse forward module and a sparse backward

module, NCAE is scalable to large datasets and robust to sparse

data. The central idea of NCAE is to learn hidden structures that

can reconstruct user/item preferences via a non-linear matrix

Supervised pre-training in the rst hidden layer is critical to the performance, since

unsupervised reconstruction method may lose user/item information. (see Sec. 4.2)

arXiv:1712.09043v2 [cs.LG] 30 Jan 2018

下载后可阅读完整内容，剩余9页未读，立即下载

Jayxp

粉丝: 6
资源: 137

深度神经网络驱动的协同自动编码器：解决推荐系统挑战

Deep Collaborative Filtering via Marginalized Denoising

2016-Collaborative Denoising Auto-Encoders for Top-N Recommender Systems.pdf

给我推荐20个比较流行的推荐算法模型

s41598-021-96434-0 .pdf

有关网络聊天室的英文参考文献

CARS python

给我推荐20个比较流行的用户画像算法模型源码地址

给我推荐20个比流行的多模态模型

推荐系统算法家族有哪些算法

引用文献介绍基于内容的推荐算法

Quill-collaborative demo

知识图谱的推荐算法都有哪些

Design resources

jupyterhub+notebook

python协同过滤推荐代码详细

把协同过滤的源码实现写给我

推荐系统 itemcf python 代码

就各学者关于信号去噪的方法的研究写一篇文献综述，并给出参考资料

item-based collaborative filtering recommendation algorithm combining item c

最新资源