arXiv subjects

Ning An

Publications and source records attributed to Ning An.

At least 37 records · Page 2Linked to original sources

arXiv2024

TechGPT-2.0: A large language model project to solve the task of knowledge graph construction

Large language models have exhibited robust performance across diverse natural language processing tasks. This report introduces TechGPT-2.0, a project designed to enhance the capabilities of large language models specifically in knowledge graph construction tasks, including named entity recognition (NER) and relationship triple extraction (RTE) tasks in NLP applications. Additionally, it serves as a LLM accessible for research within the Chinese open-source model community. We offer two 7B large language model weights and a QLoRA weight specialized for processing lengthy texts.Notably, TechGPT-2.0 is trained on Huawei's Ascend server. Inheriting all functionalities from TechGPT-1.0, it exhibits robust text processing capabilities, particularly in the domains of medicine and law. Furthermore, we introduce new capabilities to the model, enabling it to process texts in various domains such as geographical areas, transportation, organizations, literary works, biology, natural sciences, astronomical objects, and architecture. These enhancements also fortified the model's adeptness in handling hallucinations, unanswerable queries, and lengthy texts. This report provides a comprehensive and detailed introduction to the full fine-tuning process on Huawei's Ascend servers, encompassing experiences in Ascend server debugging, instruction fine-tuning data processing, and model training. Our code is available at https://github.com/neukg/TechGPT-2.0

cs.CL↗

arXiv2023

Frequency-domain MLPs are More Effective Learners in Time Series Forecasting

Time series forecasting has played the key role in different industrial, including finance, traffic, energy, and healthcare domains. While existing literatures have designed many sophisticated architectures based on RNNs, GNNs, or Transformers, another kind of approaches based on multi-layer perceptrons (MLPs) are proposed with simple structure, low complexity, and {superior performance}. However, most MLP-based forecasting methods suffer from the point-wise mappings and information bottleneck, which largely hinders the forecasting performance. To overcome this problem, we explore a novel direction of applying MLPs in the frequency domain for time series forecasting. We investigate the learned patterns of frequency-domain MLPs and discover their two inherent characteristic benefiting forecasting, (i) global view: frequency spectrum makes MLPs own a complete view for signals and learn global dependencies more easily, and (ii) energy compaction: frequency-domain MLPs concentrate on smaller key part of frequency components with compact signal energy. Then, we propose FreTS, a simple yet effective architecture built upon Frequency-domain MLPs for Time Series forecasting. FreTS mainly involves two stages, (i) Domain Conversion, that transforms time-domain signals into complex numbers of frequency domain; (ii) Frequency Learning, that performs our redesigned MLPs for the learning of real and imaginary part of frequency components. The above stages operated on both inter-series and intra-series scales further contribute to channel-wise and time-wise dependency learning. Extensive experiments on 13 real-world benchmarks (including 7 benchmarks for short-term forecasting and 6 benchmarks for long-term forecasting) demonstrate our consistent superiority over state-of-the-art methods.

cs.LG↗

arXiv2023

FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective

Multivariate time series (MTS) forecasting has shown great importance in numerous industries. Current state-of-the-art graph neural network (GNN)-based forecasting methods usually require both graph networks (e.g., GCN) and temporal networks (e.g., LSTM) to capture inter-series (spatial) dynamics and intra-series (temporal) dependencies, respectively. However, the uncertain compatibility of the two networks puts an extra burden on handcrafted model designs. Moreover, the separate spatial and temporal modeling naturally violates the unified spatiotemporal inter-dependencies in real world, which largely hinders the forecasting performance. To overcome these problems, we explore an interesting direction of directly applying graph networks and rethink MTS forecasting from a pure graph perspective. We first define a novel data structure, hypervariate graph, which regards each series value (regardless of variates or timestamps) as a graph node, and represents sliding windows as space-time fully-connected graphs. This perspective considers spatiotemporal dynamics unitedly and reformulates classic MTS forecasting into the predictions on hypervariate graphs. Then, we propose a novel architecture Fourier Graph Neural Network (FourierGNN) by stacking our proposed Fourier Graph Operator (FGO) to perform matrix multiplications in Fourier space. FourierGNN accommodates adequate expressiveness and achieves much lower complexity, which can effectively and efficiently accomplish the forecasting. Besides, our theoretical analysis reveals FGO's equivalence to graph convolutions in the time domain, which further verifies the validity of FourierGNN. Extensive experiments on seven datasets have demonstrated our superior performance with higher efficiency and fewer parameters compared with state-of-the-art methods.

