arXiv subjects

Rui Zhang

Publications and source records attributed to Rui Zhang.

At least 901 records · Page 50Linked to original sources

arXiv2021

Neural Graph Matching based Collaborative Filtering

User and item attributes are essential side-information; their interactions (i.e., their co-occurrence in the sample data) can significantly enhance prediction accuracy in various recommender systems. We identify two different types of attribute interactions, inner interactions and cross interactions: inner interactions are those between only user attributes or those between only item attributes; cross interactions are those between user attributes and item attributes. Existing models do not distinguish these two types of attribute interactions, which may not be the most effective way to exploit the information carried by the interactions. To address this drawback, we propose a neural Graph Matching based Collaborative Filtering model (GMCF), which effectively captures the two types of attribute interactions through modeling and aggregating attribute interactions in a graph matching structure for recommendation. In our model, the two essential recommendation procedures, characteristic learning and preference matching, are explicitly conducted through graph learning (based on inner interactions) and node matching (based on cross interactions), respectively. Experimental results show that our model outperforms state-of-the-art models. Further studies verify the effectiveness of GMCF in improving the accuracy of recommendation.

cs.IR↗

arXiv2021

WGCN: Graph Convolutional Networks with Weighted Structural Features

Graph structural information such as topologies or connectivities provides valuable guidance for graph convolutional networks (GCNs) to learn nodes' representations. Existing GCN models that capture nodes' structural information weight in- and out-neighbors equally or differentiate in- and out-neighbors globally without considering nodes' local topologies. We observe that in- and out-neighbors contribute differently for nodes with different local topologies. To explore the directional structural information for different nodes, we propose a GCN model with weighted structural features, named WGCN. WGCN first captures nodes' structural fingerprints via a direction and degree aware Random Walk with Restart algorithm, where the walk is guided by both edge direction and nodes' in- and out-degrees. Then, the interactions between nodes' structural fingerprints are used as the weighted node structural features. To further capture nodes' high-order dependencies and graph geometry, WGCN embeds graphs into a latent space to obtain nodes' latent neighbors and geometrical relationships. Based on nodes' geometrical relationships in the latent space, WGCN differentiates latent, in-, and out-neighbors with an attention-based geometrical aggregation. Experiments on transductive node classification tasks show that WGCN outperforms the baseline models consistently by up to 17.07% in terms of accuracy on five benchmark datasets.

cs.LG↗

arXiv2021

Intelligent Reflecting Surface Aided Multi-User Communication: Capacity Region and Deployment Strategy

Intelligent reflecting surface (IRS) is a new promising technology that is able to reconfigure the wireless propagation channel via smart and passive signal reflection. In this paper, we investigate the capacity region of a two-user communication network with one access point (AP) aided by $M$ IRS elements for enhancing the user-AP channels, where the IRS incurs negligible delay, thus the user-AP channels via the IRS follow the classic discrete memoryless channel model. In particular, we consider two practical IRS deployment strategies that lead to different effective channels between the users and AP, namely, the distributed deployment where the $M$ elements form two IRSs, each deployed in the vicinity of one user, versus the centralized deployment where all the $M$ elements are deployed in the vicinity of the AP. First, we consider the uplink multiple-access channel (MAC) and derive the capacity/achievable rate regions for both deployment strategies under different multiple access schemes. It is shown that the centralized deployment generally outperforms the distributed deployment under symmetric channel setups in terms of achievable user rates. Next, we extend the results to the downlink broadcast channel (BC) by leveraging the celebrated uplink-downlink (or MAC-BC) duality framework, and show that the superior rate performance of centralized over distributed deployment also holds. Numerical results are presented that validate our analysis, and reveal new and useful insights for optimal IRS deployment in wireless networks.

