arXiv subjects

Hui Chen

Publications and source records attributed to Hui Chen.

At least 289 records · Page 16Linked to original sources

arXiv2021

DualDE: Dually Distilling Knowledge Graph Embedding for Faster and Cheaper Reasoning

Knowledge Graph Embedding (KGE) is a popular method for KG reasoning and training KGEs with higher dimension are usually preferred since they have better reasoning capability. However, high-dimensional KGEs pose huge challenges to storage and computing resources and are not suitable for resource-limited or time-constrained applications, for which faster and cheaper reasoning is necessary. To address this problem, we propose DualDE, a knowledge distillation method to build low-dimensional student KGE from pre-trained high-dimensional teacher KGE. DualDE considers the dual-influence between the teacher and the student. In DualDE, we propose a soft label evaluation mechanism to adaptively assign different soft label and hard label weights to different triples, and a two-stage distillation approach to improve the student's acceptance of the teacher. Our DualDE is general enough to be applied to various KGEs. Experimental results show that our method can successfully reduce the embedding parameters of a high-dimensional KGE by 7 times - 15 times and increase the inference speed by 2 times - 6 times while retaining a high performance. We also experimentally prove the effectiveness of our soft label evaluation mechanism and two-stage distillation approach via ablation study.

cs.AI↗

arXiv2021

AliCG: Fine-grained and Evolvable Conceptual Graph Construction for Semantic Search at Alibaba

Conceptual graphs, which is a particular type of Knowledge Graphs, play an essential role in semantic search. Prior conceptual graph construction approaches typically extract high-frequent, coarse-grained, and time-invariant concepts from formal texts. In real applications, however, it is necessary to extract less-frequent, fine-grained, and time-varying conceptual knowledge and build taxonomy in an evolving manner. In this paper, we introduce an approach to implementing and deploying the conceptual graph at Alibaba. Specifically, We propose a framework called AliCG which is capable of a) extracting fine-grained concepts by a novel bootstrapping with alignment consensus approach, b) mining long-tail concepts with a novel low-resource phrase mining approach, c) updating the graph dynamically via a concept distribution estimation method based on implicit and explicit user behaviors. We have deployed the framework at Alibaba UC Browser. Extensive offline evaluation as well as online A/B testing demonstrate the efficacy of our approach.

cs.AI↗

arXiv2021

Ghost Imaging Based on Recurrent Neural Network

Benefit from the promising features of second-order correlation, ghost imaging (GI) has received extensive attentions in recent years. Simultaneously, GI is affected by the poor trade-off between sampling rate and imaging quality. The traditional image reconstruction method in GI is to accumulate the action result of each speckle and the corresponding bucket signal. We found that the image reconstruction process of GI is very similar to the Recurrent Neural Network (RNN), which is one of the deep learning algorithm. In this paper, we proposed a novel method that effectively implements GI on the RNN architecture, called GI-RNN. The state of each layer in RNN is determined by the output of the previous layer and the input of this layer, and the output of the network is the sum of all previous states. Therefore, we take the speckle of each illumination and the corresponding bucket signal as the input of each layer, and the output of the network is the sum of all previous speckle and bucket signal, which is the image of the target. The testing results show that the proposed method can achieve image reconstruction at a very low sampling rate (0.38$\%$). Moreover, we compare GI-RNN with traditional GI algorithm and compressed sensing algorithm. The results of different targets show that GI-RNN is 6.61 dB higher than compressed sensing algorithm and 12.58 dB higher than traditional GI algorithm on average. In our view, the proposed method makes an important step to applications of GI.

eess.IV↗

arXiv2021

TeraMIMO: A Channel Simulator for Wideband Ultra-Massive MIMO Terahertz Communications

