arXiv subjects

Nan Wang

Publications and source records attributed to Nan Wang.

At least 145 records · Page 8Linked to original sources

arXiv2023

A Cross-institutional Evaluation on Breast Cancer Phenotyping NLP Algorithms on Electronic Health Records

Objective: The generalizability of clinical large language models is usually ignored during the model development process. This study evaluated the generalizability of BERT-based clinical NLP models across different clinical settings through a breast cancer phenotype extraction task. Materials and Methods: Two clinical corpora of breast cancer patients were collected from the electronic health records from the University of Minnesota and the Mayo Clinic, and annotated following the same guideline. We developed three types of NLP models (i.e., conditional random field, bi-directional long short-term memory and CancerBERT) to extract cancer phenotypes from clinical texts. The models were evaluated for their generalizability on different test sets with different learning strategies (model transfer vs. locally trained). The entity coverage score was assessed with their association with the model performances. Results: We manually annotated 200 and 161 clinical documents at UMN and MC, respectively. The corpora of the two institutes were found to have higher similarity between the target entities than the overall corpora. The CancerBERT models obtained the best performances among the independent test sets from two clinical institutes and the permutation test set. The CancerBERT model developed in one institute and further fine-tuned in another institute achieved reasonable performance compared to the model developed on local data (micro-F1: 0.925 vs 0.932). Conclusions: The results indicate the CancerBERT model has the best learning ability and generalizability among the three types of clinical NLP models. The generalizability of the models was found to be correlated with the similarity of the target entities between the corpora.

cs.CL↗

arXiv2023

Clustered Data Sharing for Non-IID Federated Learning over Wireless Networks

Federated Learning (FL) is a novel distributed machine learning approach to leverage data from Internet of Things (IoT) devices while maintaining data privacy. However, the current FL algorithms face the challenges of non-independent and identically distributed (non-IID) data, which causes high communication costs and model accuracy declines. To address the statistical imbalances in FL, we propose a clustered data sharing framework which spares the partial data from cluster heads to credible associates through device-to-device (D2D) communication. Moreover, aiming at diluting the data skew on nodes, we formulate the joint clustering and data sharing problem based on the privacy-preserving constrained graph. To tackle the serious coupling of decisions on the graph, we devise a distribution-based adaptive clustering algorithm (DACA) basing on three deductive cluster-forming conditions, which ensures the maximum yield of data sharing. The experiments show that the proposed framework facilitates FL on non-IID datasets with better convergence and model accuracy under a limited communication environment.

cs.LG↗

arXiv2023

Practically Efficient Secure Computation of Rank-based Statistics Over Distributed Datasets

In this paper, we propose a practically efficient model for securely computing rank-based statistics, e.g., median, percentiles and quartiles, over distributed datasets in the malicious setting without leaking individual data privacy. Based on the binary search technique of Aggarwal et al. (EUROCRYPT \textquotesingle 04), we respectively present an interactive protocol and a non-interactive protocol, involving at most $\log ||R||$ rounds, where $||R||$ is the range size of the dataset elements. Besides, we introduce a series of optimisation techniques to reduce the round complexity. Our computing model is modular and can be instantiated with either homomorphic encryption or secret-sharing schemes. Compared to the state-of-the-art solutions, it provides stronger security and privacy while maintaining high efficiency and accuracy. Unlike differential-privacy-based solutions, it does not suffer a trade-off between accuracy and privacy. On the other hand, it only involves $O(N \log ||R||)$ time complexity, which is far more efficient than those bitwise-comparison-based solutions with $O(N^2\log ||R||)$ time complexity, where $N$ is the dataset size. Finally, we provide a UC-secure instantiation with the threshold Paillier cryptosystem and $Σ$-protocol zero-knowledge proofs of knowledge.

