arXiv subjects

Yue Wang

Publications and source records attributed to Yue Wang.

At least 649 records · Page 36Linked to original sources

arXiv2022

FastClass: A Time-Efficient Approach to Weakly-Supervised Text Classification

Weakly-supervised text classification aims to train a classifier using only class descriptions and unlabeled data. Recent research shows that keyword-driven methods can achieve state-of-the-art performance on various tasks. However, these methods not only rely on carefully-crafted class descriptions to obtain class-specific keywords but also require substantial amount of unlabeled data and takes a long time to train. This paper proposes FastClass, an efficient weakly-supervised classification approach. It uses dense text representation to retrieve class-relevant documents from external unlabeled corpus and selects an optimal subset to train a classifier. Compared to keyword-driven methods, our approach is less reliant on initial class descriptions as it no longer needs to expand each class description into a set of class-specific keywords. Experiments on a wide range of classification tasks show that the proposed approach frequently outperforms keyword-driven models in terms of classification accuracy and often enjoys orders-of-magnitude faster training speed.

cs.CL↗

arXiv2022

SteerNeRF: Accelerating NeRF Rendering via Smooth Viewpoint Trajectory

Neural Radiance Fields (NeRF) have demonstrated superior novel view synthesis performance but are slow at rendering. To speed up the volume rendering process, many acceleration methods have been proposed at the cost of large memory consumption. To push the frontier of the efficiency-memory trade-off, we explore a new perspective to accelerate NeRF rendering, leveraging a key fact that the viewpoint change is usually smooth and continuous in interactive viewpoint control. This allows us to leverage the information of preceding viewpoints to reduce the number of rendered pixels as well as the number of sampled points along the ray of the remaining pixels. In our pipeline, a low-resolution feature map is rendered first by volume rendering, then a lightweight 2D neural renderer is applied to generate the output image at target resolution leveraging the features of preceding and current frames. We show that the proposed method can achieve competitive rendering quality while reducing the rendering time with little memory overhead, enabling 30FPS at 1080P image resolution with a low memory footprint.

cs.CV↗

arXiv2022

Recycling of Perovskite Substrate

The use of water-soluble sacrificial layer of Sr$_3$Al$_2$O$_6$ has tremendously boosted the research on freestanding functional oxide thin films, especially thanks to its ultimate capability to produce high-quality epitaxial perovskite thin films. However, the costly single-crystalline substrates, e.g. SrTiO$_3$, were generally discarded after obtaining the freestanding thin films. Here, we demonstrate that the SrTiO$_3$ substrates can be recycled to fabricate La$_{0.7}$Sr$_{0.3}$MnO$_3$ films with nearly identical structural and electrical properties. After attaining freestanding thin films, the residues on SrTiO$_3$ can be removed by 80 \degree C hot water soaking and rinsing treatments. Consequently, the surface of SrTiO$_3$ reverted to its original step-and-terrace structure.

physics.app-ph↗

arXiv2022

HAQJSK: Hierarchical-Aligned Quantum Jensen-Shannon Kernels for Graph Classification

In this work, we propose a family of novel quantum kernels, namely the Hierarchical Aligned Quantum Jensen-Shannon Kernels (HAQJSK), for un-attributed graphs. Different from most existing classical graph kernels, the proposed HAQJSK kernels can incorporate hierarchical aligned structure information between graphs and transform graphs of random sizes into fixed-sized aligned graph structures, i.e., the Hierarchical Transitive Aligned Adjacency Matrix of vertices and the Hierarchical Transitive Aligned Density Matrix of the Continuous-Time Quantum Walk (CTQW). For a pair of graphs to hand, the resulting HAQJSK kernels are defined by measuring the Quantum Jensen-Shannon Divergence (QJSD) between their transitive aligned graph structures. We show that the proposed HAQJSK kernels not only reflect richer intrinsic global graph characteristics in terms of the CTQW, but also address the drawback of neglecting structural correspondence information arising in most existing R-convolution kernels. Furthermore, unlike the previous Quantum Jensen-Shannon Kernels associated with the QJSD and the CTQW, the proposed HAQJSK kernels can simultaneously guarantee the properties of permutation invariant and positive definiteness, explaining the theoretical advantages of the HAQJSK kernels. Experiments indicate the effectiveness of the proposed kernels.