cs.IT↗

arXiv2021

Coarse-grained Soft-Clusters Remain non-Diffusing in the Melt State

Melts of 3-dimensional dendritic beads-springs, namely coarse-grained soft-clusters, are studied by molecular dynamics simulations. The goal is to elucidate the unique dynamics of giant molecules, or generally speaking, 3-dimensional architectured polymers. When constituted by more than the critical number around 200 beads, soft-clusters cannot diffuse or relax far above their glass transition temperature, although relaxation can happen on the level of beads. Each soft-cluster can only rotate in the cage formed by neighboring soft-clusters. Such a non-diffusing state would transform to the liquid state at exceptionally high temperature, e.g. 10 times the glass transition temperature. Agreeing with experiments, 3D hierarchies lead to unique dynamics, especially their divergent relaxation times with the number of beads. These unique dynamics are in sharp contrast with 1-dimensional chain-like polymers. We name such a special state as 'cooperative glass', because of the 'cooperation' of the 3D-connected beads. The design of soft-clusters may also resemble cooperative rearranging regions where cooperativeness is contributed by low temperature, thus offer further insights into the glass problem.

cond-mat.soft↗

arXiv2021

Probing Top-philic New Physics via Four-Top-Quark Production

We explore constraints on various new physics resonances from four top-quark production based on current experimental data. Both light and heavy resonances are studied in the work. A comparison of full width effect and narrow width approximation is also made.

hep-ph↗

arXiv2021

Intelligent Reflecting Surface Aided Wireless Energy and Information Transmission: An Overview

Intelligent reflecting surface (IRS) is a promising technology for achieving spectrum and energy efficient wireless networks cost-effectively. Most existing works on IRS have focused on exploiting IRS to enhance the performance of wireless communication or wireless information transmission (WIT), while its potential for boosting the efficiency of radio-frequency (RF) wireless energy transmission (WET) still remains largely open. Although IRS-aided WET shares similar characteristics with IRS-aided WIT, they differ fundamentally in terms of design objective, receiver architecture, and practical constraints. In this paper, we provide a tutorial overview on how to efficiently design IRS-aided WET systems as well as IRS-aided systems with both WIT and WET, namely IRS-aided simultaneous wireless information and power transfer (SWIPT) and IRS-aided wireless powered communication network (WPCN), mainly from a communication and signal processing perspective. In particular, we present state-of-the-art solutions to tackle the unique challenges in operating these systems, such as IRS passive reflection optimization, channel estimation and deployment. In addition, we also propose new solution approaches and point out important directions for future research and investigation.

cs.IT↗

arXiv2021

Discovering novel drug-supplement interactions using a dietary supplements knowledge graph generated from the biomedical literature

OBJECTIVE: Leverage existing biomedical NLP tools and DS domain terminology to produce a novel and comprehensive knowledge graph containing dietary supplement (DS) information for discovering interactions between DS and drugs, or Drug-Supplement Interactions (DSI). MATERIALS AND METHODS: We created SemRepDS (an extension of SemRep), capable of extracting semantic relations from abstracts by leveraging a DS-specific terminology (iDISK) containing 28,884 DS terms not found in the UMLS. PubMed abstracts were processed using SemRepDS to generate semantic relations, which were then filtered using a PubMedBERT-based model to remove incorrect relations before generating our knowledge graph (SuppKG). Two pathways are used to identify potential DS-Drug interactions which are then evaluated by medical professionals for mechanistic plausibility. RESULTS: Comparison analysis found that SemRepDS returned 206.9% more DS relations and 158.5% more DS entities than SemRep. The fine-tuned BERT model obtained an F1 score of 0.8605 and removed 43.86% of the relations, improving the precision of the relations by 26.4% compared to pre-filtering. SuppKG consists of 2,928 DS-specific nodes. Manual review of findings identified 44 (88%) proposed DS-Gene-Drug and 32 (64%) proposed DS-Gene1-Function-Gene2-Drug pathways to be mechanistically plausible. DISCUSSION: The additional relations extracted using SemRepDS generated SuppKG that was used to find plausible DSI not found in the current literature. By the nature of the SuppKG, these interactions are unlikely to have been found using SemRep without the expanded DS terminology. CONCLUSION: We successfully extend SemRep to include DS information and produce SuppKG which can be used to find potential DS-Drug interactions.

cs.IR↗

arXiv2021

IRS Meets Relaying: Joint Resource Allocation and Passive Beamforming Optimization