cs.CR↗

arXiv2022

Rank4Class: A Ranking Formulation for Multiclass Classification

Multiclass classification (MCC) is a fundamental machine learning problem of classifying each instance into one of a predefined set of classes. In the deep learning era, extensive efforts have been spent on developing more powerful neural embedding models to better represent the instance for improving MCC performance. In this paper, we do not aim to propose new neural models for instance representation learning, but to show that it is promising to boost MCC performance with a novel formulation through the lens of ranking. In particular, by viewing MCC as to rank classes for an instance, we first argue that ranking metrics, such as Normalized Discounted Cumulative Gain, can be more informative than the commonly used Top-$K$ metrics. We further demonstrate that the dominant neural MCC recipe can be transformed to a neural ranking framework. Based on such generalization, we show that it is intuitive to leverage advanced techniques from the learning to rank literature to improve the MCC performance out of the box. Extensive empirical results on both text and image classification tasks with diverse datasets and backbone neural models show the value of our proposed framework.

cs.LG↗

arXiv2022

A Rapidly-Exploring Random Trees Motion Planning Algorithm for Hybrid Dynamical Systems

This paper proposes a rapidly-exploring random trees (RRT) algorithm to solve the motion planning problem for hybrid systems. At each iteration, the proposed algorithm, called HyRRT, randomly picks a state sample and extends the search tree by flow or jump, which is also chosen randomly when both regimes are possible. Through a definition of concatenation of functions defined on hybrid time domains, we show that HyRRT is probabilistically complete, namely, the probability of failing to find a motion plan approaches zero as the number of iterations of the algorithm increases. This property is guaranteed under mild conditions on the data defining the motion plan, which include a relaxation of the usual positive clearance assumption imposed in the literature of classical systems. The motion plan is computed through the solution of two optimization problems, one associated with the flow and the other with the jumps of the system. The proposed algorithm is applied to a walking robot so as to highlight its generality and computational features.

cs.RO↗

arXiv2022

Devaney Chaos on a Set-valued Map and Its Inverse Limit

We study relationships between a set-valued map and its inverse limits about the notion of periodic point set, transitivity, sensitivity and Devaney chaos. Density of periodic point set of a set-valued map and its inverse limits implies each other. Sensitivity of a set-valued map and its inverse limits does not imply each other. Transitivity and Devaney chaos of generalized inverse limits implies the corresponding property of a set-valued map.

math.DS↗

arXiv2022

Realization of high-dynamic-range broadband magnetic-field sensing with ensemble nitrogen-vacancy centers in diamond

We present a new magnetometry method integrating an ensemble of nitrogen-vacancy (NV) centers in a single-crystal diamond with an extended dynamic range for monitoring the fast changing magnetic-field. The NV-center spin resonance frequency is tracked using a closed-loop frequency locked technique with fast frequency hopping to achieve a 10 kHz measurement bandwidth, thus, allowing for the detection of fast changing magnetic signals up to 0.723 T/s.This technique exhibits an extended dynamic range subjected to the working bandwidth of the microwave source. This extended dynamic range can reach up to 4.3 mT, which is 86 times broader than the intrinsic dynamic range. The essential components for NV spin control and signal processing such as signal generation, microwave frequency control, data processing and readout are integrated in a board-level system. With this platform, we demonstrate broadband magnetometry with an optimized sensitivity of 4.2 nT-Hz-1/2. This magnetometry method has the potential to be implemented in a multichannel frequency locked vector magnetometer suitable for a wide range of practical applications such as magnetocardiography and high-precision current sensors.

quant-ph↗

arXiv2022

An MRC Framework for Semantic Role Labeling

Semantic Role Labeling (SRL) aims at recognizing the predicate-argument structure of a sentence and can be decomposed into two subtasks: predicate disambiguation and argument labeling. Prior work deals with these two tasks independently, which ignores the semantic connection between the two tasks. In this paper, we propose to use the machine reading comprehension (MRC) framework to bridge this gap. We formalize predicate disambiguation as multiple-choice machine reading comprehension, where the descriptions of candidate senses of a given predicate are used as options to select the correct sense. The chosen predicate sense is then used to determine the semantic roles for that predicate, and these semantic roles are used to construct the query for another MRC model for argument labeling. In this way, we are able to leverage both the predicate semantics and the semantic role semantics for argument labeling. We also propose to select a subset of all the possible semantic roles for computational efficiency. Experiments show that the proposed framework achieves state-of-the-art or comparable results to previous work. Code is available at \url{https://github.com/ShannonAI/MRC-SRL}.