cs.LG↗

arXiv2022

RoSGAS: Adaptive Social Bot Detection with Reinforced Self-Supervised GNN Architecture Search

Social bots are referred to as the automated accounts on social networks that make attempts to behave like human. While Graph Neural Networks (GNNs) has been massively applied to the field of social bot detection, a huge amount of domain expertise and prior knowledge is heavily engaged in the state-of-the art approaches to design a dedicated neural network architecture for a specific classification task. Involving oversized nodes and network layers in the model design, however, usually causes the over-smoothing problem and the lack of embedding discrimination. In this paper, we propose RoSGAS, a novel Reinforced and Self-supervised GNN Architecture Search framework to adaptively pinpoint the most suitable multi-hop neighborhood and the number of layers in the GNN architecture. More specifically, we consider the social bot detection problem as a user-centric subgraph embedding and classification task. We exploit heterogeneous information network to present the user connectivity by leveraging account metadata, relationships, behavioral features and content features. RoSGAS uses a multi-agent deep reinforcement learning (RL) mechanism for navigating the search of optimal neighborhood and network layers to learn individually the subgraph embedding for each target user. A nearest neighbor mechanism is developed for accelerating the RL training process, and RoSGAS can learn more discriminative subgraph embedding with the aid of self-supervised learning. Experiments on 5 Twitter datasets show that RoSGAS outperforms the state-of-the-art approaches in terms of accuracy, training efficiency and stability, and has better generalization when handling unseen samples.

cs.SI↗

arXiv2022

ATASI-Net: An Efficient Sparse Reconstruction Network for Tomographic SAR Imaging with Adaptive Threshold

Tomographic SAR technique has attracted remarkable interest for its ability of three-dimensional resolving along the elevation direction via a stack of SAR images collected from different cross-track angles. The emerged compressed sensing (CS)-based algorithms have been introduced into TomoSAR considering its super-resolution ability with limited samples. However, the conventional CS-based methods suffer from several drawbacks, including weak noise resistance, high computational complexity, and complex parameter fine-tuning. Aiming at efficient TomoSAR imaging, this paper proposes a novel efficient sparse unfolding network based on the analytic learned iterative shrinkage thresholding algorithm (ALISTA) architecture with adaptive threshold, named Adaptive Threshold ALISTA-based Sparse Imaging Network (ATASI-Net). The weight matrix in each layer of ATASI-Net is pre-computed as the solution of an off-line optimization problem, leaving only two scalar parameters to be learned from data, which significantly simplifies the training stage. In addition, adaptive threshold is introduced for each azimuth-range pixel, enabling the threshold shrinkage to be not only layer-varied but also element-wise. Moreover, the final learned thresholds can be visualized and combined with the SAR image semantics for mutual feedback. Finally, extensive experiments on simulated and real data are carried out to demonstrate the effectiveness and efficiency of the proposed method.

eess.SP↗

arXiv2022

Compressive Spectrum Sensing Using Blind-Block Orthogonal Least Squares

Compressive sensing (CS) has recently emerged as an extremely efficient technology of the wideband spectrum sensing. In compressive spectrum sensing (CSS), it is necessary to know the sparsity or the noise information in advance for reliable reconstruction. However, such information is usually absent in practical applications. In this paper, we propose a blind-block orthogonal least squares-based compressive spectrum sensing (B-BOLS-CSS) algorithm, which utilizes a novel blind stopping rule to cut the cords to these prior information. Specifically, we first present both the noiseless and noisy recovery guarantees for the BOLS algorithm based on the mutual incoherence property (MIP). Motivated by them, we then formulate the blind stopping rule, which exploits an $\ell_{2,\infty}$ sufficient statistic to blindly test the support atoms in the remaining measurement matrix. We further evaluate the theoretical performance analysis of the holistic B-BOLS-CSS algorithm by developing a lower bound of the signal-to-noise ratio (SNR) to ensure that the probability of exact recovery is no lower than a given threshold. Simulations not only demonstrate the improvement of our derived theoretical results, but also illustrate that B-BOLS-CSS works well in both low and high SNR environments.

