Searcharxiv⌕ Search

arXiv subjects

Kun Zhang

Publications and source records attributed to Kun Zhang.

At least 469 records · Page 26Linked to original sources
arXiv2018

Transfer Learning with Label Noise

Transfer learning aims to improve learning in target domain by borrowing knowledge from a related but different source domain. To reduce the distribution shift between source and target domains, recent methods have focused on exploring invariant representations that have similar distributions across domains. However, when learning this invariant knowledge, existing methods assume that the labels in source domain are uncontaminated, while in reality, we often have access to source data with noisy labels. In this paper, we first show how label noise adversely affect the learning of invariant representations and the correcting of label shift in various transfer learning scenarios. To reduce the adverse effects, we propose a novel Denoising Conditional Invariant Component (DCIC) framework, which provably ensures (1) extracting invariant representations given examples with noisy labels in source domain and unlabeled examples in target domain; (2) estimating the label distribution in target domain with no bias. Experimental results on both synthetic and real-world data verify the effectiveness of the proposed method.

stat.ML↗
arXiv2018

Causal Generative Domain Adaptation Networks

An essential problem in domain adaptation is to understand and make use of distribution changes across domains. For this purpose, we first propose a flexible Generative Domain Adaptation Network (G-DAN) with specific latent variables to capture changes in the generating process of features across domains. By explicitly modeling the changes, one can even generate data in new domains using the generating process with new values for the latent variables in G-DAN. In practice, the process to generate all features together may involve high-dimensional latent variables, requiring dealing with distributions in high dimensions and making it difficult to learn domain changes from few source domains. Interestingly, by further making use of the causal representation of joint distributions, we then decompose the joint distribution into separate modules, each of which involves different low-dimensional latent variables and can be learned separately, leading to a Causal G-DAN (CG-DAN). This improves both statistical and computational efficiency of the learning procedure. Finally, by matching the feature distribution in the target domain, we can recover the target-domain joint distribution and derive the learning machine for the target domain. We demonstrate the efficacy of both G-DAN and CG-DAN in domain generation and cross-domain prediction on both synthetic and real data experiments.

stat.ML↗
arXiv2018

Scalable and accurate deep learning for electronic health records

Predictive modeling with electronic health record (EHR) data is anticipated to drive personalized medicine and improve healthcare quality. Constructing predictive statistical models typically requires extraction of curated predictor variables from normalized EHR data, a labor-intensive process that discards the vast majority of information in each patient's record. We propose a representation of patients' entire, raw EHR records based on the Fast Healthcare Interoperability Resources (FHIR) format. We demonstrate that deep learning methods using this representation are capable of accurately predicting multiple medical events from multiple centers without site-specific data harmonization. We validated our approach using de-identified EHR data from two U.S. academic medical centers with 216,221 adult patients hospitalized for at least 24 hours. In the sequential format we propose, this volume of EHR data unrolled into a total of 46,864,534,945 data points, including clinical notes. Deep learning models achieved high accuracy for tasks such as predicting in-hospital mortality (AUROC across sites 0.93-0.94), 30-day unplanned readmission (AUROC 0.75-0.76), prolonged length of stay (AUROC 0.85-0.86), and all of a patient's final discharge diagnoses (frequency-weighted AUROC 0.90). These models outperformed state-of-the-art traditional predictive models in all cases. We also present a case-study of a neural-network attribution system, which illustrates how clinicians can gain some transparency into the predictions. We believe that this approach can be used to create accurate and scalable predictions for a variety of clinical scenarios, complete with explanations that directly highlight evidence in the patient's chart.

cs.CY↗
arXiv2018

User-Sensitive Recommendation Ensemble with Clustered Multi-Task Learning

This paper considers recommendation algorithm ensembles in a user-sensitive manner. Recently researchers have proposed various effective recommendation algorithms, which utilized different aspects of the data and different techniques. However, the "user skewed prediction" problem may exist for almost all recommendation algorithms -- algorithms with best average predictive accuracy may cover up that the algorithms may perform poorly for some part of users, which will lead to biased services in real scenarios. In this paper, we propose a user-sensitive ensemble method named "UREC" to address this issue. We first cluster users based on the recommendation predictions, then we use multi-task learning to learn the user-sensitive ensemble function for the users. In addition, to alleviate the negative effects of new user problem to clustering users, we propose an approximate approach based on a spectral relaxation. Experiments on real-world datasets demonstrate the superiority of our methods.

