Searcharxiv⌕ Search

arXiv subjects

Li Tan

Publications and source records attributed to Li Tan.

At least 37 records · Page 2Linked to original sources
arXiv2022

Multimodal Dual Emotion with Fusion of Visual Sentiment for Rumor Detection

In recent years, rumors have had a devastating impact on society, making rumor detection a significant challenge. However, the studies on rumor detection ignore the intense emotions of images in the rumor content. This paper verifies that the image emotion improves the rumor detection efficiency. A Multimodal Dual Emotion feature in rumor detection, which consists of visual and textual emotions, is proposed. To the best of our knowledge, this is the first study which uses visual emotion in rumor detection. The experiments on real datasets verify that the proposed features outperform the state-of-the-art sentiment features, and can be extended in rumor detectors while improving their performance.

cs.CY↗
arXiv2022

Region-enhanced Deep Graph Convolutional Networks for Rumor Detection

Social media has been rapidly developing in the public sphere due to its ease of spreading new information, which leads to the circulation of rumors. However, detecting rumors from such a massive amount of information is becoming an increasingly arduous challenge. Previous work generally obtained valuable features from propagation information. It should be noted that most methods only target the propagation structure while ignoring the rumor transmission pattern. This limited focus severely restricts the collection of spread data. To solve this problem, the authors of the present study are motivated to explore the regionalized propagation patterns of rumors. Specifically, a novel region-enhanced deep graph convolutional network (RDGCN) that enhances the propagation features of rumors by learning regionalized propagation patterns and trains to learn the propagation patterns by unsupervised learning is proposed. In addition, a source-enhanced residual graph convolution layer (SRGCL) is designed to improve the graph neural network (GNN) oversmoothness and increase the depth limit of the rumor detection methods-based GNN. Experiments on Twitter15 and Twitter16 show that the proposed model performs better than the baseline approach on rumor detection and early rumor detection.

cs.SI↗
arXiv2022

Leveraging Reaction-aware Substructures for Retrosynthesis Analysis

Retrosynthesis analysis is a critical task in organic chemistry central to many important industries. Previously, various machine learning approaches have achieved promising results on this task by representing output molecules as strings and autoregressively decoded token-by-token with generative models. Text generation or machine translation models in natural language processing were frequently utilized approaches. The token-by-token decoding approach is not intuitive from a chemistry perspective because some substructures are relatively stable and remain unchanged during reactions. In this paper, we propose a substructure-level decoding model, where the substructures are reaction-aware and can be automatically extracted with a fully data-driven approach. Our approach achieved improvement over previously reported models, and we find that the performance can be further boosted if the accuracy of substructure extraction is improved. The substructures extracted by our approach can provide users with better insights for decision-making compared to existing methods. We hope this work will generate interest in this fast growing and highly interdisciplinary area on retrosynthesis prediction and other related topics.

q-bio.QM↗
arXiv2022

Research Status of Deep Learning Methods for Rumor Detection

To manage the rumors in social media to reduce the harm of rumors in society. Many studies used methods of deep learning to detect rumors in open networks. To comprehensively sort out the research status of rumor detection from multiple perspectives, this paper analyzes the highly focused work from three perspectives: Feature Selection, Model Structure, and Research Methods. From the perspective of feature selection, we divide methods into content feature, social feature, and propagation structure feature of the rumors. Then, this work divides deep learning models of rumor detection into CNN, RNN, GNN, Transformer based on the model structure, which is convenient for comparison. Besides, this work summarizes 30 works into 7 rumor detection methods such as propagation trees, adversarial learning, cross-domain methods, multi-task learning, unsupervised and semi-supervised methods, based knowledge graph, and other methods for the first time. And compare the advantages of different methods to detect rumors. In addition, this review enumerate datasets available and discusses the potential issues and future work to help researchers advance the development of field.

cs.CY↗
arXiv2022

A 3D Positioning-based Channel Estimation Method for RIS-aided mmWave Communications

A fundamental challenge in millimeter-wave (mmWave) communication is the susceptibility to blocking objects. One way to alleviate this problem is the use of reconfigurable intelligent surfaces (RIS). Nevertheless, due to the large number of passive reflecting elements on RIS, channel estimation turns out to be a challenging task. In this paper, we address the channel estimation for RIS-aided mmWave communication systems based on a localization method. The proposed idea consists of exploiting the sparsity of the mmWave channel and the topology of the RIS. In particular, we first propose the concept of reflecting unit set (RUS) to improve the flexibility of RIS. We then propose a novel coplanar maximum likelihood-based (CML) 3D positioning method based on the RUS, and derive the Cramer-Rao lower bound (CRLB) for the positioning method. Furthermore, we develop an efficient positioning-based channel estimation scheme with low computational complexity. Compared to state-of-the-art methods, our proposed method requires less time-frequency resources in channel acquisition as the complexity is independent to the total size of the RIS but depends on the size of the RUSs, which is only a small portion of the RIS. Large performance gains are confirmed in simulations, which proves the effectiveness of the proposed method.

