Given sets of observations of training and test data, we consider the problem of re-weighting the training data such that its distribution more closely matches that of the test data. We achieve this goal by matching covariate distributions between training and test sets in a high dimensional feature space (specifically, a reproducing kernel Hilbert space). This approach does not require distribution estimation. Instead, the sample weights are obtained by a simple quadratic programming procedure. We provide a uniform convergence bound on the distance between the reweighted training feature mean and the test feature mean, a transductive bound on the expected loss of an algorithm trained on the reweighted data, and a connection to single class SVMs. While our method is designed to deal with the case of simple covariate shift (in the sense of Chapter ??), we have also found benefits for sample selection bias on the labels. Our correction procedure yields its greatest and most consistent advantages when the learning algorithm returns a classifier/regressor that is "simpler" than the data might suggest.
Differentiation of naïve CD4 + T cells into functionally distinct T helper subsets is crucial for the orchestration of immune responses. Due to extensive heterogeneity and multiple overlapping transcriptional programs in differentiating T cell populations, this process has remained a * Correspondence to: st9@sanger.ac.uk, Ashraful.Haque@qimrberghofer.edu.au or stegle@ebi.ac.uk. # denotes equal contribution † denotes equal contribution Author contributions TL and KRJ performed the single-cell RNA-seq experiments. VS developed the GPfates model in collaboration with MZ, NDL, OS and SAT. DFR and WRH generated the PbTII mouse model. KRJ, RM, IS, MSFS, LGF, ASN, UL, FSFG, PTB and CRE performed the mouse experiments. TL, VS, KRJ, LHL and FOB analysed the data and interpreted the results MJTS performed the TCR clonality analysis. TL, KRJ, RM, OB, AH and SAT designed the experiments. OS, AH and SAT cosupervised the study. TL, VS, KRJ, OS, AH and SAT wrote the manuscript. All authors have read and approved the manuscript. Competing interestsThe authors declare no competing interests. Data and materials availabilityThe data presented in this paper is publically available in the ArrayExpress database with accession number E-MTAB-4388. Europe PMC Funders Group Europe PMC Funders Author ManuscriptsEurope PMC Funders Author Manuscripts challenge for systematic dissection in vivo. By using single-cell transcriptomics and computational analysis using a temporal mixtures of Gaussian processes model, termed GPfates, we reconstructed the developmental trajectories of Th1 and Tfh cells during blood-stage Plasmodium infection in mice. By tracking clonality using endogenous TCR sequences, we first demonstrated that Th1/Tfh bifurcation had occurred at both population and single-clone levels. Next, we identified genes whose expression was associated with Th1 or Tfh fates, and demonstrated a T-cell intrinsic role for Galectin-1 in supporting a Th1 differentiation. We also revealed the close molecular relationship between Th1 and IL-10-producing Tr1 cells in this infection. Th1 and Tfh fates emerged from a highly proliferative precursor that upregulated aerobic glycolysis and accelerated cell cycling as cytokine expression began. Dynamic gene expression of chemokine receptors around bifurcation predicted roles for cell-cell in driving Th1/Tfh fates. In particular, we found that precursor Th cells were coached towards a Th1 but not a Tfh fate by inflammatory monocytes. Thus, by integrating genomic and computational approaches, our study has provided two unique resources, a database www.PlasmoTH.org, which facilitates discovery of novel factors controlling Th1/Tfh fate commitment, and more generally, GPfates, a modelling framework for characterizing cell differentiation towards multiple fates.
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
No abstract
In recent years, machine learning has transitioned from a field of academic research interest to a field capable of solving real-world business problems. However, the deployment of machine learning models in production systems can present a number of issues and concerns. This survey reviews published reports of deploying machine learning solutions in a variety of use cases, industries and applications and extracts practical considerations corresponding to stages of the machine learning deployment workflow. By mapping found challenges to the steps of the machine learning deployment workflow we show that practitioners face issues at each stage of the deployment process. The goal of this paper is to lay out a research agenda to explore approaches addressing these challenges.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.