Neural Utility Functions

Current neural network architectures have no mechanism for explicitly reasoning about item trade-offs. Such trade-offs are important for popular tasks such as recommendation. The main idea of this work is to give neural networks inductive biases that are inspired by economic theories. To this end, we propose Neural Utility Functions, which directly optimize the gradients of a neural network so that they are more consistent with utility theory, a mathematical framework for modeling choice among items. We demonstrate that Neural Utility Functions can recover theoretical item relationships better than vanilla neural networks, analytically show existing neural networks are not quasi-concave and do not inherently reason about trade-offs, and that augmenting existing models with a utility loss function improves recommendation results. The Neural Utility Functions we propose are theoretically motivated, and yield strong empirical results.

[1]  Yiqun Liu,et al.  Economic Recommendation with Surplus Maximization , 2016, WWW.

[2]  E. Ziegel.  Permutation, Parametric, and Bootstrap Tests of Hypotheses (3rd ed.) , 2005 .

[3]  Minyi Guo,et al.  RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems , 2018, CIKM.

[4]  Qi Zhao,et al.  Multi-Product Utility Maximization for Economic Recommendation , 2017, WSDM.

[5]  Yunming Ye,et al.  DeepFM: A Factorization-Machine based Neural Network for CTR Prediction , 2017, IJCAI.

[6]  Lars Schmidt-Thieme,et al.  BPR: Bayesian Personalized Ranking from Implicit Feedback , 2009, UAI.

[7]  Greg M. Allenby,et al.  A Probit Model with Structured Covariance for Similarity Effects and Source of Volume Calculations , 2015 .

[8]  Dwight Merunka,et al.  Neural networks and the multinomial logit for brand choice modelling: a hybrid approach , 2000 .

[9]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[10]  F. Maxwell Harper,et al.  The MovieLens Datasets: History and Context , 2016, TIIS.

[11]  Alexandros Karatzoglou,et al.  Session-based Recommendations with Recurrent Neural Networks , 2015, ICLR.

[12]  Yehuda Koren,et al.  Matrix Factorization Techniques for Recommender Systems , 2009, Computer.

[13]  Heng-Tze Cheng,et al.  Wide & Deep Learning for Recommender Systems , 2016, DLRS@RecSys.

[14]  Yi Tay,et al.  Deep Learning based Recommender System: A Survey and New Perspectives , 2018 .

[15]  Tat-Seng Chua,et al.  Neural Collaborative Filtering , 2017, WWW.

[16]  Jason Yosinski,et al.  Hamiltonian Neural Networks , 2019, NeurIPS.

[17]  A. Mas-Colell,et al.  Microeconomic Theory , 1995 .

[18]  Minyi Guo,et al.  DKN: Deep Knowledge-Aware Network for News Recommendation , 2018, WWW.

[19]  Anton van den Hengel,et al.  Image-Based Recommendations on Styles and Substitutes , 2015, SIGIR.

[20]  Stephen José Hanson,et al.  What connectionist models learn: Learning and representation in connectionist networks , 1990, Behavioral and Brain Sciences.

[21]  W. Nicholson.  Microeconomic theory: basic principles and extensions , 1972 .

[22]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[23]  Hao Li,et al.  Visualizing the Loss Landscape of Neural Nets , 2017, NeurIPS.

[24]  Stefano Ermon,et al.  Tile2Vec: Unsupervised representation learning for spatially distributed data , 2018, AAAI.

[25]  J. Liechty,et al.  Gremlins in the Data: Identifying the Information Content of Research Subjects , 2019, Journal of Marketing Research.

[26]  Jure Leskovec,et al.  Graph Convolutional Neural Networks for Web-Scale Recommender Systems , 2018, KDD.

[27]  Liang Zhang,et al.  Deep reinforcement learning for page-wise recommendations , 2018, RecSys.

[28]  Nicholas Jing Yuan,et al.  DRN: A Deep Reinforcement Learning Framework for News Recommendation , 2018, WWW.

[29]  Florian Heiss,et al.  Discrete Choice Methods with Simulation , 2016 .

[30]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[31]  Greg Linden,et al.  Amazon . com Recommendations Item-to-Item Collaborative Filtering , 2001 .

[32]  Jure Leskovec,et al.  Inferring Networks of Substitutable and Complementary Products , 2015, KDD.

[33]  Yuan Qi,et al.  Generative Adversarial User Model for Reinforcement Learning Based Recommendation System , 2018, ICML.