Intelligent reflecting surface (IRS) has recently emerged as a new solution to enhance wireless communication performance via passive signal reflection. In this letter, we unlock the potential of IRS controller in relaying information and propose a novel IRS-assisted communication system with both IRS passive reflection and active relaying. Specifically, we jointly optimize the time allocations for decode-and-forward (DF) relaying by the IRS controller and the IRS passive beamforming to maximize the achievable rate of the proposed system. We also compare the rate performance of the proposed system with the conventional IRS without relaying, and reveal the conditions for one to outperform the other. Simulation results demonstrate that the proposed new design can significantly improve the coverage/rate performance of IRS-assisted systems.

cs.IT↗

arXiv2021

Structured in Space, Randomized in Time: Leveraging Dropout in RNNs for Efficient Training

Recurrent Neural Networks (RNNs), more specifically their Long Short-Term Memory (LSTM) variants, have been widely used as a deep learning tool for tackling sequence-based learning tasks in text and speech. Training of such LSTM applications is computationally intensive due to the recurrent nature of hidden state computation that repeats for each time step. While sparsity in Deep Neural Nets has been widely seen as an opportunity for reducing computation time in both training and inference phases, the usage of non-ReLU activation in LSTM RNNs renders the opportunities for such dynamic sparsity associated with neuron activation and gradient values to be limited or non-existent. In this work, we identify dropout induced sparsity for LSTMs as a suitable mode of computation reduction. Dropout is a widely used regularization mechanism, which randomly drops computed neuron values during each iteration of training. We propose to structure dropout patterns, by dropping out the same set of physical neurons within a batch, resulting in column (row) level hidden state sparsity, which are well amenable to computation reduction at run-time in general-purpose SIMD hardware as well as systolic arrays. We conduct our experiments for three representative NLP tasks: language modelling on the PTB dataset, OpenNMT based machine translation using the IWSLT De-En and En-Vi datasets, and named entity recognition sequence labelling using the CoNLL-2003 shared task. We demonstrate that our proposed approach can be used to translate dropout-based computation reduction into reduced training time, with improvement ranging from 1.23x to 1.64x, without sacrificing the target metric.

cs.LG↗

arXiv2021

Deep Learning Models in Detection of Dietary Supplement Adverse Event Signals from Twitter

Objective: The objective of this study is to develop a deep learning pipeline to detect signals on dietary supplement-related adverse events (DS AEs) from Twitter. Material and Methods: We obtained 247,807 tweets ranging from 2012 to 2018 that mentioned both DS and AE. We annotated biomedical entities and relations on 2,000 randomly selected tweets. For the concept extraction task, we compared the performance of traditional word embeddings with SVM, CRF and LSTM-CRF classifiers to BERT models. For the relation extraction task, we compared GloVe vectors with CNN classifiers to BERT models. We chose the best performing models in each task to assemble an end-to-end deep learning pipeline to detect DS AE signals and compared the results to the known DS AEs from a DS knowledge base (i.e., iDISK). Results: In both tasks, the BERT-based models outperformed traditional word embeddings. The best performing concept extraction model is the BioBERT model that can identify supplement, symptom, and body organ entities with F1-scores of 0.8646, 0.8497, and 0.7104, respectively. The best performing relation extraction model is the BERT model that can identify purpose and AE relations with F1-scores of 0.8335 and 0.7538, respectively. The end-to-end pipeline was able to extract DS indication and DS AEs with an F1-score of 0.7459 and 0,7414, respectively. Comparing to the iDISK, we could find both known and novel DS-AEs. Conclusion: We have demonstrated the feasibility of detecting DS AE signals from Twitter with a BioBERT-based deep learning pipeline.

cs.CL↗

arXiv2021

Deep Contrastive Graph Representation via Adaptive Homotopy Learning

Homotopy model is an excellent tool exploited by diverse research works in the field of machine learning. However, its flexibility is limited due to lack of adaptiveness, i.e., manual fixing or tuning the appropriate homotopy coefficients. To address the problem above, we propose a novel adaptive homotopy framework (AH) in which the Maclaurin duality is employed, such that the homotopy parameters can be adaptively obtained. Accordingly, the proposed AH can be widely utilized to enhance the homotopy-based algorithm. In particular, in this paper, we apply AH to contrastive learning (AHCL) such that it can be effectively transferred from weak-supervised learning (given label priori) to unsupervised learning, where soft labels of contrastive learning are directly and adaptively learned. Accordingly, AHCL has the adaptive ability to extract deep features without any sort of prior information. Consequently, the affinity matrix formulated by the related adaptive labels can be constructed as the deep Laplacian graph that incorporates the topology of deep representations for the inputs. Eventually, extensive experiments on benchmark datasets validate the superiority of our method.

