arXiv subjects

Kai Huang

Publications and source records attributed to Kai Huang.

At least 127 records · Page 7Linked to original sources

arXiv2023

Meta Reinforcement Learning for Fast Spectrum Sharing in Vehicular Networks

In this paper, we investigate the problem of fast spectrum sharing in vehicle-to-everything communication. In order to improve the spectrum efficiency of the whole system, the spectrum of vehicle-to-infrastructure links is reused by vehicle-to-vehicle links. To this end, we model it as a problem of deep reinforcement learning and tackle it with proximal policy optimization. A considerable number of interactions are often required for training an agent with good performance, so simulation-based training is commonly used in communication networks. Nevertheless, severe performance degradation may occur when the agent is directly deployed in the real world, even though it can perform well on the simulator, due to the reality gap between the simulation and the real environments. To address this issue, we make preliminary efforts by proposing an algorithm based on meta reinforcement learning. This algorithm enables the agent to rapidly adapt to a new task with the knowledge extracted from similar tasks, leading to fewer interactions and less training time. Numerical results show that our method achieves near-optimal performance and exhibits rapid convergence.

cs.IT↗

arXiv2023

Prototypical Kernel Learning and Open-set Foreground Perception for Generalized Few-shot Semantic Segmentation

Generalized Few-shot Semantic Segmentation (GFSS) extends Few-shot Semantic Segmentation (FSS) to simultaneously segment unseen classes and seen classes during evaluation. Previous works leverage additional branch or prototypical aggregation to eliminate the constrained setting of FSS. However, representation division and embedding prejudice, which heavily results in poor performance of GFSS, have not been synthetical considered. We address the aforementioned problems by jointing the prototypical kernel learning and open-set foreground perception. Specifically, a group of learnable kernels is proposed to perform segmentation with each kernel in charge of a stuff class. Then, we explore to merge the prototypical learning to the update of base-class kernels, which is consistent with the prototype knowledge aggregation of few-shot novel classes. In addition, a foreground contextual perception module cooperating with conditional bias based inference is adopted to perform class-agnostic as well as open-set foreground detection, thus to mitigate the embedding prejudice and prevent novel targets from being misclassified as background. Moreover, we also adjust our method to the Class Incremental Few-shot Semantic Segmentation (CIFSS) which takes the knowledge of novel classes in a incremental stream. Extensive experiments on PASCAL-5i and COCO-20i datasets demonstrate that our method performs better than previous state-of-the-art.

cs.CV↗

arXiv2023

Magnetic Antiskyrmions in Two-Dimensional van der Waals Magnets Engineered by Layer Stacking

Magnetic skyrmions and antiskyrmions are topologically protected quasiparticles exhibiting a whirling spin texture in real space. Antiskyrmions offer some advantages over skyrmions as they are expected to have higher stability and can be electrically driven with no transverse motion. However, unlike the widely investigated skyrmions, antiskyrmions are rarely observed due to the required anisotropic Dzyaloshinskii-Moriya interaction (DMI). Here we propose to exploit the recently demonstrated van der Waals (vdW) assembly of two-dimensional (2D) materials that breaks inversion symmetry and creates conditions for anisotropic DMI. Using a 2D vdW magnet CrI${}_3$ as an example, we demonstrate, based on density functional theory (DFT) calculations, that this strategy is a promising platform to realize antiskyrmions. Polar layer stacking of two centrosymmetric magnetic monolayers of CrI${}_3$ efficiently lowers the symmetry, resulting in anisotropic DMI that supports antiskyrmions. The DMI is reversible by switching the ferroelectric polarization inherited from the polar layer stacking, offering the control of antiskyrmions by an electric field. Furthermore, we find that the magnetocrystalline anisotropy and DMI of CrI${}_3$ can be efficiently modulated by Mn doping, creating a possibility to control the size of antiskyrmions. Using atomistic spin dynamics simulations with the parameters obtained from our DFT calculations, we predict the formation of antiskyrmions in a Cr${}_{0.88}$Mn${}_{0.12}$I${}_3$ bilayer and switching their spin texture with polarization reversal. Our results open a new direction to generate and control magnetic antiskyrmions in 2D vdW magnetic systems.

cond-mat.mtrl-sci↗

arXiv2023

Lithium tantalate electro-optical photonic integrated circuits for high volume manufacturing

