Bayesian inference for neural networks, or Bayesian deep learning, has the potential to provide well-calibrated predictions with quantified uncertainty and robustness.
1 code implementation • 17 Jul 2023 • Xuan Zhang, Limei Wang, Jacob Helwig, Youzhi Luo, Cong Fu, Yaochen Xie, Meng Liu, Yuchao Lin, Zhao Xu, Keqiang Yan, Keir Adams, Maurice Weiler, Xiner Li, Tianfan Fu, Yucheng Wang, Haiyang Yu, Yuqing Xie, Xiang Fu, Alex Strasser, Shenglong Xu, Yi Liu, Yuanqi Du, Alexandra Saxton, Hongyi Ling, Hannah Lawrence, Hannes Stärk, Shurui Gui, Carl Edwards, Nicholas Gao, Adriana Ladera, Tailin Wu, Elyssa F. Hofgard, Aria Mansouri Tehrani, Rui Wang, Ameya Daigavane, Montgomery Bohde, Jerry Kurtin, Qian Huang, Tuong Phung, Minkai Xu, Chaitanya K. Joshi, Simon V. Mathis, Kamyar Azizzadenesheli, Ada Fang, Alán Aspuru-Guzik, Erik Bekkers, Michael Bronstein, Marinka Zitnik, Anima Anandkumar, Stefano Ermon, Pietro Liò, Rose Yu, Stephan Günnemann, Jure Leskovec, Heng Ji, Jimeng Sun, Regina Barzilay, Tommi Jaakkola, Connor W. Coley, Xiaoning Qian, Xiaofeng Qian, Tess Smidt, Shuiwang Ji
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences.
This is enabled by our approximations of infinite potential summations, where we extend the Ewald summation for several potential series approximations with provable error bounds.
Ranked #1 on Band Gap on Materials Project
We consider the prediction of the Hamiltonian matrix, which finds use in quantum chemistry and condensed matter physics.
Proteins are complex biomolecules that perform a variety of crucial functions within living organisms.
There are various sources of ionizing radiation exposure, where medical exposure for radiation therapy or diagnosis is the most common human-made source.
We argue that traditional methods have rarely made use of both times-series dynamics of the data as well as the relatedness of the features from different sensors.
Medical events of interest, such as mortality, often happen at a low rate in electronic medical records, as most admitted patients survive.
At its core is an implicit variational distribution on binary gates that are dependent on previous observations, which will select the next subset of features to observe.
Multi-omics data analysis has the potential to discover hidden molecular interactions, revealing potential regulatory and/or signal transduction pathways for cellular processes of interest when studying life and disease systems.
Moreover, as the EER is not smooth, it can not be combined with gradient-based optimization techniques to efficiently explore the continuous instance space for query synthesis.
The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) emergence began in late 2019 and has since spread rapidly worldwide.
The need for efficient computational screening of molecular candidates that possess desired properties frequently arises in various scientific and engineering problems, including drug discovery and materials design.
In this paper, we fill this gap by investigating knowledge transferability in the context of classification error estimation within a Bayesian paradigm.
We develop a new method -- SimCD -- that explicitly models cell heterogeneity and dynamic differential changes in one unified hierarchical gamma-negative binomial (hGNB) model, allowing simultaneous cell clustering and differential expression analysis for scRNA-seq data.
This interest primarily stems from the amount of compressed information encoded in these exemplars that effectively reflect the major characteristics of the respective clusters.
However, the quality of uncertainty estimation is highly dependent on the dropout probabilities.
For pool-based active learning, in each iteration a candidate training sample is chosen for labeling by optimizing an acquisition function.
In many machine learning tasks, input features with varying degrees of predictive capability are usually acquired at some cost.
High-throughput molecular profiling technologies have produced high-dimensional multi-omics data, enabling systematic understanding of living systems at the genome scale.
Various real-world applications involve modeling complex systems with immense uncertainty and optimizing multiple objectives based on the uncertain model.
Machine learning (ML) systems often encounter Out-of-Distribution (OoD) errors when dealing with testing data coming from a distribution different from training data.
This paper proposes a novel optimization method to solve the exact L0-regularized regression problem, which is also known as the best subset selection.
We propose a unified framework for adaptive connection sampling in graph neural networks (GNNs) that generalizes existing stochastic regularization methods for training GNNs.
Semantic hashing has become a crucial component of fast similarity search in many large-scale information retrieval systems, in particular, for text data.
Activity recognition in wearable computing faces two key challenges: i) activity characteristics may be context-dependent and change under different contexts or situations; ii) unknown contexts and activities may occur from time to time, requiring flexibility and adaptability of the algorithm.
In this work, we propose learnable Bernoulli dropout (LBD), a new model-agnostic dropout scheme that considers the dropout rates as parameters jointly optimized with other model parameters.
Stochastic recurrent neural networks with latent random variables of complex dependency structures have shown to be more successful in modeling sequential data than deterministic deep models.
Representation learning over graph structured data has been mostly studied in static graph settings while efforts for modeling dynamic graphs are still scant.
Ranked #2 on Dynamic Link Prediction on DBLP Temporal
Compared to VGAE, the derived graph latent representations by SIG-VAE are more interpretable, due to more expressive generative model and more faithful inference enabled by the flexible semi-implicit construction.
In either way, the loss of local fine details or global contextual information results in limited segmentation accuracy.
Ranked #4 on Land Cover Classification on DeepGlobe
Missing values frequently arise in modern biomedical studies due to various reasons, including missing tests or complex profiling technologies for different omics measurements.
This power-efficient sensing scheme can be achieved by deciding which group of sensors to use at a given time, requiring an accurate characterization of the trade-off between sensor energy usage and the uncertainty in ignoring certain sensor signals while monitoring.
The first grid-based algorithm has a complexity of $O(m\cdot n^m)$ with $n$ denoting the size of the nondominated set and $m$ the number of objectives.
Second, compared to the number of involved molecules and system complexity, the number of available samples for studying complex disease, such as cancer, is often limited, especially considering disease heterogeneity.
In this paper, we address co-saliency detection in a set of images jointly covering objects of a specific class by an unsupervised convolutional neural network (CNN).
More critically, SAIF has the safe guarantee as it has the convergence guarantee to the optimal solution to the original full LASSO problem.
Next-generation sequencing (NGS) to profile temporal changes in living systems is gaining more attention for deriving better insights into the underlying biological mechanisms compared to traditional static sequencing experiments.
Transfer learning has recently attracted significant research attention, as it simultaneously learns from different source domains, which have plenty of labeled data, and transfers the relevant knowledge to the target domain with limited labeled data to improve the prediction performance.
Since existing prediction models of SSI have quite limited capacity to utilize the evolving clinical data, we develop the corresponding solution to equip these mHealth tools with decision-making capabilities for SSI prediction with a seamless assembly of several machine learning models to tackle the analytic challenges arising from the spatial-temporal data.
For the case when the underlying interaction graph is known to be acyclic, it is shown that a simple algorithm that is based on a maximum-weight spanning tree with respect to the plug-in estimates of the influences not only has strong theoretical performance guarantees, but can also outperform generic feature selection algorithms for recovering the interaction graph from i. i. d.