Bidirectional Inference Networks: A Class of Deep Bayesian Networks for Health Profiling

We consider the problem of inferring the values of an arbitrary set of variables (e.g., risk of diseases) given other observed variables (e.g., symptoms and diagnosed diseases) and high-dimensional signals (e.g., MRI images or EEG). This is a common problem in healthcare since variables of interest often differ for different patients. Existing methods including Bayesian networks and structured prediction either do not incorporate high-dimensional signals or fail to model conditional dependencies among variables. To address these issues, we propose bidirectional inference networks (BIN), which stich together multiple probabilistic neural networks, each modeling a conditional dependency. Predictions are then made via iteratively updating variables using backpropagation (BP) to maximize corresponding posterior probability. Furthermore, we extend BIN to composite BIN (CBIN), which involves the iterative prediction process in the training stage and improves both accuracy and computational efficiency by adaptively smoothing the optimization landscape. Experiments on synthetic and real-world datasets (a sleep study and a dermatology dataset) show that CBIN is a single model that can achieve state-of-the-art performance and obtain better accuracy in most inference tasks than multiple models each specifically trained for a different task.

[1]  J. Besag Spatial Interaction and the Statistical Analysis of Lattice Systems , 1974 .

[2]  C. Sherbourne,et al.  The MOS 36-Item Short-Form Health Survey (SF-36) , 1992 .

[3]  Ware J.E.Jr.,et al.  THE MOS 36- ITEM SHORT FORM HEALTH SURVEY (SF- 36) CONCEPTUAL FRAMEWORK AND ITEM SELECTION , 1992 .

[4]  C. McHorney,et al.  The MOS 36‐Item Short‐Form Health Survey (SF‐36): II. Psychometric and Clinical Tests of Validity in Measuring Physical and Mental Health Constructs , 1993, Medical care.

[5]  J. Samet,et al.  The Sleep Heart Health Study: design, rationale, and methods. , 1997, Sleep.

[6]  J. Larson The MOS 36-Item Short form Health Survey , 1997, Evaluation & the health professions.

[7]  Hugo Larochelle,et al.  The Neural Autoregressive Distribution Estimator , 2011, AISTATS.

[8]  Harry Joe,et al.  Composite Likelihood Methods , 2012 .

[9]  Hugo Larochelle,et al.  RNADE: The real-valued neural autoregressive density-estimator , 2013, NIPS.

[10]  T. Kadir,et al.  Bayesian Networks for Clinical Decision Support in Lung Cancer Care , 2013, PloS one.

[11]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[12]  Christian Osendorfer,et al.  Learning Stochastic Recurrent Networks , 2014, NIPS 2014.

[13]  Joan Bruna,et al.  Intriguing properties of neural networks , 2013, ICLR.

[14]  Quoc V. Le,et al.  Distributed Representations of Sentences and Documents , 2014, ICML.

[15]  Yoshua Bengio,et al.  A Recurrent Latent Variable Model for Sequential Data , 2015, NIPS.

[16]  Dit-Yan Yeung,et al.  Collaborative Deep Learning for Recommender Systems , 2014, KDD.

[17]  Honglak Lee,et al.  Learning Structured Output Representation using Deep Conditional Generative Models , 2015, NIPS.

[18]  Uri Shalit,et al.  Deep Kalman Filters , 2015, ArXiv.

[19]  Hugo Larochelle,et al.  MADE: Masked Autoencoder for Distribution Estimation , 2015, ICML.

[20]  Alex Graves,et al.  DRAW: A Recurrent Neural Network For Image Generation , 2015, ICML.

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

[22]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[23]  Hugo Larochelle,et al.  Neural Autoregressive Distribution Estimation , 2016, J. Mach. Learn. Res..

[24]  Leon A. Gatys,et al.  Image Style Transfer Using Convolutional Neural Networks , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Nicholas Jing Yuan,et al.  Collaborative Knowledge Base Embedding for Recommender Systems , 2016, KDD.

[26]  Ryan P. Adams,et al.  Composing graphical models with neural networks for structured representations and fast inference , 2016, NIPS.

[27]  Dit-Yan Yeung,et al.  Towards Bayesian Deep Learning: A Framework and Some Existing Methods , 2016, IEEE Transactions on Knowledge and Data Engineering.

[28]  Il Memming Park,et al.  BLACK BOX VARIATIONAL INFERENCE FOR STATE SPACE MODELS , 2015, 1511.07367.

[29]  Andrew McCallum,et al.  Structured Prediction Energy Networks , 2015, ICML.

[30]  Dit-Yan Yeung,et al.  Natural-Parameter Networks: A Class of Probabilistic Neural Networks , 2016, NIPS.

[31]  Ole Winther,et al.  Sequential Neural Models with Stochastic Layers , 2016, NIPS.

[32]  Dit-Yan Yeung,et al.  Relational Deep Learning: A Deep Latent Variable Model for Link Prediction , 2017, AAAI.

[33]  Andrew McCallum,et al.  End-to-End Learning for Structured Prediction Energy Networks , 2017, ICML.

[34]  Leon A. Gatys,et al.  Controlling Perceptual Factors in Neural Style Transfer , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  Mohammad Emtiyaz Khan,et al.  Variational Message Passing with Structured Inference Networks , 2018, ICLR.

[36]  Hongyi Zhang,et al.  mixup: Beyond Empirical Risk Minimization , 2017, ICLR.