cs.CL↗

arXiv2022

GATE: Graph CCA for Temporal SElf-supervised Learning for Label-efficient fMRI Analysis

In this work, we focus on the challenging task, neuro-disease classification, using functional magnetic resonance imaging (fMRI). In population graph-based disease analysis, graph convolutional neural networks (GCNs) have achieved remarkable success. However, these achievements are inseparable from abundant labeled data and sensitive to spurious signals. To improve fMRI representation learning and classification under a label-efficient setting, we propose a novel and theory-driven self-supervised learning (SSL) framework on GCNs, namely Graph CCA for Temporal self-supervised learning on fMRI analysis GATE. Concretely, it is demanding to design a suitable and effective SSL strategy to extract formation and robust features for fMRI. To this end, we investigate several new graph augmentation strategies from fMRI dynamic functional connectives (FC) for SSL training. Further, we leverage canonical-correlation analysis (CCA) on different temporal embeddings and present the theoretical implications. Consequently, this yields a novel two-step GCN learning procedure comprised of (i) SSL on an unlabeled fMRI population graph and (ii) fine-tuning on a small labeled fMRI dataset for a classification task. Our method is tested on two independent fMRI datasets, demonstrating superior performance on autism and dementia diagnosis.

cs.LG↗

arXiv2022

Unconventional Charge-density-wave Order in a Dilute d-band Semiconductor

Electron-lattice coupling effects in low dimensional materials give rise to charge density wave (CDW) order and phase transitions. These phenomena are critical ingredients for superconductivity and predominantly occur in metallic model systems such as doped cuprates, transition metal dichalcogenides, and more recently, in Kagome lattice materials. However, CDW in semiconducting systems, specifically at the limit of low carrier concentration region, is uncommon. Here, we combine electrical transport, synchrotron X-ray diffraction and optical spectroscopy to discover CDW order in a quasi-one-dimensional (1D), dilute d-band semiconductor, BaTiS3, which suggests the existence of strong electron-phonon coupling. The CDW state further undergoes an unusual transition featuring a sharp increase in carrier mobility. Our work establishes BaTiS3 as a unique platform to study the CDW physics in the dilute filling limit to explore novel electronic phases.

cond-mat.mtrl-sci↗

arXiv2022

FedNI: Federated Graph Learning with Network Inpainting for Population-Based Disease Prediction

Graph Convolutional Neural Networks (GCNs) are widely used for graph analysis. Specifically, in medical applications, GCNs can be used for disease prediction on a population graph, where graph nodes represent individuals and edges represent individual similarities. However, GCNs rely on a vast amount of data, which is challenging to collect for a single medical institution. In addition, a critical challenge that most medical institutions continue to face is addressing disease prediction in isolation with incomplete data information. To address these issues, Federated Learning (FL) allows isolated local institutions to collaboratively train a global model without data sharing. In this work, we propose a framework, FedNI, to leverage network inpainting and inter-institutional data via FL. Specifically, we first federatively train missing node and edge predictor using a graph generative adversarial network (GAN) to complete the missing information of local networks. Then we train a global GCN node classifier across institutions using a federated graph learning platform. The novel design enables us to build more accurate machine learning models by leveraging federated learning and also graph learning approaches. We demonstrate that our federated model outperforms local and baseline FL methods with significant margins on two public neuroimaging datasets.