cs.LG↗

arXiv2023

The mechanism of the irradiation synergistic effect of Silicon bipolar junction transistors explained by multiscale simulations of Monte Carlo and excited-state first-principle calculations

Neutron and $γ$-ray irradiation damages to transistors are found to be non-additive, and this is denoted as the irradiation synergistic effect (ISE). Its mechanism is not well-understood. The recent defect-based model [ACS Appl. Electron. Mater. 2, 3783 (2020)] for Silicon bipolar junction transistors (BJT) achieve quantitative agreement with experiments, but its assumptions on the defect reactions are unverified. Going beyond the model requires directly representing the effect of $γ$-ray irradiation in first-principles calculations, which is not feasible previously. In this work, we examine the defect-based model of the ISE by developing a multiscale method for the simulation of the $γ$-ray irradiation, where the $γ$-ray-induced electronic excitations are treated explicitly in excited-state first-principles calculations. We find the calculations agree with experiments, and the effect of the $γ$-ray-induced excitation is significantly different from the effects of defect charge state and temperature. We propose a diffusion-based qualitative explanation of the mechanism of positive/negative ISE in NPN/PNP BJTs in the end.

cond-mat.mtrl-sci↗

arXiv2023

SUGAR: Spherical Ultrafast Graph Attention Framework for Cortical Surface Registration

Cortical surface registration plays a crucial role in aligning cortical functional and anatomical features across individuals. However, conventional registration algorithms are computationally inefficient. Recently, learning-based registration algorithms have emerged as a promising solution, significantly improving processing efficiency. Nonetheless, there remains a gap in the development of a learning-based method that exceeds the state-of-the-art conventional methods simultaneously in computational efficiency, registration accuracy, and distortion control, despite the theoretically greater representational capabilities of deep learning approaches. To address the challenge, we present SUGAR, a unified unsupervised deep-learning framework for both rigid and non-rigid registration. SUGAR incorporates a U-Net-based spherical graph attention network and leverages the Euler angle representation for deformation. In addition to the similarity loss, we introduce fold and multiple distortion losses, to preserve topology and minimize various types of distortions. Furthermore, we propose a data augmentation strategy specifically tailored for spherical surface registration, enhancing the registration performance. Through extensive evaluation involving over 10,000 scans from 7 diverse datasets, we showed that our framework exhibits comparable or superior registration performance in accuracy, distortion, and test-retest reliability compared to conventional and learning-based methods. Additionally, SUGAR achieves remarkable sub-second processing times, offering a notable speed-up of approximately 12,000 times in registering 9,000 subjects from the UK Biobank dataset in just 32 minutes. This combination of high registration performance and accelerated processing time may greatly benefit large-scale neuroimaging studies.

eess.IV↗

arXiv2023

Entire solutions to the parabolic Monge--Ampère equation with unbounded nonlinear growth in time

The Liouville type theorem on the parabolic Monge--Ampère equation $-u_t\det D^2u=1$ states that any entire parabolically convex classical solution must be of form $-t+|x|^2/2$ up to a re-scaling and transformation, under additional assumption that partial derivative with respect to time variable $u_t$ is strictly negative and bounded. In this paper, we study the case when $u_t$ is unbounded, prove an existence result of entire parabolically convex smooth solution and investigate the asymptotic behavior near infinity.