Photonic integrated circuits based on Lithium Niobate have demonstrated the vast capabilities afforded by material with a high Pockels coefficient, allowing linear and high-speed modulators operating at CMOS voltage levels for applications ranging from data-center communications and photonic accelerators for AI. However despite major progress, the industrial adoption of this technology is compounded by the high cost per wafer. Here we overcome this challenge and demonstrate a photonic platform that satisfies the dichotomy of allowing scalable manufacturing at low cost, while at the same time exhibiting equal, and superior properties to those of Lithium Niobate. We demonstrate that it is possible to manufacture low loss photonic integrated circuits using Lithium Tantalate, a material that is already commercially adopted for acoustic filters in 5G and 6G. We show that LiTaO3 posses equally attractive optical properties and can be etched with high precision and negligible residues using DUV lithography, diamond like carbon (DLC) as a hard mask and alkaline wet etching. Using this approach we demonstrate microresonators with an intrinsic cavity linewidth of 26.8 MHz, corresponding to a linear loss of 5.6 dB/m and demonstrate a Mach Zehnder modulator with Vpi L = 4.2 V cm half-wave voltage length product. In comparison to Lithium Niobate, the photonic integrated circuits based on LiTaO3 exhibit a much lower birefringence, allowing high-density circuits and broadband operation over all telecommunication bands (O to L band), exhibit higher photorefractive damage threshold, and lower microwave loss tangent. Moreover, we show that the platform supports generation of soliton microcombs in X-Cut LiTaO3 racetrack microresonator with electronically detectable repetition rate, i.e. 30.1 GHz.

physics.optics↗

arXiv2023

Learning from Symmetry: Meta-Reinforcement Learning with Symmetrical Behaviors and Language Instructions

Meta-reinforcement learning (meta-RL) is a promising approach that enables the agent to learn new tasks quickly. However, most meta-RL algorithms show poor generalization in multi-task scenarios due to the insufficient task information provided only by rewards. Language-conditioned meta-RL improves the generalization capability by matching language instructions with the agent's behaviors. While both behaviors and language instructions have symmetry, which can speed up human learning of new knowledge. Thus, combining symmetry and language instructions into meta-RL can help improve the algorithm's generalization and learning efficiency. We propose a dual-MDP meta-reinforcement learning method that enables learning new tasks efficiently with symmetrical behaviors and language instructions. We evaluate our method in multiple challenging manipulation tasks, and experimental results show that our method can greatly improve the generalization and learning efficiency of meta-reinforcement learning. Videos are available at https://tumi6robot.wixsite.com/symmetry/.

cs.AI↗

arXiv2023

A Biologically-Inspired Simultaneous Localization and Mapping System Based on LiDAR Sensor

Simultaneous localization and mapping (SLAM) is one of the essential techniques and functionalities used by robots to perform autonomous navigation tasks. Inspired by the rodent hippocampus, this paper presents a biologically inspired SLAM system based on a LiDAR sensor using a hippocampal model to build a cognitive map and estimate the robot pose in indoor environments. Based on the biologically inspired models mimicking boundary cells, place cells, and head direction cells, the SLAM system using LiDAR point cloud data is capable of leveraging the self-motion cues from the LiDAR odometry and the boundary cues from the LiDAR boundary cells to build a cognitive map and estimate the robot pose. Experiment results show that with the LiDAR boundary cells the proposed SLAM system greatly outperforms the camera-based brain-inspired method in both simulation and indoor environments, and is competitive with the conventional LiDAR-based SLAM methods.

cs.RO↗

arXiv2023

Towards human-compatible autonomous car: A study of non-verbal Turing test in automated driving with affective transition modelling

Autonomous cars are indispensable when humans go further down the hands-free route. Although existing literature highlights that the acceptance of the autonomous car will increase if it drives in a human-like manner, sparse research offers the naturalistic experience from a passenger's seat perspective to examine the humanness of current autonomous cars. The present study tested whether the AI driver could create a human-like ride experience for passengers based on 69 participants' feedback in a real-road scenario. We designed a ride experience-based version of the non-verbal Turing test for automated driving. Participants rode in autonomous cars (driven by either human or AI drivers) as a passenger and judged whether the driver was human or AI. The AI driver failed to pass our test because passengers detected the AI driver above chance. In contrast, when the human driver drove the car, the passengers' judgement was around chance. We further investigated how human passengers ascribe humanness in our test. Based on Lewin's field theory, we advanced a computational model combining signal detection theory with pre-trained language models to predict passengers' humanness rating behaviour. We employed affective transition between pre-study baseline emotions and corresponding post-stage emotions as the signal strength of our model. Results showed that the passengers' ascription of humanness would increase with the greater affective transition. Our study suggested an important role of affective transition in passengers' ascription of humanness, which might become a future direction for autonomous driving.