Following recent advances in terahertz (THz) technology, there is a consensus on the crucial role of THz communications in the next generation of wireless systems. Aiming at catalyzing THz communications research, we propose TeraMIMO, an accurate stochastic MATLAB simulator of statistical THz channels. We simulate ultra-massive multiple-input multiple-output antenna configurations as critical infrastructure enablers that overcome the limitation in THz communications distances. We consider both line-of-sight and multipath components and propose frequency- and delay-domain implementations for single- and multi-carrier paradigms in both time-invariant and time-variant scenarios. We implement exhaustive molecular absorption computations based on radiative transfer theory alongside alternative sub-THz approximations. We further model THz-specific constraints, including wideband beam split effects, spherical wave propagation, and misalignment fading. We verify TeraMIMO by analogy with measurement-based channel models in the literature and ergodic capacity analysis. We introduce a graphical user interface and a guide for using TeraMIMO in THz channel generation and analyses.

cs.IT↗

arXiv2021

DOA Estimation with Non-Uniform Linear Arrays: A Phase-Difference Projection Approach

Phase wrapping is a major problem in direction-of-arrival (DOA) estimation using phase-difference observations. For a sensor pair with an inter-sensor spacing greater than half of the wavelength ($λ/2$) of the signal, phase wrapping occurs at certain DOA angles leading to phase-difference ambiguities. Existing phase unwrapping methods exploit either frequency or spatial diversity. These techniques work by imposing restrictions on the utilized frequencies or the receiver array geometry. In addition to sensitivity to noise and calibration errors, these methods may also have high computational complexity. We propose a grid-less \emph{phase-difference projection} (PDP) DOA algorithm to overcome these issues. The concept of \emph{wrapped phased-difference pattern} (WPDP) is introduced, which allows the proposed algorithm to compute most of the parameters required for DOA estimation in an offline manner, hence resulting in a superior computational speed in realtime. Simulation results demonstrate the excellent performance of the proposed algorithm, both in terms of accuracy and speed.

eess.SP↗

arXiv2021

Multi-trends Enhanced Dynamic Micro-video Recommendation

The explosively generated micro-videos on content sharing platforms call for recommender systems to permit personalized micro-video discovery with ease. Recent advances in micro-video recommendation have achieved remarkable performance in mining users' current preference based on historical behaviors. However, most of them neglect the dynamic and time-evolving nature of users' preference, and the prediction on future micro-videos with historically mined preference may deteriorate the effectiveness of recommender systems. In this paper, we propose the DMR framework to explicitly model dynamic multi-trends of users' current preference and make predictions based on both the history and future potential trends. We devise the DMR framework, which comprises: 1) the implicit user network module which identifies sequence fragments from other users with similar interests and extracts the sequence fragments that are chronologically behind the identified fragments; 2) the multi-trend routing module which assigns each extracted sequence fragment into a trend group and update the corresponding trend vector; 3) the history-future trend prediction module jointly uses the history preference vectors and future trend vectors to yield the final click-through-rate. We validate the effectiveness of DMR over multiple state-of-the-art micro-video recommenders on two publicly available real-world datasets. Relatively extensive analysis further demonstrate the superiority of modeling dynamic multi-trend for micro-video recommendation.

cs.IR↗

arXiv2021

Learning to Ask for Data-Efficient Event Argument Extraction

Event argument extraction (EAE) is an important task for information extraction to discover specific argument roles. In this study, we cast EAE as a question-based cloze task and empirically analyze fixed discrete token template performance. As generating human-annotated question templates is often time-consuming and labor-intensive, we further propose a novel approach called "Learning to Ask," which can learn optimized question templates for EAE without human annotations. Experiments using the ACE-2005 dataset demonstrate that our method based on optimized questions achieves state-of-the-art performance in both the few-shot and supervised settings.

cs.CL↗

arXiv2021

Roton pair density wave and unconventional strong-coupling superconductivity in a topological kagome metal

