arXiv subjects

Sheng Li

Publications and source records attributed to Sheng Li.

At least 253 records · Page 14Linked to original sources

arXiv2020

Co-embedding of Nodes and Edges with Graph Neural Networks

Graph, as an important data representation, is ubiquitous in many real world applications ranging from social network analysis to biology. How to correctly and effectively learn and extract information from graph is essential for a large number of machine learning tasks. Graph embedding is a way to transform and encode the data structure in high dimensional and non-Euclidean feature space to a low dimensional and structural space, which is easily exploited by other machine learning algorithms. We have witnessed a huge surge of such embedding methods, from statistical approaches to recent deep learning methods such as the graph convolutional networks (GCN). Deep learning approaches usually outperform the traditional methods in most graph learning benchmarks by building an end-to-end learning framework to optimize the loss function directly. However, most of the existing GCN methods can only perform convolution operations with node features, while ignoring the handy information in edge features, such as relations in knowledge graphs. To address this problem, we present CensNet, Convolution with Edge-Node Switching graph neural network, for learning tasks in graph-structured data with both node and edge features. CensNet is a general graph embedding framework, which embeds both nodes and edges to a latent feature space. By using line graph of the original undirected graph, the role of nodes and edges are switched, and two novel graph convolution operations are proposed for feature propagation. Experimental results on real-world academic citation networks and quantum chemistry graphs show that our approach achieves or matches the state-of-the-art performance in four graph learning tasks, including semi-supervised node classification, multi-task graph classification, graph regression, and link prediction.

cs.LG↗

arXiv2020

Novel polymorphic phase of BaCu2As2: impact of flux for new phase formation in crystal growth

In this work, we have thoroughly studied the effects of flux composition and temperature on the crystal growth of the BaCu2As2 compound. While Pb and CuAs self-flux produce the well-known α-phase ThCr2Si2-type structure (Z=2), a new polymorphic phase of BaCu2As2 (\b{eta} phase) with a much larger c lattice parameter (Z=10), which could be considered an intergrowth of the ThCr2Si2- and CaBe2Ge2-type structures, has been discovered via Sn flux growth. We have characterized this structure through single-crystal X-ray diffraction, transmission electron microscopy (TEM), and scanning transmission electron microscopy (STEM) studies. Furthermore, we compare this new polymorphic intergrowth structure with the α-phase BaCu2As2 (ThCr2Si2 type with Z=2) and the \b{eta}-phase BaCu2Sb2 (intergrowth of ThCr2Si2 and CaBe2Ge2 types with Z=6), both with the same space group I4/mmm. Electrical transport studies reveal p-type carriers and magnetoresistivity up to 22% at 5 K and under a magnetic field of 7 T. Our work suggests a new route for the discovery of new polymorphic structures through flux and temperature control during material synthesis.

cond-mat.mtrl-sci↗

arXiv2020

Canted Antiferromagnetism in the Quasi-1D Iron Chalcogenide BaFe$_{2}$Se$_{4}$

We report the synthesis and physical properties studies of quais-1D iron chalcogenide $\rm BaFe_2Se_4$ which shares the $\rm FeSe_4$ tetrahedra building motif commonly seen in the iron chalcogenide superconductors. A high-quality polycrystalline sample was achieved by solid-state reaction method and characterized by X-ray diffraction, electrical resistivity, magnetic susceptibility and neutron diffraction measurements. $\rm BaFe_2Se_4$ is a narrow gap semiconductor that magnetically orders at $\sim$ 310 K. Both neutron powder diffraction results and isothermal M-H loops suggest a canted antiferromagnetic structure where Fe sublattice are antiferromagnetically ordered along the c-axis quasi-1D chain direction, resulting in a net ferromagnetic moment in the perpendicular direction along the a-axis with tilted angle of 18.7$^\circ$ towards the b-axis.