eess.SP↗

arXiv2022

Blind Orthogonal Least Squares based Compressive Spectrum Sensing

As an enabling technique of cognitive radio (CR), compressive spectrum sensing (CSS) based on compressive sensing (CS) can detect the spectrum opportunities from wide frequency bands efficiently and accurately by using sub-Nyquist sampling rate. However, the sensing performance of most existing CSS excessively relies on the prior information such as spectrum sparsity or noise variance. Thus, a key challenge in practical CSS is how to work effectively even in the absence of such information. In this paper, we propose a blind orthogonal least squares based CSS algorithm (B-OLS-CSS), which functions properly without the requirement of prior information. Specifically, we develop a novel blind stopping rule for the OLS algorithm based on its probabilistic recovery condition. This innovative rule gets rid of the need of the spectrum sparsity or noise information, but only requires the computational-feasible mutual incoherence property of the given measurement matrix. Our theoretical analysis indicates that the signal-to-noise ratio required by the proposed B-OLS-CSS for achieving a certain sensing accuracy is relaxed than that by the benchmark CSS using the OMP algorithm, which is verified by extensive simulation results.

eess.SP↗

arXiv2022

$4$-choosability of planar graphs with $4$-cycles far apart via the Combinatorial Nullstellensatz

By a well-known theorem of Thomassen and a planar graph depicted by Voigt, we know that every planar graph is $5$-choosable, and the bound is tight. In 1999, Lam, Xu and Liu reduced $5$ to $4$ on $C_4$-free planar graphs. In the paper, by applying the famous Combinatorial Nullstellensatz, we design an effective algorithm to deal with list coloring problems. At the same time, we prove that a planar graph $G$ is $4$-choosable if any two $4$-cycles having distance at least $5$ in $G$, which extends the result of Lam et al.

math.CO↗

arXiv2022

Mathematical Representation of Clausius' and Kelvin's Statements of the Second Law and Irreversibility

We provide a stochastic mathematical representation for Clausius' and Kelvin-Planck's statements of the Second Law of Thermodynamics in terms of the entropy productions of a finite, compact driven Markov system and its lift. A surjective map is rigorously established through the lift when the state space is either a discrete graph or a continuous n-dimensional torus T^n. The corresponding lifted processes have detailed balance thus a natural potential function but no stationary probability. We show that in the long-time limit the entropy production of the finite driven system precisely equals the potential energy decrease in the lifted system. This theorem provides a dynamic foundation for the two equivalent statements of Second Law of Thermodynamics, a la Kelvin's and Clausius'. It suggests a modernized, combined statement: "A mesoscopic engine that works in completing irreversible internal cycles statistically has necessarily an external effect that lowering a weight accompanied by passing heat from a warmer to a colder body."

math.PR↗

arXiv2022

Deep Multi-agent Reinforcement Learning for Highway On-Ramp Merging in Mixed Traffic

On-ramp merging is a challenging task for autonomous vehicles (AVs), especially in mixed traffic where AVs coexist with human-driven vehicles (HDVs). In this paper, we formulate the mixed-traffic highway on-ramp merging problem as a multi-agent reinforcement learning (MARL) problem, where the AVs (on both merge lane and through lane) collaboratively learn a policy to adapt to HDVs to maximize the traffic throughput. We develop an efficient and scalable MARL framework that can be used in dynamic traffic where the communication topology could be time-varying. Parameter sharing and local rewards are exploited to foster inter-agent cooperation while achieving great scalability. An action masking scheme is employed to improve learning efficiency by filtering out invalid/unsafe actions at each step. In addition, a novel priority-based safety supervisor is developed to significantly reduce collision rate and greatly expedite the training process. A gym-like simulation environment is developed and open-sourced with three different levels of traffic densities. We exploit curriculum learning to efficiently learn harder tasks from trained models under simpler settings. Comprehensive experimental results show the proposed MARL framework consistently outperforms several state-of-the-art benchmarks.