The transition-metal kagome lattice materials host frustrated, correlated, and topological quantum states of matter. Recently, a new family of vanadium-based kagome metals AV3Sb5 (A=K, Rb, and Cs) with topological band structures has been discovered. These layered compounds are nonmagnetic and undergo charge density wave transitions before developing superconductivity at low temperatures. Here we report the observation of unconventional superconductivity and pair density wave (PDW) in CsV3Sb5 using scanning tunneling microscope/spectroscopy (STM/STS) and Josephson STS. We find that CsV3Sb5 exhibits a V-shaped pairing gap Δ~0.5 meV and is a strong-coupling superconductor (2Δ/kBTc~5) that coexists with 4a0 unidirectional and 2a0X2a0 charge order. Remarkably, we discover a 3Q PDW accompanied by bidirectional 4a0/3 spatial modulations of the superconducting gap, coherence peak and gap-depth in the tunneling conductance. We term this novel quantum state a roton-PDW associated with an underlying vortex-antivortex lattice that can account for the observed conductance modulations. Probing the electronic states in the vortex halo in an applied magnetic field, in strong-field that suppresses superconductivity, and in zero-field above Tc reveals that the PDW is a primary state responsible for an emergent pseudogap and intertwined electronic order. Our findings show striking analogies and distinctions to the phenomenology of high-Tc cuprate superconductors, and provide groundwork for understanding the microscopic origin of correlated electronic states and superconductivity in vanadium-based kagome metals.

cond-mat.supr-con↗

arXiv2021

Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis

In multimodal sentiment analysis (MSA), the performance of a model highly depends on the quality of synthesized embeddings. These embeddings are generated from the upstream process called multimodal fusion, which aims to extract and combine the input unimodal raw data to produce a richer multimodal representation. Previous work either back-propagates the task loss or manipulates the geometric property of feature spaces to produce favorable fusion results, which neglects the preservation of critical task-related information that flows from input to the fusion results. In this work, we propose a framework named MultiModal InfoMax (MMIM), which hierarchically maximizes the Mutual Information (MI) in unimodal input pairs (inter-modality) and between multimodal fusion result and unimodal input in order to maintain task-related information through multimodal fusion. The framework is jointly trained with the main task (MSA) to improve the performance of the downstream MSA task. To address the intractable issue of MI bounds, we further formulate a set of computationally simple parametric and non-parametric methods to approximate their truth value. Experimental results on the two widely used datasets demonstrate the efficacy of our approach. The implementation of this work is publicly available at https://github.com/declare-lab/Multimodal-Infomax.

cs.CL↗

arXiv2021

Generative-Adversarial-Networks-based Ghost Recognition

Nowadays, target recognition technique plays an important role in many fields. However, the current target image information based methods suffer from the influence of image quality and the time cost of image reconstruction. In this paper, we propose a novel imaging-free target recognition method combining ghost imaging (GI) and generative adversarial networks (GAN). Based on the mechanism of GI, a set of random speckles sequence is employed to illuminate target, and a bucket detector without resolution is utilized to receive echo signal. The bucket signal sequence formed after continuous detections is constructed into a bucket signal array, which is regarded as the sample of GAN. Then, conditional GAN is used to map bucket signal array and target category. In practical application, the speckles sequence in training step is employed to illuminate target, and the bucket signal array is input GAN for recognition. The proposed method can improve the problems caused by conventional recognition methods that based on target image information, and provide a certain turbulence-free ability. Extensive experiments show that the proposed method achieves promising performance.

cs.CV↗

arXiv2021

Bi-Bimodal Modality Fusion for Correlation-Controlled Multimodal Sentiment Analysis