cs.IT↗
arXiv2021

Pandemic Drugs at Pandemic Speed: Infrastructure for Accelerating COVID-19 Drug Discovery with Hybrid Machine Learning- and Physics-based Simulations on High Performance Computers

The race to meet the challenges of the global pandemic has served as a reminder that the existing drug discovery process is expensive, inefficient and slow. There is a major bottleneck screening the vast number of potential small molecules to shortlist lead compounds for antiviral drug development. New opportunities to accelerate drug discovery lie at the interface between machine learning methods, in this case developed for linear accelerators, and physics-based methods. The two in silico methods, each have their own advantages and limitations which, interestingly, complement each other. Here, we present an innovative infrastructural development that combines both approaches to accelerate drug discovery. The scale of the potential resulting workflow is such that it is dependent on supercomputing to achieve extremely high throughput. We have demonstrated the viability of this workflow for the study of inhibitors for four COVID-19 target proteins and our ability to perform the required large-scale calculations to identify lead antiviral compounds through repurposing on a variety of supercomputers.

cs.DC↗
arXiv2021

RIS-Aided Wireless Communications: Prototyping, Adaptive Beamforming, and Indoor/Outdoor Field Trials

The prospects of using a Reconfigurable Intelligent Surface (RIS) to aid wireless communication systems have recently received much attention from academia and industry. Most papers make theoretical studies based on elementary models, while the prototyping of RIS-aided wireless communication and real-world field trials are scarce. In this paper, we describe a new RIS prototype consisting of 1100 controllable elements working at 5.8 GHz band. We propose an efficient algorithm for configuring the RIS over the air by exploiting the geometrical array properties and a practical receiver-RIS feedback link. In our indoor test, where the transmitter and receiver are separated by a 30 cm thick concrete wall, our RIS prototype provides a 26 dB power gain compared to the baseline case where the RIS is replaced by a copper plate. A 27 dB power gain was observed in the short-distance outdoor measurement. We also carried out long-distance measurements and successfully transmitted a 32 Mbps data stream over 500 m. A 1080p video was live-streamed and it only played smoothly when the RIS was utilized. The power consumption of the RIS is around 1 W. Our paper is vivid proof that the RIS is a very promising technology for future wireless communications.

cs.IT↗
arXiv2021

A Received Power Model for Reconfigurable Intelligent Surface and Measurement-based Validations

The idea of using a Reconfigurable Intelligent Surface (RIS) consisting of a large array of passive scattering elements to assist wireless communication systems has recently attracted much attention from academia and industry. A central issue with RIS is how much power they can effectively convey to the target radio nodes. Regarding this question, several power level models exist in the literature but few have been validated through experiments. In this paper, we propose a radar cross section-based received power model for an RIS-aided wireless communication system that is rooted in the physical properties of RIS. Our proposed model follows the intuition that the received power is related to the distances from the transmitter/receiver to the RIS, the angles in the TX-RIS-RX triangle, the effective area of each element, and the reflection coefficient of each element. To the best of our knowledge, this paper is the first to model the angle-dependent phase shift of the reflection coefficient, which is typically ignored in existing literature. We further measure the received power with our experimental platform in different scenarios to validate our model. The measurement results show that our model is appropriate both in near field and far field and can characterize the impact of angles well.

cs.IT↗
arXiv2020

Scalable HPC and AI Infrastructure for COVID-19 Therapeutics

COVID-19 has claimed more 1 million lives and resulted in over 40 million infections. There is an urgent need to identify drugs that can inhibit SARS-CoV-2. In response, the DOE recently established the Medical Therapeutics project as part of the National Virtual Biotechnology Laboratory, and tasked it with creating the computational infrastructure and methods necessary to advance therapeutics development. We discuss innovations in computational infrastructure and methods that are accelerating and advancing drug design. Specifically, we describe several methods that integrate artificial intelligence and simulation-based approaches, and the design of computational infrastructure to support these methods at scale. We discuss their implementation and characterize their performance, and highlight science advances that these capabilities have enabled.

cs.DC↗
arXiv2020

IMPECCABLE: Integrated Modeling PipelinE for COVID Cure by Assessing Better LEads

The drug discovery process currently employed in the pharmaceutical industry typically requires about 10 years and $2-3 billion to deliver one new drug. This is both too expensive and too slow, especially in emergencies like the COVID-19 pandemic. In silicomethodologies need to be improved to better select lead compounds that can proceed to later stages of the drug discovery protocol accelerating the entire process. No single methodological approach can achieve the necessary accuracy with required efficiency. Here we describe multiple algorithmic innovations to overcome this fundamental limitation, development and deployment of computational infrastructure at scale integrates multiple artificial intelligence and simulation-based approaches. Three measures of performance are:(i) throughput, the number of ligands per unit time; (ii) scientific performance, the number of effective ligands sampled per unit time and (iii) peak performance, in flop/s. The capabilities outlined here have been used in production for several months as the workhorse of the computational infrastructure to support the capabilities of the US-DOE National Virtual Biotechnology Laboratory in combination with resources from the EU Centre of Excellence in Computational Biomedicine.