cs.CV↗

arXiv2021

Shuffle Transformer with Feature Alignment for Video Face Parsing

This is a short technical report introducing the solution of the Team TCParser for Short-video Face Parsing Track of The 3rd Person in Context (PIC) Workshop and Challenge at CVPR 2021. In this paper, we introduce a strong backbone which is cross-window based Shuffle Transformer for presenting accurate face parsing representation. To further obtain the finer segmentation results, especially on the edges, we introduce a Feature Alignment Aggregation (FAA) module. It can effectively relieve the feature misalignment issue caused by multi-resolution feature aggregation. Benefiting from the stronger backbone and better feature aggregation, the proposed method achieves 86.9519% score in the Short-video Face Parsing track of the 3rd Person in Context (PIC) Workshop and Challenge, ranked the first place.

cs.CV↗

arXiv2021

Non-Gradient Manifold Neural Network

Deep neural network (DNN) generally takes thousands of iterations to optimize via gradient descent and thus has a slow convergence. In addition, softmax, as a decision layer, may ignore the distribution information of the data during classification. Aiming to tackle the referred problems, we propose a novel manifold neural network based on non-gradient optimization, i.e., the closed-form solutions. Considering that the activation function is generally invertible, we reconstruct the network via forward ridge regression and low rank backward approximation, which achieve the rapid convergence. Moreover, by unifying the flexible Stiefel manifold and adaptive support vector machine, we devise the novel decision layer which efficiently fits the manifold structure of the data and label information. Consequently, a jointly non-gradient optimization method is designed to generate the network with closed-form results. Eventually, extensive experiments validate the superior performance of the model.

cs.LG↗

arXiv2021

Social and behavioral determinants of health in the era of artificial intelligence with electronic health records: A scoping review

Background: There is growing evidence that social and behavioral determinants of health (SBDH) play a substantial effect in a wide range of health outcomes. Electronic health records (EHRs) have been widely employed to conduct observational studies in the age of artificial intelligence (AI). However, there has been little research into how to make the most of SBDH information from EHRs. Methods: A systematic search was conducted in six databases to find relevant peer-reviewed publications that had recently been published. Relevance was determined by screening and evaluating the articles. Based on selected relevant studies, a methodological analysis of AI algorithms leveraging SBDH information in EHR data was provided. Results: Our synthesis was driven by an analysis of SBDH categories, the relationship between SBDH and healthcare-related statuses, and several NLP approaches for extracting SDOH from clinical literature. Discussion: The associations between SBDH and health outcomes are complicated and diverse; several pathways may be involved. Using Natural Language Processing (NLP) technology to support the extraction of SBDH and other clinical ideas simplifies the identification and extraction of essential concepts from clinical data, efficiently unlocks unstructured data, and aids in the resolution of unstructured data-related issues. Conclusion: Despite known associations between SBDH and disease, SBDH factors are rarely investigated as interventions to improve patient outcomes. Gaining knowledge about SBDH and how SBDH data can be collected from EHRs using NLP approaches and predictive models improves the chances of influencing health policy change for patient wellness, and ultimately promoting health and health equity. Keywords: Social and Behavioral Determinants of Health, Artificial Intelligence, Electronic Health Records, Natural Language Processing, Predictive Model

