arXiv subjects

Yang Wang

Publications and source records attributed to Yang Wang.

At least 631 records · Page 35Linked to original sources

arXiv2021

Deep Generative Learning via Schrödinger Bridge

We propose to learn a generative model via entropy interpolation with a Schrödinger Bridge. The generative learning task can be formulated as interpolating between a reference distribution and a target distribution based on the Kullback-Leibler divergence. At the population level, this entropy interpolation is characterized via an SDE on $[0,1]$ with a time-varying drift term. At the sample level, we derive our Schrödinger Bridge algorithm by plugging the drift term estimated by a deep score estimator and a deep density ratio estimator into the Euler-Maruyama method. Under some mild smoothness assumptions of the target distribution, we prove the consistency of both the score estimator and the density ratio estimator, and then establish the consistency of the proposed Schrödinger Bridge approach. Our theoretical results guarantee that the distribution learned by our approach converges to the target distribution. Experimental results on multimodal synthetic data and benchmark data support our theoretical findings and indicate that the generative model via Schrödinger Bridge is comparable with state-of-the-art GANs, suggesting a new formulation of generative learning. We demonstrate its usefulness in image interpolation and image inpainting.

cs.LG↗

arXiv2021

Trajectory Design for UAV-Based Internet-of-Things Data Collection: A Deep Reinforcement Learning Approach

In this paper, we investigate an unmanned aerial vehicle (UAV)-assisted Internet-of-Things (IoT) system in a sophisticated three-dimensional (3D) environment, where the UAV's trajectory is optimized to efficiently collect data from multiple IoT ground nodes. Unlike existing approaches focusing only on a simplified two-dimensional scenario and the availability of perfect channel state information (CSI), this paper considers a practical 3D urban environment with imperfect CSI, where the UAV's trajectory is designed to minimize data collection completion time subject to practical throughput and flight movement constraints. Specifically, inspired from the state-of-the-art deep reinforcement learning approaches, we leverage the twin-delayed deep deterministic policy gradient (TD3) to design the UAV's trajectory and present a TD3-based trajectory design for completion time minimization (TD3-TDCTM) algorithm. In particular, we set an additional information, i.e., the merged pheromone, to represent the state information of UAV and environment as a reference of reward which facilitates the algorithm design. By taking the service statuses of IoT nodes, the UAV's position, and the merged pheromone as input, the proposed algorithm can continuously and adaptively learn how to adjust the UAV's movement strategy. By interacting with the external environment in the corresponding Markov decision process, the proposed algorithm can achieve a near-optimal navigation strategy. Our simulation results show the superiority of the proposed TD3-TDCTM algorithm over three conventional non-learning based baseline methods.

cs.IT↗

arXiv2021

Bias-Tolerant Fair Classification

The label bias and selection bias are acknowledged as two reasons in data that will hinder the fairness of machine-learning outcomes. The label bias occurs when the labeling decision is disturbed by sensitive features, while the selection bias occurs when subjective bias exists during the data sampling. Even worse, models trained on such data can inherit or even intensify the discrimination. Most algorithmic fairness approaches perform an empirical risk minimization with predefined fairness constraints, which tends to trade-off accuracy for fairness. However, such methods would achieve the desired fairness level with the sacrifice of the benefits (receive positive outcomes) for individuals affected by the bias. Therefore, we propose a Bias-TolerantFAirRegularizedLoss (B-FARL), which tries to regain the benefits using data affected by label bias and selection bias. B-FARL takes the biased data as input, calls a model that approximates the one trained with fair but latent data, and thus prevents discrimination without constraints required. In addition, we show the effective components by decomposing B-FARL, and we utilize the meta-learning framework for the B-FARL optimization. The experimental results on real-world datasets show that our method is empirically effective in improving fairness towards the direction of true but latent labels.

cs.LG↗

arXiv2021

Long-Time Magnetic Relaxation in Antiferromagnetic Topological Material EuCd$_2$As$_2$