Multimodal sentiment analysis aims to extract and integrate semantic information collected from multiple modalities to recognize the expressed emotions and sentiment in multimodal data. This research area's major concern lies in developing an extraordinary fusion scheme that can extract and integrate key information from various modalities. However, one issue that may restrict previous work to achieve a higher level is the lack of proper modeling for the dynamics of the competition between the independence and relevance among modalities, which could deteriorate fusion outcomes by causing the collapse of modality-specific feature space or introducing extra noise. To mitigate this, we propose the Bi-Bimodal Fusion Network (BBFN), a novel end-to-end network that performs fusion (relevance increment) and separation (difference increment) on pairwise modality representations. The two parts are trained simultaneously such that the combat between them is simulated. The model takes two bimodal pairs as input due to the known information imbalance among modalities. In addition, we leverage a gated control mechanism in the Transformer architecture to further improve the final output. Experimental results on three datasets (CMU-MOSI, CMU-MOSEI, and UR-FUNNY) verifies that our model significantly outperforms the SOTA. The implementation of this work is available at https://github.com/declare-lab/multimodal-deep-learning.

cs.AI↗

arXiv2021

Text-guided Legal Knowledge Graph Reasoning

Recent years have witnessed the prosperity of legal artificial intelligence with the development of technologies. In this paper, we propose a novel legal application of legal provision prediction (LPP), which aims to predict the related legal provisions of affairs. We formulate this task as a challenging knowledge graph completion problem, which requires not only text understanding but also graph reasoning. To this end, we propose a novel text-guided graph reasoning approach. We collect amounts of real-world legal provision data from the Guangdong government service website and construct a legal dataset called LegalLPP. Extensive experimental results on the dataset show that our approach achieves better performance compared with baselines. The code and dataset are available in \url{https://github.com/zxlzr/LegalPP} for reproducibility.

cs.AI↗

arXiv2021

Knowledge Perceived Multi-modal Pretraining in E-commerce

In this paper, we address multi-modal pretraining of product data in the field of E-commerce. Current multi-modal pretraining methods proposed for image and text modalities lack robustness in the face of modality-missing and modality-noise, which are two pervasive problems of multi-modal product data in real E-commerce scenarios. To this end, we propose a novel method, K3M, which introduces knowledge modality in multi-modal pretraining to correct the noise and supplement the missing of image and text modalities. The modal-encoding layer extracts the features of each modality. The modal-interaction layer is capable of effectively modeling the interaction of multiple modalities, where an initial-interactive feature fusion model is designed to maintain the independence of image modality and text modality, and a structure aggregation module is designed to fuse the information of image, text, and knowledge modalities. We pretrain K3M with three pretraining tasks, including masked object modeling (MOM), masked language modeling (MLM), and link prediction modeling (LPM). Experimental results on a real-world E-commerce dataset and a series of product-based downstream tasks demonstrate that K3M achieves significant improvements in performances than the baseline and state-of-the-art methods when modality-noise or modality-missing exists.

cs.CV↗

arXiv2021

0.8% Nyquist computational ghost imaging via non-experimental deep learning

We present a framework for computational ghost imaging based on deep learning and customized pink noise speckle patterns. The deep neural network in this work, which can learn the sensing model and enhance image reconstruction quality, is trained merely by simulation. To demonstrate the sub-Nyquist level in our work, the conventional computational ghost imaging results, reconstructed imaging results using white noise and pink noise via deep learning are compared under multiple sampling rates at different noise conditions. We show that the proposed scheme can provide high-quality images with a sampling rate of 0.8% even when the object is outside the training dataset, and it is robust to noisy environments. This method is excellent for various applications, particularly those that require a low sampling rate, fast reconstruction efficiency, or experience strong noise interference.

eess.IV↗

arXiv2021

Observing two-photon subwavelength interference of broadband chaotic light in polarization-selective Michelson interferometer