cs.HC↗

arXiv2023

A Survey on Automated Program Repair Techniques

With the rapid development and large-scale popularity of program software, modern society increasingly relies on software systems. However, the problems exposed by software have also come to the fore. Software defect has become an important factor troubling developers. In this context, Automated Program Repair (APR) techniques have emerged, aiming to automatically fix software defect problems and reduce manual debugging work. In particular, benefiting from the advances in deep learning, numerous learning-based APR techniques have emerged in recent years, which also bring new opportunities for APR research. To give researchers a quick overview of APR techniques' complete development and future opportunities, we revisit the evolution of APR techniques and discuss in depth the latest advances in APR research. In this paper, the development of APR techniques is introduced in terms of four different patch generation schemes: search-based, constraint-based, template-based, and learning-based. Moreover, we propose a uniform set of criteria to review and compare each APR tool, summarize the advantages and disadvantages of APR techniques, and discuss the current state of APR development. Furthermore, we introduce the research on the related technical areas of APR that have also provided a strong motivation to advance APR development. Finally, we analyze current challenges and future directions, especially highlighting the critical opportunities that large language models bring to APR research.

cs.SE↗

arXiv2023

Meta-Reinforcement Learning Based on Self-Supervised Task Representation Learning

Meta-reinforcement learning enables artificial agents to learn from related training tasks and adapt to new tasks efficiently with minimal interaction data. However, most existing research is still limited to narrow task distributions that are parametric and stationary, and does not consider out-of-distribution tasks during the evaluation, thus, restricting its application. In this paper, we propose MoSS, a context-based Meta-reinforcement learning algorithm based on Self-Supervised task representation learning to address this challenge. We extend meta-RL to broad non-parametric task distributions which have never been explored before, and also achieve state-of-the-art results in non-stationary and out-of-distribution tasks. Specifically, MoSS consists of a task inference module and a policy module. We utilize the Gaussian mixture model for task representation to imitate the parametric and non-parametric task variations. Additionally, our online adaptation strategy enables the agent to react at the first sight of a task change, thus being applicable in non-stationary tasks. MoSS also exhibits strong generalization robustness in out-of-distributions tasks which benefits from the reliable and robust task representation. The policy is built on top of an off-policy RL algorithm and the entire network is trained completely off-policy to ensure high sample efficiency. On MuJoCo and Meta-World benchmarks, MoSS outperforms prior works in terms of asymptotic performance, sample efficiency (3-50x faster), adaptation efficiency, and generalization robustness on broad and diverse task distributions.

cs.LG↗

arXiv2023

Safety Guaranteed Manipulation Based on Reinforcement Learning Planner and Model Predictive Control Actor

Deep reinforcement learning (RL) has been endowed with high expectations in tackling challenging manipulation tasks in an autonomous and self-directed fashion. Despite the significant strides made in the development of reinforcement learning, the practical deployment of this paradigm is hindered by at least two barriers, namely, the engineering of a reward function and ensuring the safety guaranty of learning-based controllers. In this paper, we address these challenging limitations by proposing a framework that merges a reinforcement learning \lstinline[columns=fixed]{planner} that is trained using sparse rewards with a model predictive controller (MPC) \lstinline[columns=fixed]{actor}, thereby offering a safe policy. On the one hand, the RL \lstinline[columns=fixed]{planner} learns from sparse rewards by selecting intermediate goals that are easy to achieve in the short term and promising to lead to target goals in the long term. On the other hand, the MPC \lstinline[columns=fixed]{actor} takes the suggested intermediate goals from the RL \lstinline[columns=fixed]{planner} as the input and predicts how the robot's action will enable it to reach that goal while avoiding any obstacles over a short period of time. We evaluated our method on four challenging manipulation tasks with dynamic obstacles and the results demonstrate that, by leveraging the complementary strengths of these two components, the agent can solve manipulation tasks in complex, dynamic environments safely with a $100\%$ success rate. Videos are available at \url{https://videoviewsite.wixsite.com/mpc-hgg}.

cs.RO↗

arXiv2023

Towards Spatio-temporal Sea Surface Temperature Forecasting via Static and Dynamic Learnable Personalized Graph Convolution Network