Magnetic topological materials have attracted much attention due to the correlation between topology and magnetism. Recent studies suggest that EuCd$_2$As$_2$ is an antiferromagnetic topological material. Here by carrying out thorough magnetic, electrical and thermodynamic property measurements, we discover a long time relaxation of the magnetic susceptibility in EuCd$_2$As$_2$. The (001) in-plane magnetic susceptibility at 5 K is found to continuously increase up to $\sim$10% over the time of $\sim$14 hours. The magnetic relaxation is anisotropic and strongly depends on the temperature and the applied magnetic field. These results will stimulate further theoretical and experimental studies to understand the origin of the relaxation process and its effect on the electronic structure and physical properties of the magnetic topological materials.

cond-mat.mtrl-sci↗

arXiv2021

Data Augmentation for Graph Convolutional Network on Semi-Supervised Classification

Data augmentation aims to generate new and synthetic features from the original data, which can identify a better representation of data and improve the performance and generalizability of downstream tasks. However, data augmentation for graph-based models remains a challenging problem, as graph data is more complex than traditional data, which consists of two features with different properties: graph topology and node attributes. In this paper, we study the problem of graph data augmentation for Graph Convolutional Network (GCN) in the context of improving the node embeddings for semi-supervised node classification. Specifically, we conduct cosine similarity based cross operation on the original features to create new graph features, including new node attributes and new graph topologies, and we combine them as new pairwise inputs for specific GCNs. Then, we propose an attentional integrating model to weighted sum the hidden node embeddings encoded by these GCNs into the final node embeddings. We also conduct a disparity constraint on these hidden node embeddings when training to ensure that non-redundant information is captured from different features. Experimental results on five real-world datasets show that our method improves the classification accuracy with a clear margin (+2.5% - +84.2%) than the original GCN model.

cs.LG↗

arXiv2021

Multi-spectral programmable absorbers

We designed and demonstrated a multi-spectral programmable perfect absorber that exploits two different phase-change materials. This programmability is possible by resonantly coupling two phase change materials, a Ge2Sb2Te5 layer to vanadium dioxide nanoparticles (VO2 NPs). The perfect absorption is attributed to the coalescence of gap plasmon modes excited between the NPs and waveguide cavity-like modes excited between the film and the NPs. The absorptance peak (>90%) can be tuned to four different infrared (IR) wavelengths from 1906 to 2960 nm by heating the structure to different temperatures. The perfect absorber is reconfigurable, lithography-free, large-scale, polarization-insensitive omnidirectional. Our strategy opens a new path for programmable infrared photonics.

physics.optics↗

arXiv2021

Generalized Linear Bandits with Local Differential Privacy

Contextual bandit algorithms are useful in personalized online decision-making. However, many applications such as personalized medicine and online advertising require the utilization of individual-specific information for effective learning, while user's data should remain private from the server due to privacy concerns. This motivates the introduction of local differential privacy (LDP), a stringent notion in privacy, to contextual bandits. In this paper, we design LDP algorithms for stochastic generalized linear bandits to achieve the same regret bound as in non-privacy settings. Our main idea is to develop a stochastic gradient-based estimator and update mechanism to ensure LDP. We then exploit the flexibility of stochastic gradient descent (SGD), whose theoretical guarantee for bandit problems is rarely explored, in dealing with generalized linear bandits. We also develop an estimator and update mechanism based on Ordinary Least Square (OLS) for linear bandits. Finally, we conduct experiments with both simulation and real-world datasets to demonstrate the consistently superb performance of our algorithms under LDP constraints with reasonably small parameters $(\varepsilon, δ)$ to ensure strong privacy protection.

stat.ML↗

arXiv2021

Learning Elastic Embeddings for Customizing On-Device Recommenders

In today's context, deploying data-driven services like recommendation on edge devices instead of cloud servers becomes increasingly attractive due to privacy and network latency concerns. A common practice in building compact on-device recommender systems is to compress their embeddings which are normally the cause of excessive parameterization. However, despite the vast variety of devices and their associated memory constraints, existing memory-efficient recommender systems are only specialized for a fixed memory budget in every design and training life cycle, where a new model has to be retrained to obtain the optimal performance while adapting to a smaller/larger memory budget. In this paper, we present a novel lightweight recommendation paradigm that allows a well-trained recommender to be customized for arbitrary device-specific memory constraints without retraining. The core idea is to compose elastic embeddings for each item, where an elastic embedding is the concatenation of a set of embedding blocks that are carefully chosen by an automated search function. Correspondingly, we propose an innovative approach, namely recommendation with universally learned elastic embeddings (RULE). To ensure the expressiveness of all candidate embedding blocks, RULE enforces a diversity-driven regularization when learning different embedding blocks. Then, a performance estimator-based evolutionary search function is designed, allowing for efficient specialization of elastic embeddings under any memory constraint for on-device recommendation. Extensive experiments on real-world datasets reveal the superior performance of RULE under tight memory budgets.