cs.CY↗

arXiv2021

Wireless Communication with Extremely Large-Scale Intelligent Reflecting Surface

Intelligent reflecting surface (IRS) is a promising technology for wireless communications, thanks to its potential capability to engineer the radio environment. However, in practice, such an envisaged benefit is attainable only when the passive IRS is of a sufficiently large size, for which the conventional uniform plane wave (UPW)-based channel model may become inaccurate. In this paper, we pursue a new channel modelling and performance analysis for wireless communications with extremely large-scale IRS (XL-IRS). By taking into account the variations in signal's amplitude and projected aperture across different reflecting elements, we derive both lower- and upper-bounds of the received signal-to-noise ratio (SNR) for the general uniform planar array (UPA)-based XL-IRS. Our results reveal that, instead of scaling quadratically with the increased number of reflecting elements M as in the conventional UPW model, the SNR under the more practically applicable non-UPW model increases with M only with a diminishing return and gets saturated eventually. To gain more insights, we further study the special case of uniform linear array (ULA)-based XL-IRS, for which a closed-form SNR expression in terms of the IRS size and transmitter/receiver location is derived. This result shows that the SNR mainly depends on the two geometric angles formed by the transmitter/receiver locations with the IRS, as well as the boundary points of the IRS. Numerical results validate our analysis and demonstrate the importance of proper channel modelling for wireless communications aided by XL-IRS.

cs.IT↗

arXiv2021

Single-shot quantitative polarization imaging of complex birefringent structure dynamics

Polarization light microscopes are powerful tools for probing molecular order and orientation in birefringent materials. While a multitude of polarization light microscopy techniques are often used to access steady-state properties of birefringent samples, quantitative measurements of the molecular orientation dynamics on the millisecond time scale have remained a challenge. We propose polarized shearing interference microscopy (PSIM), a single-shot quantitative polarization imaging method, for extracting the retardance and orientation angle of the laser beam transmitting through optically anisotropic specimens with complex structures. The measurement accuracy and imaging performances of PSIM are validated by imaging a rotating wave plate and a bovine tendon specimen. We demonstrate that PSIM can quantify the dynamics of a flowing lyotropic chromonic liquid crystal in a microfluidic channel at an imaging speed of 506 frames per second (only limited by the camera frame rate), with a field-of-view of up to $350\times350 μm^2$ and a diffraction-limit spatial resolution of $\sim 2μm$. We envision that PSIM will find a broad range of applications in quantitative material characterization under dynamical conditions.

physics.optics↗

arXiv2021

Security and Privacy for Healthcare Blockchains

Healthcare blockchains provide an innovative way to store healthcare information, execute healthcare transactions, and build trust for healthcare data sharing and data integration in a decentralized open healthcare network environment. Although the healthcare blockchain technology has attracted broad interests and attention in industry, government and academia, the security and privacy concerns remain the focus of debate when deploying blockchains for information sharing in the healthcare sector from business operation to research collaboration. This paper focuses on the security and privacy requirements for medical data sharing using blockchain, and provides a comprehensive analysis of the security and privacy risks and requirements, accompanied by technical solution techniques and strategies. First, we discuss the security and privacy requirements and attributes required for electronic medical data sharing by deploying the healthcare blockchain. Second, we categorize existing efforts into three reference blockchain usage scenarios for electronic medical data sharing, and discuss the technologies for implementing these security and privacy properties in the three categories of usage scenarios for healthcare blockchain, such as anonymous signatures, attribute-based encryption, zero-knowledge proofs, verification techniques for smart contract security. Finally, we discuss other potential blockchain application scenarios in healthcare sector. We conjecture that this survey will help healthcare professionals, decision makers, and healthcare service developers to gain technical and intuitive insights into the security and privacy of healthcare blockchains in terms of concepts, risks, requirements, development and deployment technologies and systems.

cs.CR↗

arXiv2021

Instrument Space Selection for Kernel Maximum Moment Restriction

Kernel maximum moment restriction (KMMR) recently emerges as a popular framework for instrumental variable (IV) based conditional moment restriction (CMR) models with important applications in conditional moment (CM) testing and parameter estimation for IV regression and proximal causal learning. The effectiveness of this framework, however, depends critically on the choice of a reproducing kernel Hilbert space (RKHS) chosen as a space of instruments. In this work, we presents a systematic way to select the instrument space for parameter estimation based on a principle of the least identifiable instrument space (LIIS) that identifies model parameters with the least space complexity. Our selection criterion combines two distinct objectives to determine such an optimal space: (i) a test criterion to check identifiability; (ii) an information criterion based on the effective dimension of RKHSs as a complexity measure. We analyze the consistency of our method in determining the LIIS, and demonstrate its effectiveness for parameter estimation via simulations.

cs.LG↗