cond-mat.str-el↗

arXiv2020

Effect of isotope disorder on the Raman spectra of cubic boron arsenide

Boron arsenide (c-BAs) is at the forefront of research on ultrahigh thermal conductivity materials. We present a Raman scattering study of isotopically tailored cubic boron arsenide single crystals for 11 isotopic compositions spanning the range from nearly pure c-$^{10}$BAs to nearly pure c-$^{11}$BAs. Our results provide insights on the effects of strong mass disorder on optical phonons and the appearance of two-mode behavior in the Raman spectra of mixed crystals. Strong isotope disorder also relaxes the one-phonon Raman selection rules, resulting in disorder-activated Raman scattering by acoustic phonons.

cond-mat.mtrl-sci↗

arXiv2020

Analysis of Fleet Management and Network Design for On-Demand Urban Air Mobility Operations

A significant challenge in estimating operational feasibility of Urban Air Mobility (UAM) missions lies in understanding how choices in design impact the performance of a complex system-of-systems. This work examines the ability of the UAM ecosystem and the operations within it to meet a variety of demand profiles that may emerge in the coming years. We perform a set of simulation driven feasibility and scalability analyses based on UAM operational models with the goal of estimating capacity and throughput for a given set of parameters that represent an operational UAM ecosystem. UAM ecosystem design guidelines, vehicle constraints, and effective operational policies can be drawn from our analysis. Results show that, while critical for enabling UAM, the performance of the UAM ecosystem is robust to variations in ground infrastructure and fleet design decisions, while being sensitive to decisions for fleet and traffic management policies. We show that so long as the ecosystem design parameters for ground infrastructure and fleet design fall within a sensible range, the performance of the UAM ecosystem is affected by the policies used to manage the UAM traffic.

cs.OH↗

arXiv2020

Non-Abelian Aharonov-Bohm Caging in Photonic Lattices

Aharonov-Bohm (AB) caging is the localization effect in translational-invariant lattices due to destructive interference induced by penetrated magnetic fields. While current research focuses mainly on the case of Abelian AB caging, here we go beyond and develop the non-Abelian AB caging concept by considering the particle localization in a 1D multi-component rhombic lattice with non-Abelian background gauge field. In contrast to its Abelian counterpart, the non-Abelian AB cage depends on both the form of the nilpotent interference matrix and the initial state of the lattice. This phenomena is the consequence of the non-Abelian nature of the gauge potential and thus has no Abelian analog. We further propose a circuit quantum electrodynamics realization of the proposed physics, in which the required non-Abelian gauge field can be synthesized by the parametric conversion method, and the non-Abelian AB caging can be unambiguously demonstrated through the pumping and the steady-state measurements of only a few sites on the lattice. Requiring only currently available technique, our proposal can be readily tested in experiment and may pave a new route towards the investigation of exotic photonic quantum fluids.

quant-ph↗

arXiv2020

Cross-scale Attention Model for Acoustic Event Classification

A major advantage of a deep convolutional neural network (CNN) is that the focused receptive field size is increased by stacking multiple convolutional layers. Accordingly, the model can explore the long-range dependency of features from the top layers. However, a potential limitation of the network is that the discriminative features from the bottom layers (which can model the short-range dependency) are smoothed out in the final representation. This limitation is especially evident in the acoustic event classification (AEC) task, where both short- and long-duration events are involved in an audio clip and needed to be classified. In this paper, we propose a cross-scale attention (CSA) model, which explicitly integrates features from different scales to form the final representation. Moreover, we propose the adoption of the attention mechanism to specify the weights of local and global features based on the spatial and temporal characteristics of acoustic events. Using mathematic formulations, we further reveal that the proposed CSA model can be regarded as a weighted residual CNN (ResCNN) model when the ResCNN is used as a backbone model. We tested the proposed model on two AEC datasets: one is an urban AEC task, and the other is an AEC task in smart car environments. Experimental results show that the proposed CSA model can effectively improve the performance of current state-of-the-art deep learning algorithms.

