Training Deep AutoEncoders for Collaborative Filtering (2017-08-05T00:00:00.000000Z)

TL;DR

A novel model for the rating prediction task in recommender systems which significantly outperforms previous state-of-the art models on a time-split Netflix data set and a new training algorithm based on iterative output re-feeding to overcome natural sparseness of collaborate filtering is proposed.

Abstract

This paper proposes a novel model for the rating prediction task in recommender systems which significantly outperforms previous state-of-the art models on a time-split Netflix data set. Our model is based on deep autoencoder with 6 layers and is trained end-to-end without any layer-wise pre-training. We empirically demonstrate that: a) deep autoencoder models generalize much better than the shallow ones, b) non-linear activation functions with negative parts are crucial for training deep models, and c) heavy use of regularization techniques such as dropout is necessary to prevent over-fiting. We also propose a new training algorithm based on iterative output re-feeding to overcome natural sparseness of collaborate filtering. The new algorithm significantly speeds up training and improves model performance. Our code is available at this https URL

Authors

Boris Ginsburg

3 papers

Oleksii Kuchaiev

3 papers

Training Deep AutoEncoders for Collaborative Filtering

TL;DR

Abstract

Authors

References23 items

Self-Normalizing Neural Networks

Neural Collaborative Filtering

Recurrent Recommender Networks

Collaborative Filtering with Stacked Denoising AutoEncoders and Sparse Inputs

Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)

AutoRec: Autoencoders Meet Collaborative Filtering

Empirical Evaluation of Rectified Activations in Convolutional Network

Matrix Factorization Techniques for Recommender Systems

Collaborative filtering with temporal dynamics

Context-aware recommender systems

Nonnegative Matrix Factorization Based on Alternating Nonnegativity Constrained Least Squares and Active Set Method

Probabilistic Matrix Factorization

Restricted Boltzmann machines for collaborative filtering

Empirical Analysis of Predictive Algorithms for Collaborative Filtering

Autoencoders, Minimum Description Length and Helmholtz Free Energy

Deep Learning

Introduction to Recommender Systems Handbook

The BellKor Solution to the Netflix Grand Prize

Reducing the Dimensionality of Data with Neural

Learning Deep Architectures for AI

The Netflix Prize

and Net ix Net ix

Supporting Online Material for Reducing the Dimensionality of Data with Neural Networks

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names