Transferring knowledge from a teacher neural network pretrained on the same or a similar task to a student neural network can significantly improve the performance of the student neural network. Existing knowledge transfer approaches match the activations or the corresponding handcrafted features of the teacher and the student networks. We propose an information-theoretic framework for knowledge transfer which formulates knowledge transfer as maximizing the mutual information between the teacher and the student networks. We compare our method with existing knowledge transfer methods on both knowledge distillation and transfer learning tasks and show that our method consistently outperforms existing methods. We further demonstrate the strength of our method on knowledge transfer across heterogeneous network architectures by transferring knowledge from a convolutional neural network (CNN) to a multi-layer perceptron (MLP) on CIFAR-10. The resulting MLP significantly outperforms the-state-of-the-art methods and it achieves similar performance to the CNN with a single convolutional layer.

Multi-fidelity modelling enables accurate inference of quantities of interest by synergistically combining realizations of low-cost/low-fidelity models with a small set of high-fidelity observations. This is particularly effective when the low- and high-fidelity models exhibit strong correlations, and can lead to significant computational gains over approaches that solely rely on high-fidelity models. However, in many cases of practical interest, low-fidelity models can only be well correlated to their high-fidelity counterparts for a specific range of input parameters, and potentially return wrong trends and erroneous predictions if probed outside of their validity regime. Here we put forth a probabilistic framework based on Gaussian process regression and nonlinear autoregressive schemes that is capable of learning complex nonlinear and space-dependent cross-correlations between models of variable fidelity, and can effectively safeguard against low-fidelity models that provide wrong trends. This introduces a new class of multi-fidelity information fusion algorithms that provide a fundamental extension to the existing linear autoregressive methodologies, while still maintaining the same algorithmic complexity and overall computational cost. The performance of the proposed methods is tested in several benchmark problems involving both synthetic and real multi-fidelity datasets from computational fluid dynamics simulations.

No abstract

Enzymes that bind and process ubiquitin, a small 76-amino-acid protein, have been recognized as pharmacological targets in oncology, immunological disorders, and neurodegeneration. Mass spectrometry technology has now reached the capacity to cover the proteome with enough depth to interrogate entire biochemical pathways including those that contain DUBs and E3 ligase substrates. We have recently characterized the breast cancer cell (MCF7) deep proteome by detecting and quantifying ~10,000 proteins, and within this data set, we can detect endogenous expression of 65 deubiquitylating enzymes (DUBs), whereas matching transcriptomics detected 78 DUB mRNAs. Since enzyme activity provides another meaningful layer of information in addition to the expression levels, we have combined advanced mass spectrometry technology, pre-fractionation, and more potent/selective ubiquitin active-site probes with propargylic-based electrophiles to profile 74 DUBs including distinguishable isoforms for 5 DUBs in MCF7 crude extract material. Competition experiments with cysteine alkylating agents and pan-DUB inhibitors combined with probe labeling revealed the proportion of active cellular DUBs directly engaged with probes by label-free quantitative (LFQ) mass spectrometry. This demonstrated that USP13, 39, and 40 are non-reactive to probe, indicating restricted enzymatic activity under these cellular conditions. Our extended chemoproteomics workflow increases depth of covering the active DUBome, including isoform-specific resolution, and provides the framework for more comprehensive cell-based small-molecule DUB selectivity profiling.

No abstract