An Updating Survey for Bayesian Deep Learning (BDL)
This is an updating survey for Bayesian Deep Learning (BDL), an constantly updated and extended version for the manuscript, 'A Survey on Bayesian Deep Learning', published in ACM Computing Surveys 2020.
Bayesian deep learning is a powerful framework for designing models across a wide range of applications. See our Nature Medicine paper for a possible application on healthcare.
Contents
- Survey
- BDL and Recommender Systems
- BDL and Domain Adaptation (and Domain Generalization, Meta Learning, etc.)
- BDL and Healthcare
- BDL and Natural Language Processing (NLP)
- BDL and Computer Vision (CV)
- BDL and Control/Planning
- BDL and Graphs (Link Prediction, Graph Neural Networks, Knowledge Graphs, etc.)
- BDL and Topic Modeling
- BDL and Speech Recognition/Synthesis
- BDL and Forecasting (Time Series Analysis)
- BDL and Distributed/Federated Learning
- BDL and Continual/Life-Long Learning
- BDL and AI4Science
- BDL as a Framework (Miscellaneous)
- Bayesian/Probabilistic Neural Networks as Building Blocks of BDL
Survey
A Survey on Bayesian Deep Learning
by Wang et al., ACM Computing Surveys (CSUR) 2020
[PDF] [Blog] [BDL Framework in 2016]
BDL and Recommender Systems
Collaborative Deep Learning for Recommender Systems
by Wang et al., KDD 2015
[PDF] [Project Page] [2014 Arxiv Version] [Code] [MXNet Code] [TensorFlow Code] [Dataset A] [Dataset B] [Jupyter Notebook] [Slides] [Slides (Long)]
Collaborative Recurrent Autoencoder: Recommend while Learning to Fill in the Blanks
by Wang et al., NIPS 2016
[PDF]
Collaborative Knowledge Base Embedding for Recommender Systems
by Zhang et al., KDD 2016
[PDF]
Collaborative Deep Ranking: A Hybrid Pair-Wise Recommendation Algorithm with Implicit Feedback
by Ying et al., PAKDD 2016
[PDF]
Collaborative Variational Autoencoder for Recommender Systems
by Li et al., KDD 2017
[PDF]
Variational Autoencoders for Collaborative Filtering
by Liang et al., WWW 2018
[PDF]
Probabilistic Metric Learning with Adaptive Margin for Top-K Recommendation
by Ma et al., KDD 2020
[PDF]
BDL and Domain Adaptation (and Domain Generalization, Meta Learning, etc.)
Probabilistic Model-Agnostic Meta-Learning
by Finn et al., NIPS 2018
[PDF]
Bayesian Model-Agnostic Meta-Learning
by Yoon et al., NIPS 2018
[PDF]
Recasting Gradient-Based Meta-Learning as Hierarchical Bayes
by Grant et al., ICLR 2018
[PDF]
Reconciling Meta-Learning and Continual Learning with Online Mixtures of Tasks
by Jerfal et al., NIPS 2019
[PDF]
Meta-Learning Probabilistic Inference For Prediction
by Gordon et al., ICLR 2019
[PDF]
Learning to Learn with Variational Information Bottleneck for Domain Generalization
by Du et al., ECCV 2020
[PDF]
Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels
by Patacchiola et al., NIPS 2020
[PDF]
Continuously Indexed Domain Adaptation
by Wang et al., ICML 2020
[PDF]
A Bit More Bayesian: Domain-Invariant Learning with Uncertainty
by Xiao et al., ICML 2021
[PDF]
Domain-Indexing Variational Bayes: Interpretable Domain Index for Domain Adaptation
by Xu et al., ICLR 2023
[PDF]
BDL and Healthcare
Electronic Health Record Analysis via Deep Poisson Factor Models
by Henao et al., JMLR 2016
[PDF]
Structured Inference Networks for Nonlinear State Space Models
by Krishnan et al., AAAI 2017
[PDF]
Causal Effect Inference with Deep Latent-Variable Models
by Louizos et al., NIPS 2017
[PDF]
Black Box FDR
by Tansey et al., ICML 2018
[PDF]