Sea surface temperature (SST) is uniquely important to the Earth's atmosphere since its dynamics are a major force in shaping local and global climate and profoundly affect our ecosystems. Accurate forecasting of SST brings significant economic and social implications, for example, better preparation for extreme weather such as severe droughts or tropical cyclones months ahead. However, such a task faces unique challenges due to the intrinsic complexity and uncertainty of ocean systems. Recently, deep learning techniques, such as graphical neural networks (GNN), have been applied to address this task. Even though these methods have some success, they frequently have serious drawbacks when it comes to investigating dynamic spatiotemporal dependencies between signals. To solve this problem, this paper proposes a novel static and dynamic learnable personalized graph convolution network (SD-LPGC). Specifically, two graph learning layers are first constructed to respectively model the stable long-term and short-term evolutionary patterns hidden in the multivariate SST signals. Then, a learnable personalized convolution layer is designed to fuse this information. Our experiments on real SST datasets demonstrate the state-of-the-art performances of the proposed approach on the forecasting task.

cs.LG↗

arXiv2023

Switchable anomalous Hall effects in polar-stacked 2D antiferromagnet MnBi2Te4

Van der Waals (vdW) assembly allows controlling symmetry of two-dimensional (2D) materials that determines their physical properties. Especially interesting is the recently demonstrated breaking inversion symmetry by polar layer stacking to realize novel electronic, magnetic, and transport properties of 2D vdW materials switchable by induced electric polarization. Here, based on symmetry analyses and density-functional calculations, we explore the emergence of the anomalous Hall effect (AHE) in antiferromagnetic MnBi2Te4 films assembled by polar layer stacking. We demonstrate that breaking PT symmetry in an MnBi2Te4 bilayer makes this 2D material magnetoelectric and produces a spontaneous AHE switchable by electric polarization. We find that reversable polarization at one of the interfaces in a three-layer MnBi2Te4 film drives a metal-insulator transition, as well as switching between an AHE and quantum AHE (QAHE). Finally, we predict that engineering an interlayer polarization in a three-layer MnBi2Te4 film allows converting MnBi2Te4 from a trivial insulator to a Chern insulator. Overall, our work emphasizes the emergence of quantum-transport phenomena in 2D vdW antiferromagnets by polar layer stacking, which do not exist in this material in the bulk or bulk-like thin-film forms.

cond-mat.mtrl-sci↗

arXiv2022

Stateful Switch: Optimized Time Series Release with Local Differential Privacy

Time series data have numerous applications in big data analytics. However, they often cause privacy issues when collected from individuals. To address this problem, most existing works perturb the values in the time series while retaining their temporal order, which may lead to significant distortion of the values. Recently, we propose TLDP model that perturbs temporal perturbation to ensure privacy guarantee while retaining original values. It has shown great promise to achieve significantly higher utility than value perturbation mechanisms in many time series analysis. However, its practicability is still undermined by two factors, namely, utility cost of extra missing or empty values, and inflexibility of privacy budget settings. To address them, in this paper we propose {\it switch} as a new two-way operation for temporal perturbation, as opposed to the one-way {\it dispatch} operation. The former inherently eliminates the cost of missing, empty or repeated values. Optimizing switch operation in a {\it stateful} manner, we then propose $StaSwitch$ mechanism for time series release under TLDP. Through both analytical and empirical studies, we show that $StaSwitch$ has significantly higher utility for the published time series than any state-of-the-art temporal- or value-perturbation mechanism, while allowing any combination of privacy budget settings.

cs.CR↗

arXiv2022

TED: Towards Discovering Top-k Edge-Diversified Patterns in a Graph Database

With an exponentially growing number of graphs from disparate repositories, there is a strong need to analyze a graph database containing an extensive collection of small- or medium-sized data graphs (e.g., chemical compounds). Although subgraph enumeration and subgraph mining have been proposed to bring insights into a graph database by a set of subgraph structures, they often end up with similar or homogenous topologies, which is undesirable in many graph applications. To address this limitation, we propose the Top-k Edge-Diversified Patterns Discovery problem to retrieve a set of subgraphs that cover the maximum number of edges in a database. To efficiently process such query, we present a generic and extensible framework called Ted which achieves a guaranteed approximation ratio to the optimal result. Two optimization strategies are further developed to improve the performance. Experimental studies on real-world datasets demonstrate the superiority of Ted to traditional techniques.

