@article{Wang_Mao_He_Zhao_Jaakkola_Katabi_2019, title={Bidirectional Inference Networks:A Class of Deep Bayesian Networks for Health Profiling}, volume={33}, url={https://ojs.aaai.org/index.php/AAAI/article/view/3855}, DOI={10.1609/aaai.v33i01.3301766}, abstractNote={<p>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 <em>bidirectional inference networks</em> (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 <em>composite BIN</em> (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 <em>a single model</em> that can achieve state-of-the-art performance and obtain better accuracy in most inference tasks than <em>multiple models each specifically trained for a different task</em>.</p>}, number={01}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Wang, Hao and Mao, Chengzhi and He, Hao and Zhao, Mingmin and Jaakkola, Tommi S. and Katabi, Dina}, year={2019}, month={Jul.}, pages={766-773} }