cs.LG↗

arXiv2022

VIP-SLAM: An Efficient Tightly-Coupled RGB-D Visual Inertial Planar SLAM

In this paper, we propose a tightly-coupled SLAM system fused with RGB, Depth, IMU and structured plane information. Traditional sparse points based SLAM systems always maintain a mass of map points to model the environment. Huge number of map points bring us a high computational complexity, making it difficult to be deployed on mobile devices. On the other hand, planes are common structures in man-made environment especially in indoor environments. We usually can use a small number of planes to represent a large scene. So the main purpose of this article is to decrease the high complexity of sparse points based SLAM. We build a lightweight back-end map which consists of a few planes and map points to achieve efficient bundle adjustment (BA) with an equal or better accuracy. We use homography constraints to eliminate the parameters of numerous plane points in the optimization and reduce the complexity of BA. We separate the parameters and measurements in homography and point-to-plane constraints and compress the measurements part to further effectively improve the speed of BA. We also integrate the plane information into the whole system to realize robust planar feature extraction, data association, and global consistent planar reconstruction. Finally, we perform an ablation study and compare our method with similar methods in simulation and real environment data. Our system achieves obvious advantages in accuracy and efficiency. Even if the plane parameters are involved in the optimization, we effectively simplify the back-end map by using planar structures. The global bundle adjustment is nearly 2 times faster than the sparse points based SLAM algorithm.

cs.RO↗

arXiv2022

MISSU: 3D Medical Image Segmentation via Self-distilling TransUNet

U-Nets have achieved tremendous success in medical image segmentation. Nevertheless, it may suffer limitations in global (long-range) contextual interactions and edge-detail preservation. In contrast, Transformer has an excellent ability to capture long-range dependencies by leveraging the self-attention mechanism into the encoder. Although Transformer was born to model the long-range dependency on the extracted feature maps, it still suffers from extreme computational and spatial complexities in processing high-resolution 3D feature maps. This motivates us to design the efficiently Transformer-based UNet model and study the feasibility of Transformer-based network architectures for medical image segmentation tasks. To this end, we propose to self-distill a Transformer-based UNet for medical image segmentation, which simultaneously learns global semantic information and local spatial-detailed features. Meanwhile, a local multi-scale fusion block is first proposed to refine fine-grained details from the skipped connections in the encoder by the main CNN stem through self-distillation, only computed during training and removed at inference with minimal overhead. Extensive experiments on BraTS 2019 and CHAOS datasets show that our MISSU achieves the best performance over previous state-of-the-art methods. Code and models are available at \url{https://github.com/wangn123/MISSU.git}

cs.CV↗

arXiv2022

Age-driven Joint Sampling and Non-slot Based Scheduling for Industrial Internet of Things

Effective control of time-sensitive industrial applications depends on the real-time transmission of data from underlying sensors. Quantifying the data freshness through age of information (AoI), in this paper, we jointly design sampling and non-slot based scheduling policies to minimize the maximum time-average age of information (MAoI) among sensors with the constraints of average energy cost and finite queue stability. To overcome the intractability involving high couplings of such a complex stochastic process, we first focus on the single-sensor time-average AoI optimization problem and convert the constrained Markov decision process (CMDP) into an unconstrained Markov decision process (MDP) by the Lagrangian method. With the infinite-time average energy and AoI expression expended as the Bellman equation, the single-sensor time-average AoI optimization problem can be approached through the steady-state distribution probability. Further, we propose a low-complexity sub-optimal sampling and semi-distributed scheduling scheme for the multi-sensor scenario. The simulation results show that the proposed scheme reduces the MAoI significantly while achieving a balance between the sampling rate and service rate for multiple sensors.