cs.DB↗

arXiv2022

Automatic Depth-Optimized Quantum Circuit Synthesis for Diagonal Unitary Matrices with Asymptotically Optimal Gate Count

Current noisy intermediate-scale quantum (NISQ) devices can only execute small circuits with shallow depth, as they are still constrained by the presence of noise: quantum gates have error rates and quantum states are fragile due to decoherence. Hence, it is of great importance to optimize the depth/gate-count when designing quantum circuits for specific tasks. Diagonal unitary matrices are well-known to be key building blocks of many quantum algorithms or quantum computing procedures. Prior work has discussed the synthesis of diagonal unitary matrices over the primitive gate set $\{\text{CNOT}, R_Z\}$. However, the problem has not yet been fully understood, since the existing synthesis methods have not optimized the circuit depth. In this paper, we propose a depth-optimized synthesis algorithm that automatically produces a quantum circuit for any given diagonal unitary matrix. Specially, it not only ensures the asymptotically optimal gate-count, but also nearly halves the total circuit depth compared with the previous method. Technically, we discover a uniform circuit rewriting rule well-suited for reducing the circuit depth. The performance of our synthesis algorithm is both theoretically analyzed and experimentally validated by evaluations on two examples. First, we achieve a nearly 50\% depth reduction over Welch's method for synthesizing random diagonal unitary matrices with up to 16 qubits. Second, we achieve an average of 22.05\% depth reduction for resynthesizing the diagonal part of specific quantum approximate optimization algorithm (QAOA) circuits with up to 14 qubits.

quant-ph↗

arXiv2022

Challenges of `imaging' particulate materials in three dimensions

In this perspective article, we discuss the challenges of imaging assemblies of particles in three dimensions. Starting from a brief motivation for the investigation of particulate materials, we provide an overview of experimental approaches developed for imaging particles. We list the challenges and existing solutions associated with X-ray tomography, one of the standard methods to study statics. Subsequently, we discuss challenges and opportunities arising from emerging new techniques such as radar tracking and `smart' tracers for exploring granular dynamics. We close with a tentative view on the outstanding problems and potential solutions in the future.

cond-mat.soft↗

arXiv2022

A Joint Framework Towards Class-aware and Class-agnostic Alignment for Few-shot Segmentation

Few-shot segmentation (FSS) aims to segment objects of unseen classes given only a few annotated support images. Most existing methods simply stitch query features with independent support prototypes and segment the query image by feeding the mixed features to a decoder. Although significant improvements have been achieved, existing methods are still face class biases due to class variants and background confusion. In this paper, we propose a joint framework that combines more valuable class-aware and class-agnostic alignment guidance to facilitate the segmentation. Specifically, we design a hybrid alignment module which establishes multi-scale query-support correspondences to mine the most relevant class-aware information for each query image from the corresponding support features. In addition, we explore utilizing base-classes knowledge to generate class-agnostic prior mask which makes a distinction between real background and foreground by highlighting all object regions, especially those of unseen classes. By jointly aggregating class-aware and class-agnostic alignment guidance, better segmentation performances are obtained on query images. Extensive experiments on PASCAL-$5^i$ and COCO-$20^i$ datasets demonstrate that our proposed joint framework performs better, especially on the 1-shot setting.

cs.CV↗

arXiv2022

Meta-Reinforcement Learning via Language Instructions

Although deep reinforcement learning has recently been very successful at learning complex behaviors, it requires a tremendous amount of data to learn a task. One of the fundamental reasons causing this limitation lies in the nature of the trial-and-error learning paradigm of reinforcement learning, where the agent communicates with the environment and progresses in the learning only relying on the reward signal. This is implicit and rather insufficient to learn a task well. On the contrary, humans are usually taught new skills via natural language instructions. Utilizing language instructions for robotic motion control to improve the adaptability is a recently emerged topic and challenging. In this paper, we present a meta-RL algorithm that addresses the challenge of learning skills with language instructions in multiple manipulation tasks. On the one hand, our algorithm utilizes the language instructions to shape its interpretation of the task, on the other hand, it still learns to solve task in a trial-and-error process. We evaluate our algorithm on the robotic manipulation benchmark (Meta-World) and it significantly outperforms state-of-the-art methods in terms of training and testing task success rates. Codes are available at \url{https://tumi6robot.wixsite.com/million}.

cs.RO↗