cs.IR↗
arXiv2018

Muon Tracking with the fastest light in the JUNO Central Detector

The Jiangmen Underground Neutrino Observatory (JUNO) is a multi-purpose neutrino experiment designed to measure the neutrino mass hierarchy using a central detector (CD), which contains 20 kton liquid scintillator (LS) surrounded by about 18,000 photomultiplier tubes (PMTs), located 700~m underground. The rate of cosmic muons reaching the JUNO detector is about 3~Hz and the muon induced neutrons and isotopes are major backgrounds for the neutrino detection. Reconstruction of the muon trajectory in the detector is crucial for the study and rejection of those backgrounds. This paper will introduce the muon tracking algorithm in the JUNO CD, with a least squares method of PMTs' first hit time (FHT). Correction of the FHT for each PMT was found to be important to reduce the reconstruction bias. The spatial resolution and angular resolution are better than 3~cm and 0.4~degree, respectively, and the tracking efficiency is greater than 90\% up to 16~m far from the detector center.

physics.ins-det↗
arXiv2018

Ultra-Fast Ferrimagnetic All Spin Logic Device

All spin logic device (ASLD) blazes an alternative path for realizing ultra-low power computing in the Post-Moore era. However, initial device structure relying on ferromagnetic input/output and spin transfer torque (STT) driven magnetization switching degrades its performance and even hinders its realization. In this paper, we propose an ASLD based on rare-earth (RE)-transition-metal (TM) ferromagnetic alloy that can achieve an ultra-high frequency up to terahertz. The spin orbit torque (SOT) induced fast precession near the spin angular momentum compensated point is investigated through the macrospin model. Combining the non-local spin current diffusing from the input to the output, a deterministic picosecond switching can be realized without any external magnetic field. Our results show that ASLD has the potential to exceed the performance of mainstream computing.

physics.app-ph↗
arXiv2017

Collaborative Filtering with Social Exposure: A Modular Approach to Social Recommendation

This paper is concerned with how to make efficient use of social information to improve recommendations. Most existing social recommender systems assume people share similar preferences with their social friends. Which, however, may not hold true due to various motivations of making online friends and dynamics of online social networks. Inspired by recent causal process based recommendations that first model user exposures towards items and then use these exposures to guide rating prediction, we utilize social information to capture user exposures rather than user preferences. We assume that people get information of products from their online friends and they do not have to share similar preferences, which is less restrictive and seems closer to reality. Under this new assumption, in this paper, we present a novel recommendation approach (named SERec) to integrate social exposure into collaborative filtering. We propose two methods to implement SERec, namely social regularization and social boosting, each with different ways to construct social exposures. Experiments on four real-world datasets demonstrate that our methods outperform the state-of-the-art methods on top-N recommendations. Further study compares the robustness and scalability of the two proposed methods.

cs.IR↗
arXiv2017

Causality Refined Diagnostic Prediction

Applying machine learning in the health care domain has shown promising results in recent years. Interpretable outputs from learning algorithms are desirable for decision making by health care personnel. In this work, we explore the possibility of utilizing causal relationships to refine diagnostic prediction. We focus on the task of diagnostic prediction using discomfort drawings, and explore two ways to employ causal identification to improve the diagnostic results. Firstly, we use causal identification to infer the causal relationships among diagnostic labels which, by itself, provides interpretable results to aid the decision making and training of health care personnel. Secondly, we suggest a post-processing approach where the inferred causal relationships are used to refine the prediction accuracy of a multi-view probabilistic model. Experimental results show firstly that causal identification is capable of detecting the causal relationships among diagnostic labels correctly, and secondly that there is potential for improving pain diagnostics prediction accuracy using the causal relationships.