math.AP↗

arXiv2023

A Monolithic Graphene-Functionalized Microlaser for Multispecies Gas Detection

Optical microcavity enhanced light-matter interaction offers a powerful tool to develop fast and precise sensing techniques, spurring applications in the detection of biochemical targets ranging from cells, nanoparticles, and large molecules. However, the intrinsic inertness of such pristine microresonators limits their spread in new fields such as gas detection. Here, a functionalized microlaser sensor is realized by depositing graphene in an erbium-doped over-modal microsphere. By using a 980 nm pump, multiple laser lines excited in different mode families of the microresonator are co-generated in a single device. The interference between these splitting mode lasers produce beat notes in the electrical domain (0.2-1.1 MHz) with sub-kHz accuracy, thanks to the graphene-induced intracavity backward scattering. This allows for multispecies gas identification from a mixture, and ultrasensitive gas detection down to individual molecule.

physics.optics↗

arXiv2022

Few-Shot Nested Named Entity Recognition

While Named Entity Recognition (NER) is a widely studied task, making inferences of entities with only a few labeled data has been challenging, especially for entities with nested structures. Unlike flat entities, entities and their nested entities are more likely to have similar semantic feature representations, drastically increasing difficulties in classifying different entity categories in the few-shot setting. Although prior work has briefly discussed nested structures in the context of few-shot learning, to our best knowledge, this paper is the first one specifically dedicated to studying the few-shot nested NER task. Leveraging contextual dependency to distinguish nested entities, we propose a Biaffine-based Contrastive Learning (BCL) framework. We first design a Biaffine span representation module for learning the contextual span dependency representation for each entity span rather than only learning its semantic representation. We then merge these two representations by the residual connection to distinguish nested entities. Finally, we build a contrastive learning framework to adjust the representation distribution for larger margin boundaries and more generalized domain transfer learning ability. We conducted experimental studies on three English, German, and Russian nested NER datasets. The results show that the BCL outperformed three baseline models on the 1-shot and 5-shot tasks in terms of F1 score.

cs.CL↗

arXiv2022

Edge-Varying Fourier Graph Networks for Multivariate Time Series Forecasting

The key problem in multivariate time series (MTS) analysis and forecasting aims to disclose the underlying couplings between variables that drive the co-movements. Considerable recent successful MTS methods are built with graph neural networks (GNNs) due to their essential capacity for relational modeling. However, previous work often used a static graph structure of time-series variables for modeling MTS failing to capture their ever-changing correlations over time. To this end, a fully-connected supra-graph connecting any two variables at any two timestamps is adaptively learned to capture the high-resolution variable dependencies via an efficient graph convolutional network. Specifically, we construct the Edge-Varying Fourier Graph Networks (EV-FGN) equipped with Fourier Graph Shift Operator (FGSO) which efficiently performs graph convolution in the frequency domain. As a result, a high-efficiency scale-free parameter learning scheme is derived for MTS analysis and forecasting according to the convolution theorem. Extensive experiments show that EV-FGN outperforms state-of-the-art methods on seven real-world MTS datasets.

cs.LG↗

arXiv2021

Exploring the design space for nonlinear buckling of composite thin-walled lenticular tubes under pure bending

This paper presents an automatic finite element simulation scheme accounting for high geometric nonlinearity and the difference between linear and nonlinear buckling of composite thin-walled lenticular tubes (CTLTs). Parameterizing of cross-section shapes and generation of design space for CTLTs with both circular and parabolic arcs were accomplished, and several key factors were identified, in particular the contrary effect of lumbus length and parabolic coefficient on the bending stiffness anisotropy. The first quantitative comparison of triangular rollable and collapsible (TRAC) booms and CTLTs is given in terms of bending performance in two directions, showing that the optimal CTLT carefully selected from the design space demonstrates a comparable or even better performance than the TRAC boom. This is of great importance from both academic and engineering perspectives. Our efforts enhance the understanding of nonlinear buckling and post-buckling behavior of CTLTs, and provide guidelines for future design of CTLTs with desirable performance.