cs.IR↗

arXiv2021

A Sequence-to-Sequence Approach to Dialogue State Tracking

This paper is concerned with dialogue state tracking (DST) in a task-oriented dialogue system. Building a DST module that is highly effective is still a challenging issue, although significant progresses have been made recently. This paper proposes a new approach to dialogue state tracking, referred to as Seq2Seq-DU, which formalizes DST as a sequence-to-sequence problem. Seq2Seq-DU employs two BERT-based encoders to respectively encode the utterances in the dialogue and the descriptions of schemas, an attender to calculate attentions between the utterance embeddings and the schema embeddings, and a decoder to generate pointers to represent the current state of dialogue. Seq2Seq-DU has the following advantages. It can jointly model intents, slots, and slot values; it can leverage the rich representations of utterances and schemas based on BERT; it can effectively deal with categorical and non-categorical slots, and unseen schemas. In addition, Seq2Seq-DU can also be used in the NLU (natural language understanding) module of a dialogue system. Experimental results on benchmark datasets in different settings (SGD, MultiWOZ2.2, MultiWOZ2.1, WOZ2.0, DSTC2, M2M, SNIPS, and ATIS) show that Seq2Seq-DU outperforms the existing methods.

cs.CL↗

arXiv2021

Dual-side Sparse Tensor Core

Leveraging sparsity in deep neural network (DNN) models is promising for accelerating model inference. Yet existing GPUs can only leverage the sparsity from weights but not activations, which are dynamic, unpredictable, and hence challenging to exploit. In this work, we propose a novel architecture to efficiently harness the dual-side sparsity (i.e., weight and activation sparsity). We take a systematic approach to understand the (dis)advantages of previous sparsity-related architectures and propose a novel, unexplored paradigm that combines outer-product computation primitive and bitmap-based encoding format. We demonstrate the feasibility of our design with minimal changes to the existing production-scale inner-product-based Tensor Core. We propose a set of novel ISA extensions and co-design the matrix-matrix multiplication and convolution algorithms, which are the two dominant computation patterns in today's DNN models, to exploit our new dual-side sparse Tensor Core. Our evaluation shows that our design can fully unleash the dual-side DNN sparsity and improve the performance by up to one order of magnitude with \hl{small} hardware overhead.

cs.AR↗

arXiv2021

Cosmic Velocity Field Reconstruction Using AI

We develop a deep learning technique to infer the non-linear velocity field from the dark matter density field. The deep learning architecture we use is an "U-net" style convolutional neural network, which consists of 15 convolution layers and 2 deconvolution layers. This setup maps the 3-dimensional density field of $32^3$-voxels to the 3-dimensional velocity or momentum fields of $20^3$-voxels. Through the analysis of the dark matter simulation with a resolution of $2 {h^{-1}}{\rm Mpc}$, we find that the network can predict the the non-linearity, complexity and vorticity of the velocity and momentum fields, as well as the power spectra of their value, divergence and vorticity and its prediction accuracy reaches the range of $k\simeq1.4$ $h{\rm Mpc}^{-1}$ with a relative error ranging from 1% to $\lesssim$10%. A simple comparison shows that neural networks may have an overwhelming advantage over perturbation theory in the reconstruction of velocity or momentum fields.