Differing from the traditional method of achieving subwavelength interference, we have demonstrated the two-photon subwavelength interference effect of broadband chaotic light in a polarization-selective Michelson interferometer with an ultrafast two-photon absorption detector the first time, which is achieved by manipulating two-photon probability amplitudes involved in the interference. In theory, the two-photon polarization coherence matrix and probability amplitudes matrix are combined to develop polarized two-photon interference terms, which explains the experimental results well. In order to make better use of this interferometer to produce the subwavelength effect, we also make a series of error analyses to find out the relationship between the visibility and the degree of polarization error. Our experimental and theoretical results are helpful to understand the two-photon subwavelength interference, which sheds light on the development of the two-photon interference theory of vector light field based on quantum mechanics. These experimental results may help to develop future optical interferometry, optical polarimetry, and subwavelength lithography.

quant-ph↗

arXiv2021

Evidence of a hidden flux phase in the topological kagome metal CsV$_3$Sb$_5$

Phase transitions governed by spontaneous time reversal symmetry breaking (TRSB) have long been sought in many quantum systems, including materials with anomalous Hall effect (AHE), cuprate high temperature superconductors, Iridates and so on. However, experimentally identifying such a phase transition is extremely challenging because the transition is hidden from many experimental probes. Here, using zero-field muon spin relaxation (ZF-$μ$SR) technique, we observe strong TRSB signals below 70 K in the newly discovered kagome superconductor CsV$_3$Sb$_5$. The TRSB state emerges from the 2 x 2 charge density wave (CDW) phase present below ~ 95 K. By carrying out optical second-harmonic generation (SHG) experiments, we also find that inversion symmetry is maintained in the temperature range of interest. Combining all the experimental results and symmetry constraints, we conclude that the interlayer coupled chiral flux phase (CFP) is the most promising candidate for the TRSB state among all theoretical proposals of orbital current orders. Thus, this prototypical kagome metal CsV3Sb5 can be a platform to establish a TRSB current-ordered state and explore its relationship with CDW, giant AHE, and superconductivity.

cond-mat.supr-con↗

arXiv2021

Serrin-type regularity criteria for the 3D MHD equations via one velocity component and one magnetic component

In this paper, we consider the Cauchy problem to the 3D MHD equations. We show that the Serrin--type conditions imposed on one component of the velocity $u_{3}$ and one component of magnetic fields $b_{3}$ with $$ u_{3} \in L^{p_{0},1}(-1,0;L^{q_{0}}(B(2))),\ b_{3} \in L^{p_{1},1}(-1,0;L^{q_{1}}(B(2))), $$ $\frac{2}{p_{0}}+\frac{3}{q_{0}}=\frac{2}{p_{1}}+\frac{3}{q_{1}}=1$ and $3<q_{0},q_{1}<+\infty$ imply that the suitable weak solution is regular at $(0,0)$. The proof is based on the new local energy estimates introduced by Chae-Wolf (Arch. Ration. Mech. Anal. 2021) and Wang-Wu-Zhang (arXiv:2005.11906).

math.AP↗

arXiv2021

Intrinsically Honeycomb-patterned Hydrogenated Graphene with Spin Polarized Edge-states

Since the advent of graphene ushered the era of two-dimensional materials, many forms of hydrogenated graphene have been reported, exhibiting diverse properties ranging from a tunable band gap to ferromagnetic ordering. Patterned hydrogenated graphene with micron-scale patterns has been fabricated by lithographic means. Here we report successful millimeter-scale synthesis of an intrinsically honeycomb patterned form of hydrogenated graphene on Ru(0001) by epitaxial growth followed by hydrogenation. Combining scanning tunneling microscopy observations with density-functional-theory (DFT) calculations, we reveal that an atomic-hydrogen layer intercalates between graphene and Ru(0001). The result is a hydrogen honeycomb structure that serves as a template for the final hydrogenation, which converts the graphene into graphane only over the template, yielding honeycomb-patterned hydrogenated graphene (HPHG). In effect, HPHG is a form of patterned graphane. DFT calculations find that the unhydrogenated graphene regions embedded in the patterned graphane exhibit spin-polarized edge states. This type of growth mechanism provides new pathways for the fabrication of intrinsically patterned graphene-based materials.

cond-mat.mtrl-sci↗