physics.app-ph↗

arXiv2021

Electrically Tunable Four-Wave-Mixing in Graphene Heterogeneous Fiber for Individual Gas Molecule Detection

Detection of individual molecules is the ultimate goal of any chemical sensor. In the case of gas detection, such resolution has been achieved in advanced nanoscale electronic solid-state sensors, but it has not been possible so far in integrated photonic devices, where the weak light-molecule interaction is typically hidden by noise. Here, we demonstrate a scheme to generate ultrasensitive down-conversion four-wave-mixing (FWM) in a graphene bipolar-junction-transistor heterogeneous D-shaped fiber. In the communication band, the FWM conversion efficiency can change steeply when the graphene Fermi level approaches 0.4 eV. In this condition, we exploit our unique two-step optoelectronic heterodyne detection scheme, and we achieve real-time individual gas molecule detection in vacuum. Such combination of graphene strong nonlinearities, electrical tunability, and all-fiber integration paves the way toward the design of versatile high-performance graphene photonic devices.

cond-mat.mes-hall↗

arXiv2020

Gain-assisted chiral soliton microcombs

The emerging microresonator-based frequency combs revolutionize a broad range of applications from optical communications to astronomical calibration. Despite of their significant merits, low energy efficiency and the lack of all-optical dynamical control severely hinder the transfer of microcomb system to real-world applications. Here, by introducing active lasing medium into the soliton microcomb, for the first time, we experimentally achieve the chiral soliton with agile on-off switch and tunable dual-comb generation in a packaged microresonator. It is found that such a microresonator enables a soliton slingshot effect, the rapid soliton formation arising from the extra energy accumulation induced by inter-modal couplings. Moreover, tuning the erbium gain can generate versatile multi-soliton states, and extend the soliton operation window to a remarkable range over 18 GHz detuning. Finally, the gain-assisted chirality of counterpropagating soliton is demonstrated, which enables an unprecedented fast on-off switching of soliton microcombs. The non-trivial chiral soliton formation with active controllability inspires new paradigms of miniature optical frequency combs and brings the fast tunable soliton tools within reach.

physics.optics↗

arXiv2020

Digital personal health libraries: a systematic literature review

Objective: This paper gives context on recent literature regarding the development of digital personal health libraries (PHL) and provides insights into the potential application of consumer health informatics in diverse clinical specialties. Materials and Methods: A systematic literature review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. Here, 2,850 records were retrieved from PubMed and EMBASE in March 2020 using search terms: personal, health, and library. Information related to the health topic, target population, study purpose, library function, data source, data science method, evaluation measure, and status were extracted from each eligible study. In addition, knowledge discovery methods, including co-occurrence analysis and multiple correspondence analysis, were used to explore research trends of PHL. Results: After screening, this systematic review focused on a dozen articles related to PHL. These encompassed health topics such as infectious diseases, congestive heart failure, electronic prescribing. Data science methods included relational database, information retrieval technology, ontology construction technology. Evaluation measures were heterogeneous regarding PHL functions and settings. At the time of writing, only one of the PHLs described in these articles is available for the public while the others are either prototypes or in the pilot stage. Discussion: Although PHL researches have used different methods to address problems in diverse health domains, there is a lack of an effective PHL to meet the needs of older adults. Conclusion: The development of PHLs may create an unprecedented opportunity for promoting the health of older consumers by providing diverse health information.

cs.DL↗

arXiv2020

A deep belief network-based method to identify proteomic risk markers for Alzheimer disease

While a large body of research has formally identified apolipoprotein E (APOE) as a major genetic risk marker for Alzheimer disease, accumulating evidence supports the notion that other risk markers may exist. The traditional Alzheimer-specific signature analysis methods, however, have not been able to make full use of rich protein expression data, especially the interaction between attributes. This paper develops a novel feature selection method to identify pathogenic factors of Alzheimer disease using the proteomic and clinical data. This approach has taken the weights of network nodes as the importance order of signaling protein expression values. After generating and evaluating the candidate subset, the method helps to select an optimal subset of proteins that achieved an accuracy greater than 90%, which is superior to traditional machine learning methods for clinical Alzheimer disease diagnosis. Besides identifying a proteomic risk marker and further reinforce the link between metabolic risk factors and Alzheimer disease, this paper also suggests that apidonectin-linked pathways are a possible therapeutic drug target.