astro-ph.CO↗

arXiv2021

A strange metal in a bosonic system

Fermi liquid theory forms the basis for our understanding of the majority of metals, which is manifested in the description of transport properties that the electrical resistivity goes as temperature squared in the limit of zero temperature. However, the observations of strange metal states in various quantum materials, notably high-temperature superconductors, bring this spectacularly successful theoretical framework into crisis. When electron scattering rate 1/τ hits its limit, kBT/{\hbar} where {\hbar} is the reduced Planck's constant, T represents absolute temperature and kB denotes Boltzmann's constant, Planckian dissipation occurs and lends strange metals a surprising link to black holes, gravity, and quantum information theory. Here, we show the characteristic signature of strange metallicity arising unprecedentedly in a bosonic system. Our nanopatterned YBa2Cu3O7-δ(YBCO) film arrays reveal T-linear resistance as well as B-linear magnetoresistance over an extended temperature and magnetic field range in a quantum critical region in the phase diagram. Moreover, the slope of the T-linear resistance α_cp appears bounded by α_cp {\approx} h/2e^2 [1/T]_c^onset where T_c^onset is the temperature at which Cooper pairs form, intimating a common scale-invariant transport mechanism corresponding to Planckian dissipation.In contrast to fermionic systems where the temperature and magnetic field dependent scattering rates combine in quadrature of {\hbar}/τ {\approx} {\sqrt} (((k_B T)^2+(μ_B B)^2)), both terms linearly combine in the present bosonic system, i.e. {\hbar}/τ {\approx} (k_B T+[γμ]_B B), where γ is a constant. By extending the reach of strange metal phenomenology to a bosonic system, our results suggest that there is a fundamental principle governing their transport which transcends particle statistics.

cond-mat.supr-con↗

arXiv2021

Quaternion Factorization Machines: A Lightweight Solution to Intricate Feature Interaction Modelling

As a well-established approach, factorization machine (FM) is capable of automatically learning high-order interactions among features to make predictions without the need for manual feature engineering. With the prominent development of deep neural networks (DNNs), there is a recent and ongoing trend of enhancing the expressiveness of FM-based models with DNNs. However, though better results are obtained with DNN-based FM variants, such performance gain is paid off by an enormous amount (usually millions) of excessive model parameters on top of the plain FM. Consequently, the heavy parameterization impedes the real-life practicality of those deep models, especially efficient deployment on resource-constrained IoT and edge devices. In this paper, we move beyond the traditional real space where most deep FM-based models are defined, and seek solutions from quaternion representations within the hypercomplex space. Specifically, we propose the quaternion factorization machine (QFM) and quaternion neural factorization machine (QNFM), which are two novel lightweight and memory-efficient quaternion-valued models for sparse predictive analytics. By introducing a brand new take on FM-based models with the notion of quaternion algebra, our models not only enable expressive inter-component feature interactions, but also significantly reduce the parameter size due to lower degrees of freedom in the hypercomplex Hamilton product compared with real-valued matrix multiplication. Extensive experimental results on three large-scale datasets demonstrate that QFM achieves 4.36% performance improvement over the plain FM without introducing any extra parameters, while QNFM outperforms all baselines with up to two magnitudes' parameter size reduction in comparison to state-of-the-art peer methods.

cs.IR↗

arXiv2021

DerainCycleGAN: Rain Attentive CycleGAN for Single Image Deraining and Rainmaking

Single image deraining (SID) is an important and challenging topic in emerging vision applications, and most of emerged deraining methods are supervised relying on the ground truth (i.e., paired images) in recent years. However, in practice it is rather common to have no un-paired images in real deraining task, in such cases how to remove the rain streaks in an unsupervised way will be a very challenging task due to lack of constraints between images and hence suffering from low-quality recovery results. In this paper, we explore the unsupervised SID task using unpaired data and propose a novel net called Attention-guided Deraining by Constrained CycleGAN (or shortly, DerainCycleGAN), which can fully utilize the constrained transfer learning abilitiy and circulatory structure of CycleGAN. Specifically, we design an unsu-pervised attention guided rain streak extractor (U-ARSE) that utilizes a memory to extract the rain streak masks with two constrained cycle-consistency branches jointly by paying attention to both the rainy and rain-free image domains. As a by-product, we also contribute a new paired rain image dataset called Rain200A, which is constructed by our network automatically. Compared with existing synthesis datasets, the rainy streaks in Rain200A contains more obvious and diverse shapes and directions. As a result, existing supervised methods trained on Rain200A can perform much better for processing real rainy images. Extensive experiments on synthesis and real datasets show that our net is superior to existing unsupervised deraining networks, and is also very competitive to other related supervised networks.