eess.SY↗

arXiv2022

CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning

Program synthesis or code generation aims to generate a program that satisfies a problem specification. Recent approaches using large-scale pretrained language models (LMs) have shown promising results, yet they have some critical limitations. In particular, they often follow a standard supervised fine-tuning procedure to train a code generation model only from the pairs of natural-language problem descriptions and ground-truth programs. Such paradigm largely ignores some important but potentially useful signals in the problem specification such as unit tests, which thus often results in poor performance when solving complex unseen coding tasks. To address the limitations, we propose "CodeRL", a new framework for program synthesis tasks through pretrained LMs and deep reinforcement learning (RL). Specifically, during training, we treat the code-generating LM as an actor network, and introduce a critic network that is trained to predict the functional correctness of generated programs and provide dense feedback signals to the actor. During inference, we introduce a new generation procedure with a critical sampling strategy that allows a model to automatically regenerate programs based on feedback from example unit tests and critic scores. For the model backbones, we extended the encoder-decoder architecture of CodeT5 with enhanced learning objectives, larger model sizes, and better pretraining data. Our method not only achieves new SOTA results on the challenging APPS benchmark, but also shows strong zero-shot transfer capability with new SOTA results on the simpler MBPP benchmark.

cs.LG↗

arXiv2022

Phenotypic Equilibrium as Probabilistic Convergence in Multi-phenotype Cell Population Dynamics

We consider the cell population dynamics with $n$ different phenotypes. Both the Markovian branching process model (stochastic model) and the ordinary differential equation (ODE) system model (deterministic model) are presented, and exploited to investigate the dynamics of the phenotypic proportions. We will prove that in both models, these proportions will tend to constants regardless of initial population states ("phenotypic equilibrium") under weak conditions, which explains the experimental phenomenon in Gupta et al.'s paper. We also prove that Gupta et al.'s explanation is the ODE model under a special assumption. As an application, we will give sufficient and necessary conditions under which the proportion of one phenotype tends to $0$ (die out) or $1$ (dominate). We also extend our results to non-Markovian cases.

q-bio.PE↗

arXiv2022

Inference on tissue transplantation experiments

We review studies on tissue transplantation experiments for various species: one piece of the donor tissue is excised and transplanted into a slit in the host tissue, then observe the behavior of this grafted tissue. Although we have known the results of some transplantation experiments, there are many more possible experiments with unknown results. We develop a penalty function-based method that uses the known experimental results to infer the unknown experimental results. Similar experiments without similar results get penalized and correspond to smaller probability. This method can provide the most probable results of a group of experiments or the probability of a specific result for each experiment. This method is also generalized to other situations. Besides, we solve a problem: how to design experiments so that such a method can be applied most efficiently.

q-bio.QM↗

arXiv2022

Downlink Massive MIMO Channel Estimation via Deep Unrolling : Sparsity Exploitations in Angular Domain

In frequency division duplex (FDD) massive MIMO systems, reliable downlink channel estimation is essential for the subsequent data transmission but is realized at the cost of massive pilot overhead due to hundreds of antennas at base station (BS). In order to reduce the pilot overhead without compromising the estimation, compressive sensing (CS) based methods have been widely applied for channel estimation by exploiting the inherent sparse structure of massive MIMO channel in angular domain. However, they still suffer from high complexity during optimization process and the requirement of prior knowledge on sparsity information. To overcome these challenges, this paper develops a novel hybrid channel estimation framework by integrating the model-driven CS and data-driven deep unrolling techniques. The proposed framework is composed of a coarse estimation part and a fine correction part, which is implemented in a two-stage manner to exploit both inter- and intra-frame sparsities of channels in angular domain. Then, two estimation schemes are designed depending on whether priori sparsity information is required, where the second scheme designs a new thresholding function to eliminate such requirement. Numerical results are provided to verify that our schemes can achieve high accuracy with low pilot overhead and low complexity.