cs.SD↗

arXiv2020

Stereotype-Free Classification of Fictitious Faces

Equal Opportunity and Fairness are receiving increasing attention in artificial intelligence. Stereotyping is another source of discrimination, which yet has been unstudied in literature. GAN-made faces would be exposed to such discrimination, if they are classified by human perception. It is possible to eliminate the human impact on fictitious faces classification task by the use of statistical approaches. We present a novel approach through penalized regression to label stereotype-free GAN-generated synthetic unlabeled images. The proposed approach aids labeling new data (fictitious output images) by minimizing a penalized version of the least squares cost function between realistic pictures and target pictures.

cs.CV↗

arXiv2020

Learning Robust Data Representation: A Knowledge Flow Perspective

It is always demanding to learn robust visual representation for various learning problems; however, this learning and maintenance process usually suffers from noise, incompleteness or knowledge domain mismatch. Thus, robust representation learning by removing noisy features or samples, complementing incomplete data, and mitigating the distribution difference becomes the key. Along this line of research, low-rank modeling has been widely-applied to solving representation learning challenges. This survey covers the topic from a knowledge flow perspective in terms of: (1) robust knowledge recovery, (2) robust knowledge transfer, and (3) robust knowledge fusion, centered around several major applications. First of all, we deliver a unified formulation for robust knowledge discovery given single dataset. Second, we discuss robust knowledge transfer and fusion given multiple datasets with different knowledge flows, followed by practical challenges, model variations, and remarks. Finally, we highlight future research of robust knowledge discovery for incomplete, unbalance, large-scale data analysis. This would benefit AI community from literature review to future direction.

cs.LG↗

arXiv2020

Voice-Indistinguishability: Protecting Voiceprint in Privacy-Preserving Speech Data Release

With the development of smart devices, such as the Amazon Echo and Apple's HomePod, speech data have become a new dimension of big data. However, privacy and security concerns may hinder the collection and sharing of real-world speech data, which contain the speaker's identifiable information, i.e., voiceprint, which is considered a type of biometric identifier. Current studies on voiceprint privacy protection do not provide either a meaningful privacy-utility trade-off or a formal and rigorous definition of privacy. In this study, we design a novel and rigorous privacy metric for voiceprint privacy, which is referred to as voice-indistinguishability, by extending differential privacy. We also propose mechanisms and frameworks for privacy-preserving speech data release satisfying voice-indistinguishability. Experiments on public datasets verify the effectiveness and efficiency of the proposed methods.

cs.CR↗

arXiv2020

SegVoxelNet: Exploring Semantic Context and Depth-aware Features for 3D Vehicle Detection from Point Cloud

3D vehicle detection based on point cloud is a challenging task in real-world applications such as autonomous driving. Despite significant progress has been made, we observe two aspects to be further improved. First, the semantic context information in LiDAR is seldom explored in previous works, which may help identify ambiguous vehicles. Second, the distribution of point cloud on vehicles varies continuously with increasing depths, which may not be well modeled by a single model. In this work, we propose a unified model SegVoxelNet to address the above two problems. A semantic context encoder is proposed to leverage the free-of-charge semantic segmentation masks in the bird's eye view. Suspicious regions could be highlighted while noisy regions are suppressed by this module. To better deal with vehicles at different depths, a novel depth-aware head is designed to explicitly model the distribution differences and each part of the depth-aware head is made to focus on its own target detection range. Extensive experiments on the KITTI dataset show that the proposed method outperforms the state-of-the-art alternatives in both accuracy and efficiency with point cloud as input only.