cs.CV↗

arXiv2021

Semi-DerainGAN: A New Semi-supervised Single Image Deraining Network

Removing the rain streaks from single image is still a challenging task, since the shapes and directions of rain streaks in the synthetic datasets are very different from real images. Although supervised deep deraining networks have obtained impressive results on synthetic datasets, they still cannot obtain satisfactory results on real images due to weak generalization of rain removal capacity, i.e., the pre-trained models usually cannot handle new shapes and directions that may lead to over-derained/under-derained results. In this paper, we propose a new semi-supervised GAN-based deraining network termed Semi-DerainGAN, which can use both synthetic and real rainy images in a uniform network using two supervised and unsupervised processes. Specifically, a semi-supervised rain streak learner termed SSRML sharing the same parameters of both processes is derived, which makes the real images contribute more rain streak information. To deliver better deraining results, we design a paired discriminator for distinguishing the real pairs from fake pairs. Note that we also contribute a new real-world rainy image dataset Real200 to alleviate the difference between the synthetic and real image do-mains. Extensive results on public datasets show that our model can obtain competitive performance, especially on real images.

cs.CV↗

arXiv2021

DynACPD Embedding Algorithm for Prediction Tasks in Dynamic Networks

Classical network embeddings create a low dimensional representation of the learned relationships between features across nodes. Such embeddings are important for tasks such as link prediction and node classification. In the current paper, we consider low dimensional embeddings of dynamic networks, that is a family of time varying networks where there exist both temporal and spatial link relationships between nodes. We present novel embedding methods for a dynamic network based on higher order tensor decompositions for tensorial representations of the dynamic network. In one sense, our embeddings are analogous to spectral embedding methods for static networks. We provide a rationale for our algorithms via a mathematical analysis of some potential reasons for their effectiveness. Finally, we demonstrate the power and efficiency of our approach by comparing our algorithms' performance on the link prediction task against an array of current baseline methods across three distinct real-world dynamic networks.

cs.AI↗

arXiv2021

Spectroscopic Evidence on Realization of a Genuine Topological Nodal Line Semimetal in LaSbTe

The nodal line semimetals have attracted much attention due to their unique topological electronic structure and exotic physical properties. A genuine nodal line semimetal is qualified by the presence of Dirac nodes along a line in the momentum space that are protected against the spin-orbit coupling. In addition, it requires that the Dirac points lie close to the Fermi level allowing to dictate the macroscopic physical properties. Although the material realization of nodal line semimetals have been theoretically predicted in numerous compounds, only a few of them have been experimentally verified and the realization of a genuine nodal line semimetal is particularly rare. Here we report the realization of a genuine nodal line semimetal in LaSbTe. We investigated the electronic structure of LaSbTe by band structure calculations and angle-resolved photoemission (ARPES) measurements. Taking spin-orbit coupling into account, our band structure calculations predict that a nodal line is formed in the boundary surface of the Brillouin zone which is robust and lies close to the Fermi level. The Dirac nodes along the X-R line in momentum space are directly observed in our ARPES measurements and the energies of these Dirac nodes are all close to the Fermi level. These results constitute clear evidence that LaSbTe is a genuine nodal line semimetal,providing a new platform to explore for novel phenomena and possible applications associated with the nodal line semimetals.

cond-mat.mtrl-sci↗

arXiv2021

AdaCrowd: Unlabeled Scene Adaptation for Crowd Counting

We address the problem of image-based crowd counting. In particular, we propose a new problem called unlabeled scene-adaptive crowd counting. Given a new target scene, we would like to have a crowd counting model specifically adapted to this particular scene based on the target data that capture some information about the new scene. In this paper, we propose to use one or more unlabeled images from the target scene to perform the adaptation. In comparison with the existing problem setups (e.g. fully supervised), our proposed problem setup is closer to the real-world applications of crowd counting systems. We introduce a novel AdaCrowd framework to solve this problem. Our framework consists of a crowd counting network and a guiding network. The guiding network predicts some parameters in the crowd counting network based on the unlabeled images from a particular scene. This allows our model to adapt to different target scenes. The experimental results on several challenging benchmark datasets demonstrate the effectiveness of our proposed approach compared with other alternative methods. Code is available at https://github.com/maheshkkumar/adacrowd.

cs.CV↗