eess.SP↗

arXiv2022

Van der Waals Materials for Applications in Nanophotonics

Numerous optical phenomena and applications have been enabled by nanophotonic structures. Their current fabrication from high refractive index dielectrics, such as silicon or gallium phosphide, pose restricting fabrication challenges, while metals, relying on plasmons and thus exhibiting high ohmic losses, limit the achievable applications. Here, we present an emerging class of layered so-called van der Waals (vdW) crystals as a viable nanophotonics platform. We extract the dielectric response of 11 mechanically exfoliated thin-film (20-200 nm) van der Waals crystals, revealing high refractive indices up to n = 5, pronounced birefringence up to $Δ$n = 3, sharp absorption resonances, and a range of transparency windows from ultraviolet to near-infrared. We then fabricate nanoantennas on SiO$_2$ and gold utilizing the compatibility of vdW thin films with a variety of substrates. We observe pronounced Mie resonances due to the high refractive index contrast on SiO$_2$ leading to a strong exciton-photon coupling regime as well as largely unexplored high-quality-factor, hybrid Mie-plasmon modes on gold. We demonstrate further vdW-material-specific degrees of freedom in fabrication by realizing nanoantennas from stacked twisted crystalline thin-films, enabling control of nonlinear optical properties, and post-fabrication nanostructure transfer, important for nano-optics with sensitive materials.

physics.optics↗

arXiv2022

Robust Distributed Learning Against Both Distributional Shifts and Byzantine Attacks

In distributed learning systems, robustness issues may arise from two sources. On one hand, due to distributional shifts between training data and test data, the trained model could exhibit poor out-of-sample performance. On the other hand, a portion of working nodes might be subject to byzantine attacks which could invalidate the learning result. Existing works mostly deal with these two issues separately. In this paper, we propose a new algorithm that equips distributed learning with robustness measures against both distributional shifts and byzantine attacks. Our algorithm is built on recent advances in distributionally robust optimization as well as norm-based screening (NBS), a robust aggregation scheme against byzantine attacks. We provide convergence proofs in three cases of the learning model being nonconvex, convex, and strongly convex for the proposed algorithm, shedding light on its convergence behaviors and endurability against byzantine attacks. In particular, we deduce that any algorithm employing NBS (including ours) cannot converge when the percentage of byzantine nodes is 1/3 or higher, instead of 1/2, which is the common belief in current literature. The experimental results demonstrate the effectiveness of our algorithm against both robustness issues. To the best of our knowledge, this is the first work to address distributional shifts and byzantine attacks simultaneously.

cs.LG↗

arXiv2022

Distributed Swarm Learning for Internet of Things at the Edge: Where Artificial Intelligence Meets Biological Intelligence

With the proliferation of versatile Internet of Things (IoT) services, smart IoT devices are increasingly deployed at the edge of wireless networks to perform collaborative machine learning tasks using locally collected data, giving rise to the edge learning paradigm. Due to device restrictions and resource constraints, edge learning among massive IoT devices faces major technical challenges caused by the communication bottleneck, data and device heterogeneity, non-convex optimization, privacy and security concerns, and dynamic environments. To overcome these challenges, this article studies a new framework of distributed swarm learning (DSL) through a holistic integration of artificial intelligence and biological swarm intelligence. Leveraging efficient and robust signal processing and communication techniques, DSL contributes to novel tools for learning and optimization tailored for real-time operations of large-scale IoT in edge wireless environments, which will benefit a wide range of edge IoT applications.

eess.SP↗