Bidirectional Inference Networks: A Class of Deep Bayesian Networks for Health Profiling
by Wang et al., AAAI 2019
[PDF]
Sampling-free Uncertainty Estimation in Gated Recurrent Units with Applications to Normative Modeling in Neuroimaging
by Hwang et al., UAI 2019
[PDF]
Neural Jump Stochastic Differential Equations
by Jia et al., NIPS 2019
[PDF]
Towards Interpretable Clinical Diagnosis with Bayesian Network Ensembles Stacked on Entity-Aware CNNs
by Chen et al., ACL 2020
[PDF]
Continuously Indexed Domain Adaptation
by Wang et al., ICML 2020
[PDF] [Cross Referenced in BDL and Domain Adaptation]
Assessment of medication self-administration using artificial intelligence
by Zhao et al., Nature Medicine 2021
[PDF]
Neural Pharmacodynamic State Space Modeling
by Hussain et al., ICML 2021
[PDF]
Self-Interpretable Time Series Prediction with Counterfactual Explanations
by Yan et al., ICML 2023
[PDF] [Cross Referenced in BDL and Forecasting (Time Series Analysis)]
BDL and NLP
Sequence to Better Sequence: Continuous Revision of Combinatorial Structures
by Mueller et al., ICML 2017
[PDF]
QuaSE: Sequence Editing under Quantifiable Guidance
by Liao et al., EMNLP 2018
[PDF]
Dispersed Exponential Family Mixture VAEs for Interpretable Text Generation
by Shi et al., ICML 2020
[PDF]
Towards Interpretable Clinical Diagnosis with Bayesian Network Ensembles Stacked on Entity-Aware CNNs
by Chen et al., ACL 2020
[PDF] [Cross Referenced in BDL and Healthcare]
What You Say and How You Say it: Joint Modeling of Topics and Discourse in Microblog Conversations
by Zeng et al., ACL 2020
[PDF]
Latent Diffusion Energy-Based Model for Interpretable Text Modeling
by Yu et al., ICML 2022
[PDF]
Diffusion-LM Improves Controllable Text Generation
by Li et al., NeurIPS 2022
[PDF]
Tractable Control for Autoregressive Language Generation
by Zhang et al., ICML 2023
[PDF]
BDL and Computer Vision
Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
by Eslami et al., NIPS 2016
[PDF]
Efficient Inference in Occlusion-aware Generative Models of Images
by Huang et al., ICLR 2016
[PDF]
Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects
by Kosiorek et al., NIPS 2018
[PDF]
Gaussian Process Prior Variational Autoencoders
by Casale et al., NIPS 2018
[PDF]
Spatially Invariant Unsupervised Object Detection with Convolutional Neural Networks
by Crawford et al., AAAI 2019
[PDF]
Faster Attend-Infer-Repeat with Tractable Probabilistic Models
by Stelzner et al., ICML 2019
[PDF]
Asynchronous Temporal Fields for Action Recognition
by Sigurdsson et al., CVPR 2017
[PDF]
Generalizing Eye Tracking with Bayesian Adversarial Learning
by Wang et al., CVPR 2019
[PDF]
Sequential Neural Processes
by Singh et al., NIPS 2019
[PDF]
SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition
by Lin et al., ICLR 2020
[PDF]
Being Bayesian about Categorical Probability
by Joo et al., ICML 2020
[PDF]
NVAE: A Deep Hierarchical Variational Autoencoder
by Vahdat et al., NIPS 2020
[PDF]
Learning Latent Space Energy-Based Prior Model
by Pang et al., NIPS 2020
[PDF]
Generative Neurosymbolic Machines
by Jiang et al., NIPS 2020
[PDF]
Denoising Diffusion Probabilistic Models
by Ho et al., NIPS 2020
[PDF]
A Causal View of Compositional Zero-shot Recognition
by Atzmon et al., NIPS 2020
[PDF]
Counterfactuals Uncover the Modular Structure of Deep Generative Models
by Besserve et al., ICLR 2020
[PDF]
ROOTS: Object-Centric Representation and Rendering of 3D Scenes
by Chen et al., JMLR 2021
[PDF]