cs.LG↗
arXiv2017

Learning Vector Autoregressive Models with Latent Processes

We study the problem of learning the support of transition matrix between random processes in a Vector Autoregressive (VAR) model from samples when a subset of the processes are latent. It is well known that ignoring the effect of the latent processes may lead to very different estimates of the influences among observed processes, and we are concerned with identifying the influences among the observed processes, those between the latent ones, and those from the latent to the observed ones. We show that the support of transition matrix among the observed processes and lengths of all latent paths between any two observed processes can be identified successfully under some conditions on the VAR model. From the lengths of latent paths, we reconstruct the latent subgraph (representing the influences among the latent processes) with a minimum number of variables uniquely if its topology is a directed tree. Furthermore, we propose an algorithm that finds all possible minimal latent graphs under some conditions on the lengths of latent paths. Our results apply to both non-Gaussian and Gaussian cases, and experimental results on various synthetic and real-world datasets validate our theoretical results.

cs.LG↗
arXiv2017

Quantum partial search for uneven distribution of multiple target items

Quantum partial search algorithm is approximate search. It aims to find a target block (which has the target items). It runs a little faster than full Grover search. In this paper, we consider quantum partial search algorithm for multiple target items unevenly distributed in database (target blocks have different number of target items). The algorithm we describe can locate one of the target blocks. Efficiency of the algorithm is measured by number of queries to the oracle. We optimize the algorithm in order to improve efficiency. By perturbation method, we find that the algorithm runs the fastest when target items are evenly distributed in database.

quant-ph↗
arXiv2017

Reflecting Diffusion Process on Time-Inhomogeneous Manifolds with Boundary

Let $L_t:=Δ_t+Z_t$ for a $C^{1,1}$-vector field $Z$ on a differential manifold $M$ with boundary $\partial M$, where $Δ_t$ is the Laplacian induced by a time dependent metric $g_t$ differentiable in $t\in [0,T_c)$. We first introduce the reflecting diffusion process generated by $L_t$ and establish the derivative formula for the associated diffusion semigroup; then construct the couplings for the reflecting $L_t$-diffusion processes by parallel and reflecting displacement, which implies the gradient estimates of the associated heat semigroup; and finally, present a number of equivalent inequalities for the curvature lower bound and the convexity of the boundary, including the gradient estimations, Harnack inequalities, transportation-cost inequalities and other functional inequalities for diffusion semigroup.

math.PR↗
arXiv2017

The emergence of the two cell fates and their associated switching for a negative auto-regulating gene

Decisions in the cell that lead to its ultimate fate are important for cellular functions such as proliferation, growth, differentiation, development and death. Understanding this decision process is imperative for advancements in the treatment of diseases such as cancer. It is clear that underlying gene regulatory networks and surrounding environments of the cells are crucial for function. The self-repressor is a very abundant gene regulatory motif, and is often believed to have only one cell fate. In this study, we elucidate the effects of microenvironments mimicking the epigenetic effects on cell fates through the introduction of inducers capable of binding to a self-repressing gene product (protein), thus regulating the associated gene. This alters the effective regulatory binding speed of the self-repressor regulatory protein to its destination DNA without changing the gene itself. The steady state observations and real time monitoring of the self-repressor expression dynamics reveal the emergence of the two cell fates, The simulations are consistent with the experimental findings. We provide physical and quantitative explanations for the origin of the two phenotypic cell fates. We find that two cell fates, rather than a single fate, and their associated switching dynamics emerge from a change in effective gene regulation strengths. The switching time scale is quantified. Our results reveal a new mechanism for the emergence of multiple cell fates. This provides an origin for the heterogeneity often observed among cell states, while illustrating the influence of microenvironments on cell fates and their decision-making processes without genetic changes