cs.CV↗

arXiv2020

A Survey on Causal Inference

Causal inference is a critical research topic across many domains, such as statistics, computer science, education, public policy and economics, for decades. Nowadays, estimating causal effect from observational data has become an appealing research direction owing to the large amount of available data and low budget requirement, compared with randomized controlled trials. Embraced with the rapidly developed machine learning area, various causal effect estimation methods for observational data have sprung up. In this survey, we provide a comprehensive review of causal inference methods under the potential outcome framework, one of the well known causal inference framework. The methods are divided into two categories depending on whether they require all three assumptions of the potential outcome framework or not. For each category, both the traditional statistical methods and the recent machine learning enhanced methods are discussed and compared. The plausible applications of these methods are also presented, including the applications in advertising, recommendation, medicine and so on. Moreover, the commonly used benchmark datasets as well as the open-source codes are also summarized, which facilitate researchers and practitioners to explore, evaluate and apply the causal inference methods.

stat.ME↗

arXiv2019

Learning Hybrid Representation by Robust Dictionary Learning in Factorized Compressed Space

In this paper, we investigate the robust dictionary learning (DL) to discover the hybrid salient low-rank and sparse representation in a factorized compressed space. A Joint Robust Factorization and Projective Dictionary Learning (J-RFDL) model is presented. The setting of J-RFDL aims at improving the data representations by enhancing the robustness to outliers and noise in data, encoding the reconstruction error more accurately and obtaining hybrid salient coefficients with accurate reconstruction ability. Specifically, J-RFDL performs the robust representation by DL in a factorized compressed space to eliminate the negative effects of noise and outliers on the results, which can also make the DL process efficient. To make the encoding process robust to noise in data, J-RFDL clearly uses sparse L2, 1-norm that can potentially minimize the factorization and reconstruction errors jointly by forcing rows of the reconstruction errors to be zeros. To deliver salient coefficients with good structures to reconstruct given data well, J-RFDL imposes the joint low-rank and sparse constraints on the embedded coefficients with a synthesis dictionary. Based on the hybrid salient coefficients, we also extend J-RFDL for the joint classification and propose a discriminative J-RFDL model, which can improve the discriminating abilities of learnt coeffi-cients by minimizing the classification error jointly. Extensive experiments on public datasets demonstrate that our formulations can deliver superior performance over other state-of-the-art methods.

cs.LG↗

arXiv2019

Optimizing Collision Avoidance in Dense Airspace using Deep Reinforcement Learning

New methodologies will be needed to ensure the airspace remains safe and efficient as traffic densities rise to accommodate new unmanned operations. This paper explores how unmanned free-flight traffic may operate in dense airspace. We develop and analyze autonomous collision avoidance systems for aircraft operating in dense airspace where traditional collision avoidance systems fail. We propose a metric for quantifying the decision burden on a collision avoidance system as well as a metric for measuring the impact of the collision avoidance system on airspace. We use deep reinforcement learning to compute corrections for an existing collision avoidance approach to account for dense airspace. The results show that a corrected collision avoidance system can operate more efficiently than traditional methods in dense airspace while maintaining high levels of safety.

cs.LG↗

arXiv2019

Flexible Auto-weighted Local-coordinate Concept Factorization: A Robust Framework for Unsupervised Clustering

Concept Factorization (CF) and its variants may produce inaccurate representation and clustering results due to the sensitivity to noise, hard constraint on the reconstruction error and pre-obtained approximate similarities. To improve the representation ability, a novel unsupervised Robust Flexible Auto-weighted Local-coordinate Concept Factorization (RFA-LCF) framework is proposed for clustering high-dimensional data. Specifically, RFA-LCF integrates the robust flexible CF by clean data space recovery, robust sparse local-coordinate coding and adaptive weighting into a unified model. RFA-LCF improves the representations by enhancing the robustness of CF to noise and errors, providing a flexible constraint on the reconstruction error and optimizing the locality jointly. For robust learning, RFA-LCF clearly learns a sparse projection to recover the underlying clean data space, and then the flexible CF is performed in the projected feature space. RFA-LCF also uses a L2,1-norm based flexible residue to encode the mismatch between the recovered data and its reconstruction, and uses the robust sparse local-coordinate coding to represent data using a few nearby basis concepts. For auto-weighting, RFA-LCF jointly preserves the manifold structures in the basis concept space and new coordinate space in an adaptive manner by minimizing the reconstruction errors on clean data, anchor points and coordinates. By updating the local-coordinate preserving data, basis concepts and new coordinates alternately, the representation abilities can be potentially improved. Extensive results on public databases show that RFA-LCF delivers the state-of-the-art clustering results compared with other related methods.