cs.IT↗

arXiv2022

Comparative Explanations of Recommendations

As recommendation is essentially a comparative (or ranking) process, a good explanation should illustrate to users why an item is believed to be better than another, i.e., comparative explanations about the recommended items. Ideally, after reading the explanations, a user should reach the same ranking of items as the system's. Unfortunately, little research attention has yet been paid on such comparative explanations. In this work, we develop an extract-and-refine architecture to explain the relative comparisons among a set of ranked items from a recommender system. For each recommended item, we first extract one sentence from its associated reviews that best suits the desired comparison against a set of reference items. Then this extracted sentence is further articulated with respect to the target user through a generative model to better explain why the item is recommended. We design a new explanation quality metric based on BLEU to guide the end-to-end training of the extraction and refinement components, which avoids generation of generic content. Extensive offline evaluations on two large recommendation benchmark datasets and serious user studies against an array of state-of-the-art explainable recommendation algorithms demonstrate the necessity of comparative explanations and the effectiveness of our solution.

cs.IR↗

arXiv2022

Unbiased Graph Embedding with Biased Graph Observations

Graph embedding techniques are pivotal in real-world machine learning tasks that operate on graph-structured data, such as social recommendation and protein structure modeling. Embeddings are mostly performed on the node level for learning representations of each node. Since the formation of a graph is inevitably affected by certain sensitive node attributes, the node embeddings can inherit such sensitive information and introduce undesirable biases in downstream tasks. Most existing works impose ad-hoc constraints on the node embeddings to restrict their distributions for unbiasedness/fairness, which however compromise the utility of the resulting embeddings. In this paper, we propose a principled new way for unbiased graph embedding by learning node embeddings from an underlying bias-free graph, which is not influenced by sensitive node attributes. Motivated by this new perspective, we propose two complementary methods for uncovering such an underlying graph, with the goal of introducing minimum impact on the utility of the embeddings. Both our theoretical justification and extensive experimental comparisons against state-of-the-art solutions demonstrate the effectiveness of our proposed methods.

cs.LG↗

arXiv2022

BPMR: Bayesian Probabilistic Multivariate Ranking

Multi-aspect user preferences are attracting wider attention in recommender systems, as they enable more detailed understanding of users' evaluations of items. Previous studies show that incorporating multi-aspect preferences can greatly improve the performance and explainability of recommendation. However, as recommendation is essentially a ranking problem, there is no principled solution for ranking multiple aspects collectively to enhance the recommendation. In this work, we derive a multi-aspect ranking criterion. To maintain the dependency among different aspects, we propose to use a vectorized representation of multi-aspect ratings and develop a probabilistic multivariate tensor factorization framework (PMTF). The framework naturally leads to a probabilistic multi-aspect ranking criterion, which generalizes the single-aspect ranking to a multivariate fashion. Experiment results on a large multi-aspect review rating dataset confirmed the effectiveness of our solution.

cs.IR↗

arXiv2022

Orientation Controlled Anisotropy in Single Crystals of Quasi-1D BaTiS3

Low-dimensional materials with chain-like (one-dimensional) or layered (twodimensional) structures are of significant interest due to their anisotropic electrical, optical, thermal properties. One material with chain-like structure, BaTiS3 (BTS), was recently shown to possess giant in-plane optical anisotropy and glass-like thermal conductivity. To understand the origin of these effects, it is necessary to fully characterize the optical, thermal, and electronic anisotropy of BTS. To this end, BTS crystals with different orientations (aand c-axis orientations) were grown by chemical vapor transport. X-ray absorption spectroscopy (XAS) was used to characterize the local structure and electronic anisotropy of BTS. Fourier transform infrared (FTIR) reflection/transmission spectra show a large inplane optical anisotropy in the a-oriented crystals, while the c-axis oriented crystals were nearly isotropic in-plane. BTS platelet crystals are promising uniaxial materials for IR optics with their optic axis parallel to the c-axis. The thermal conductivity measurements revealed a thermal anisotropy of ~4.5 between the c- and a-axis. Time-domain Brillouin scattering showed that the longitudinal sound speed along the two axes is nearly the same suggesting that the thermal anisotropy is a result of different phonon scattering rates.

cond-mat.mtrl-sci↗