q-bio.MN↗
arXiv2017

Exploring the underlying mechanisms of Xenopus laevis embryonic cell cycle

Cell cycle is an indispensable process in the proliferation and development. Despite significant efforts, global quantification and physical understanding are still challenging. In this study, we explored the mechanisms of Xenopus laevis embryonic cell cycle by quantifying the underlying landscape and flux. We uncovered the irregular Mexican hat landscape of the Xenopus laevis embryonic cell cycle with several local basins and barriers on the oscillation path. The local basins characterize the different phases of Xenopus laevis embryonic cell cycle and the local barriers represent the checkpoints. The checkpoint mechanism of cell cycle is revealed by the landscape basins and barriers. While landscape shape determines the stabilities of the states on the oscillation path, the curl flux force determines the stability of the cell cycle flow. Replication is fundamental for biology of living. From our quantitative study here, we see that replication can not proceed without energy input. In fact, the curl flux originated from energy or nutrition supply determines the speed of the cell cycle and guarantees the progression. Speed of cell cycle is a hallmark of cancer. Through landscape and flux analysis, one can identify the key elements for controlling the speed. This can help to design effective strategy for drug discovery against cancer.

q-bio.MN↗
arXiv2017

Causal Discovery in the Presence of Measurement Error: Identifiability Conditions

Measurement error in the observed values of the variables can greatly change the output of various causal discovery methods. This problem has received much attention in multiple fields, but it is not clear to what extent the causal model for the measurement-error-free variables can be identified in the presence of measurement error with unknown variance. In this paper, we study precise sufficient identifiability conditions for the measurement-error-free causal model and show what information of the causal model can be recovered from observed data. In particular, we present two different sets of identifiability conditions, based on the second-order statistics and higher-order statistics of the data, respectively. The former was inspired by the relationship between the generating model of the measurement-error-contaminated data and the factor analysis model, and the latter makes use of the identifiability result of the over-complete independent component analysis problem.

stat.ME↗
arXiv2017

A New Measure of Conditional Dependence

Measuring conditional dependencies among the variables of a network is of great interest to many disciplines. This paper studies some shortcomings of the existing dependency measures in detecting direct causal influences or their lack of ability for group selection to capture strong dependencies and accordingly introduces a new statistical dependency measure to overcome them. This measure is inspired by Dobrushin's coefficients and based on the fact that there is no dependency between $X$ and $Y$ given another variable $Z$, if and only if the conditional distribution of $Y$ given $X=x$ and $Z=z$ does not change when $X$ takes another realization $x'$ while $Z$ takes the same realization $z$. We show the advantages of this measure over the related measures in the literature. Moreover, we establish the connection between our measure and the integral probability metric (IPM) that helps to develop estimators of the measure with lower complexity compared to other relevant information theoretic based measures. Finally, we show the performance of this measure through numerical simulations.

stat.ML↗
arXiv2017

Learning Causal Structures Using Regression Invariance

We study causal inference in a multi-environment setting, in which the functional relations for producing the variables from their direct causes remain the same across environments, while the distribution of exogenous noises may vary. We introduce the idea of using the invariance of the functional relations of the variables to their causes across a set of environments. We define a notion of completeness for a causal inference algorithm in this setting and prove the existence of such algorithm by proposing the baseline algorithm. Additionally, we present an alternate algorithm that has significantly improved computational and sample complexity compared to the baseline algorithm. The experiment results show that the proposed algorithm outperforms the other existing algorithms.

cs.LG↗
arXiv2017

Approximate Kernel-based Conditional Independence Tests for Fast Non-Parametric Causal Discovery

Constraint-based causal discovery (CCD) algorithms require fast and accurate conditional independence (CI) testing. The Kernel Conditional Independence Test (KCIT) is currently one of the most popular CI tests in the non-parametric setting, but many investigators cannot use KCIT with large datasets because the test scales cubicly with sample size. We therefore devise two relaxations called the Randomized Conditional Independence Test (RCIT) and the Randomized conditional Correlation Test (RCoT) which both approximate KCIT by utilizing random Fourier features. In practice, both of the proposed tests scale linearly with sample size and return accurate p-values much faster than KCIT in the large sample size context. CCD algorithms run with RCIT or RCoT also return graphs at least as accurate as the same algorithms run with KCIT but with large reductions in run time.

stat.ME↗