Fetching the paper…

Reading the bibliography…

2016

Wide & Deep Learning for Recommender Systems

Cheng, Heng-Tze, Koc, Levent, Harmsen, Jeremiah et al.

Original
PDF
Post on X

Understand

Generalized linear models with nonlinear feature transformations are widely used for large-scale regression and classification problems with sparse inputs.

Memorization of feature interactions through a wide set of cross-product feature transformations are effective and interpretable, while generalization requires more feature engineering effort.
With less feature engineering, deep neural networks can generalize better to unseen feature combinations through low-dimensional dense embeddings learned for the sparse features.
However, deep neural networks with embeddings can over-generalize and recommend less relevant items when the user-item interactions are sparse and high-rank.

Wide & Deep Learning for Recommender Systems · Around

Built on

Adaptive subgradient methods for online learning and stochastic optimization
J. Duchi, E. Hazan, and Y. Singer · 2011
Earlier work this paper cites.
Follow-the-regularized-leader and mirror descent: Equivalence theorems and l1 regularization
H. B. McMahan · 2011
Earlier work this paper cites.
Strategies for training large scale neural network language models
T. Mikolov, A. Deoras, D. Povey, L. Burget, and J. H. Cernocky · 2011
Earlier work this paper cites.

Similar

AppJoy: Personalized mobile application discovery
B. Yan and G. Chen · 2011
Cited alongside, same era.
Factorization machines with libFM
S. Rendle · 2012
Cited alongside, same era.
Joint training of a convolutional network and a graphical model for human pose estimation
J. J. Tompson, A. Jain, Y. LeCun, and C. Bregler · 2014
Cited alongside, same era.

Then

Collaborative deep learning for recommender systems
H. Wang, N. Wang, and D.-Y. Yeung · 2015
Later among the works it cites.
Deep residual learning for image recognition
K. He, X. Zhang, S. Ren, and J. Sun · 2016
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…