cs.DC↗
arXiv2019

Soft Error Resilience and Failure Recovery for Continuum Dynamics Applications

The persistently growing resilience concerns of large-scale computing systems today require not only generic fault tolerance approaches, but also application-level resilience, due to demanding efficiency and various domain-specific requirements. Scientific applications within a particular domain generally comply with domain conservation laws, which can be leveraged as an error detection criterion to study the resilience of this domain of applications sharing similar program characteristics. However, it is challenging to achieve application resilience: (a) how to identify the invariants of a given domain of applications, knowing the conservation laws, and (b) how to utilize the invariants to efficiently detect and recover from failures in application runs. In this work, we target several continuum dynamics software packages, FleCSALE [1] and CODY [2] (with intrinsic invariants during computation), study their resilience to soft errors online (injected using an open-source fault injector), and investigate the opportunities for non-intrusive and lightweight failure recovery (checksum-based invariant checking). We propose a checksum-retry approach to achieve our goals, and experimental results on a virtualized platform with extensive fault injection campaigns demonstrate the effectiveness and efficiency of the proposed approach.

cs.DC↗
arXiv2019

Failure Analysis and Quantification for Contemporary and Future Supercomputers

Large-scale computing systems today are assembled by numerous computing units for massive computational capability needed to solve problems at scale, which enables failures common events in supercomputing scenarios. Considering the demanding resilience requirements of supercomputers today, we present a quantitative study on fine-grained failure modeling for contemporary and future large-scale computing systems. We integrate various types of failures from different system hierarchical levels and system components, and summarize the overall system failure rates formally. Given that nowadays system-wise failure rate needs to be capped under a threshold value for reliability and cost-efficiency purposes, we quantitatively discuss different scenarios of system resilience, and analyze the impacts of resilience to different error types on the variation of system failure rates, and the correlation of hierarchical failure rates. Moreover, we formalize and showcase the resilience efficiency of failure-bounded supercomputers today.

cs.DC↗
arXiv2019

3D Virtual Garment Modeling from RGB Images

We present a novel approach that constructs 3D virtual garment models from photos. Unlike previous methods that require photos of a garment on a human model or a mannequin, our approach can work with various states of the garment: on a model, on a mannequin, or on a flat surface. To construct a complete 3D virtual model, our approach only requires two images as input, one front view and one back view. We first apply a multi-task learning network called JFNet that jointly predicts fashion landmarks and parses a garment image into semantic parts. The predicted landmarks are used for estimating sizing information of the garment. Then, a template garment mesh is deformed based on the sizing information to generate the final 3D model. The semantic parts are utilized for extracting color textures from input images. The results of our approach can be used in various Virtual Reality and Mixed Reality applications.

cs.CV↗
arXiv2019

Multilevel Monte Carlo theta EM scheme for SDDEs with small noise

In this paper, a multilevel Monte Carlo theta EM scheme is provided for stochastic differential delay equations with small noise. Under a global Lipschitz condition, the variance of two coupled paths is derived. Then, the global Lipschitz condition is replaced by one-sided Lipschitz condition, in order to guarantee the moment finiteness of numerical scheme, a modified multilevel Monte Carlo theta EM scheme is put forward and the second moment of two coupled paths is estimated.

math.NA↗
arXiv2018

Convergence rates of truncated EM scheme for NSDDEs

This paper is concerned with strong convergence of the truncated Euler-Maruyama scheme for neutral stochastic differential delay equations driven by Brownian motion and pure jumps respectively. Under local Lipschitz condition, convergence rates of the truncated EM scheme are given.

math.NA↗
arXiv2018

A note on strong convergence of implicit scheme for SDEs under local one-sided Lipschitz conditions

Under a local one-sided Lipschitz condition, Krylov [KR] proved the existence and uniqueness of the strong solutions for stochastic differential equations by using the Euler-Maruyama approximation, where he showed that the sequence of numerical solutions converges to the true solution in probability as the stepsize tends to zero. In this note, we shall extend the results in [KR] and investigate an implicit numerical scheme for these equations under a local one-sided Lipschitz condition.

math.NA↗
arXiv2017

Realization of t-bit semiclassical quantum Fourier transform on IBM's quantum cloud computer

To overcome the difficulty of realizing large-scale quantum Fourier transform (QFT) within existing technology, this paper presents a resource-saving method, namely t-bit semiclassical QFT over (Z_(2^n)), which could realize large-scale QFT using arbitrary-scale quantum register. Using our method, the scale of quantum register can be determined flexibility according to the scale of quantum system, enabling the quantum resource and speed of realizing QFT to be optimal. By developing a feasible method to realize the control quantum gate R_k, we experimentally demonstrate the 2-bit semiclassical QFT over (Z_(2^3)) on IBM's quantum cloud computer, showing the feasibility of our proposed method. Then, we compare the actual performance of 2-bit semiclassical QFT and standard QFT in the experiments. Experimental data show that the fidelity of the result of 2-bit semiclassical QFT is higher than that of standard QFT, which is mainly due to less two-qubit controlled gates are required in the semiclassical QFT. Furthermore, based on the proposed method, we successfully implement the Shor's algorithm to factorize N=15.

quant-ph↗