cs.CV↗

arXiv2019

Adaptive Structure-constrained Robust Latent Low-Rank Coding for Image Recovery

In this paper, we propose a robust representation learning model called Adaptive Structure-constrained Low-Rank Coding (AS-LRC) for the latent representation of data. To recover the underlying subspaces more accurately, AS-LRC seamlessly integrates an adaptive weighting based block-diagonal structure-constrained low-rank representation and the group sparse salient feature extraction into a unified framework. Specifically, AS-LRC performs the latent decomposition of given data into a low-rank reconstruction by a block-diagonal codes matrix, a group sparse locality-adaptive salient feature part and a sparse error part. To enforce the block-diagonal structures adaptive to different real datasets for the low-rank recovery, AS-LRC clearly computes an auto-weighting matrix based on the locality-adaptive features and multiplies by the low-rank coefficients for direct minimization at the same time. This encourages the codes to be block-diagonal and can avoid the tricky issue of choosing optimal neighborhood size or kernel width for the weight assignment, suffered in most local geometrical structures-preserving low-rank coding methods. In addition, our AS-LRC selects the L2,1-norm on the projection for extracting group sparse features rather than learning low-rank features by Nuclear-norm regularization, which can make learnt features robust to noise and outliers in samples, and can also make the feature coding process efficient. Extensive visualizations and numerical results demonstrate the effectiveness of our AS-LRC for image representation and recovery.

cs.CV↗

arXiv2019

Robust Subspace Discovery by Block-diagonal Adaptive Locality-constrained Representation

We propose a novel and unsupervised representation learning model, i.e., Robust Block-Diagonal Adaptive Locality-constrained Latent Representation (rBDLR). rBDLR is able to recover multi-subspace structures and extract the adaptive locality-preserving salient features jointly. Leveraging on the Frobenius-norm based latent low-rank representation model, rBDLR jointly learns the coding coefficients and salient features, and improves the results by enhancing the robustness to outliers and errors in given data, preserving local information of salient features adaptively and ensuring the block-diagonal structures of the coefficients. To improve the robustness, we perform the latent representation and adaptive weighting in a recovered clean data space. To force the coefficients to be block-diagonal, we perform auto-weighting by minimizing the reconstruction error based on salient features, constrained using a block-diagonal regularizer. This ensures that a strict block-diagonal weight matrix can be obtained and salient features will possess the adaptive locality preserving ability. By minimizing the difference between the coefficient and weights matrices, we can obtain a block-diagonal coefficients matrix and it can also propagate and exchange useful information between salient features and coefficients. Extensive results demonstrate the superiority of rBDLR over other state-of-the-art methods.

cs.CV↗

arXiv2019

Thermal expansion coefficients of high thermal conducting BAs and BP materials

Recent reported very high thermal conductivities in the cubic boron arsenide (BAs) and boron phosphide (BP) crystals could potentially provide a revolutionary solution in the thermal management of high power density devices. To fully facilitate such application, compatible coefficient of thermal expansion (CTE) between the heat spreader and device substrate, in order to minimize the thermal stress, need to be considered. Here we report our experimental CTE studies of BAs and BP in the temperature range from 100K to 1150K, through a combination of X-ray single crystal diffraction and neutron powder diffraction. We demonstrated the room temperature CTE, 3.6 $\pm$ 0.15 $\times$ 10E-6 /K for BAs and 3.2 $\pm$ 0.2 $\times$ 10E-6 /K for BP, are more compatible with most of the semiconductors including Si and GaAs, in comparison with diamond, and thus could be better candidates for the future heat spreader materials in power electronic devices.

cond-mat.mtrl-sci↗