［干货］Hulu推荐团队论文被ICML录用：推荐算法跻身业内领先地位

日前，Hulu 推荐团队的论文：“A Neural Autoregressive Approach to Collaborative Filtering” （作者：郑胤，唐邦晟，丁文奎，周涵宁）被机器学习领域最高水平的国际会议之一的ICML 2016录用并受邀在会议上做口头报告。这篇论文使用深度学习技术对推荐系统中的核心问题“协同滤波”进行建模，并且在Netflix等公开权威的数据集上显著地提高了推荐性能，达到了目前已知的最好结果。这项工作标志着Hulu在推荐算法领域已经跻身业界领先地位，也将为Hulu未来进一步提升推荐系统性能和用户体验提供帮助。

ICML全称是International Conference on Machine Learning，是由国际机器学习学会（International Machine Learning Society）主办的年度机器学习国际会议。ICML与NIPS并称为当今国际上机器学习领域的两大*会议。今年ICML收到稿件1327篇，录用322篇，录用率24.3%，将于今年6月19日在纽约召开。

本文的第一作者郑胤博士2015年加入Hulu推荐团队，主要研究方向是推荐算法，计算机视觉，深度学习。目前已经在TPAMI（影响因子5.78）、IJCV(影响因子3.81）、CVPR等期刊和会议上有论文发表，并且担任ICML/NIPS/ECCV/ICML/TMM/SPL等会议和期刊的审稿人。

干货奉送

Abstract 

This paper proposes CF-NADE, a neural autoregressive architecture for collaborative filtering (CF) tasks, which is inspired by the Restricted Boltzmann Machine (RBM) based CF model and the Neural Autoregressive Distribution Estimator(NADE). We first describe the basic CF-NADE model for CF tasks. Then we propose to improve the model by utilizing rating-invariant information and sharing parameters between different ratings. A factored version of CF-NADE is also proposed for better scalability. Furthermore,we take the ordinal nature of the preferences into consideration and propose an ordinal cost to optimizeCF-NADE, which shows superior performance. Finally, CF-NADE can be extended to a deep model, with computational complexity increased moderately. Experimental results show that CF-NADE with a single hidden layer outperforms the state-of-the-art methods on MovieLens1M, MovieLens 10M, and Netflix datasets, and adding more hidden layers can further improve the performance.

点击“阅读原文”查看Hulu Beijing热招信息，Come TV with us！