q-bio.QM↗

arXiv2019

Deep ensemble learning for Alzheimers disease classification

Ensemble learning use multiple algorithms to obtain better predictive performance than any single one of its constituent algorithms could. With growing popularity of deep learning, researchers have started to ensemble them for various purposes. Few if any, however, has used the deep learning approach as a means to ensemble algorithms. This paper presents a deep ensemble learning framework which aims to harness deep learning algorithms to integrate multisource data and tap the wisdom of experts. At the voting layer, a sparse autoencoder is trained for feature learning to reduce the correlation of attributes and diversify the base classifiers ultimately. At the stacking layer, a nonlinear feature-weighted method based on deep belief networks is proposed to rank the base classifiers which may violate the conditional independence. Neural network is used as meta classifier. At the optimizing layer, under-sampling and threshold-moving are used to cope with cost-sensitive problem. Optimized predictions are obtained based on ensemble of probabilistic predictions by similarity calculation. The proposed deep ensemble learning framework is used for Alzheimers disease classification. Experiments with the clinical dataset from national Alzheimers coordinating center demonstrate that the classification accuracy of our proposed framework is 4% better than 6 well-known ensemble approaches as well as the standard stacking algorithm. Adequate coverage of more accurate diagnostic services can be provided by utilizing the wisdom of averaged physicians. This paper points out a new way to boost the primary care of Alzheimers disease from the view of machine learning.

cs.LG↗

arXiv2018

Secure Mobile Crowdsensing with Deep Learning

In order to stimulate secure sensing for Internet of Things (IoT) applications such as healthcare and traffic monitoring, mobile crowdsensing (MCS) systems have to address security threats, such as jamming, spoofing and faked sensing attacks, during both the sensing and the information exchange processes in large-scale dynamic and heterogenous networks. In this article, we investigate secure mobile crowdsensing and present how to use deep learning (DL) methods such as stacked autoencoder (SAE), deep neural network (DNN), and convolutional neural network (CNN) to improve the MCS security approaches including authentication, privacy protection, faked sensing countermeasures, intrusion detection and anti-jamming transmissions in MCS. We discuss the performance gain of these DL-based approaches compared with traditional security schemes and identify the challenges that need to be addressed to implement them in practical MCS systems.

cs.CR↗

arXiv2016

Enhancement of UV Second-Harmonic Radiation at Nonlinear Interfaces with Discontinuous Second-order Susceptibilities

We investigate the generation of ultraviolet (UV) second-harmonic radiation on the boundary of a UV transparent crystal, which is derived from the automatic partial phase matching of the incident wave and the total internal reflection. By adhering to another UV non-transparency crystal with larger second-order nonlinear coefficient χ^{(2)}, an nonlinear interface with large disparity in χ^{(2)} is formed and the enhancement of UV second-harmonic radiation is observed experimentally. The intensity of enhanced second harmonic wave generated at the nonlinear interface was up to 11.6 times at the crystal boundary. As a tunable phase-matching method, it may suggest potential applications in the UV, even vacuum-UV, spectral region.

physics.optics↗

arXiv2016

Surface enhanced nonlinear Cherenkov radiation in one-dimensional nonlinear photonic crystal

We study the configuration of efficient nonlinear Cerenkov diffraction generated from a one-dimensional nonlinear photonic crystal surface, which underlies the incorporation of both quasi-phase-matching and total internal reflection by the crystal surface. Multidirectional radiation spots with different Cerenkov angles are demonstrated experimentally, which results from different orders of reciprocal vectors. At specific angles, the incident light and total internal reflect light associating with quasi-phase-matching format completely phase-matching scheme, leading to great enhancement of harmonic efficiency.

physics.optics↗