arXiv subjects

Ling Wang

Publications and source records attributed to Ling Wang.

At least 91 records · Page 5Linked to original sources

arXiv2023

Enhancing the Robustness of QMIX against State-adversarial Attacks

Deep reinforcement learning (DRL) performance is generally impacted by state-adversarial attacks, a perturbation applied to an agent's observation. Most recent research has concentrated on robust single-agent reinforcement learning (SARL) algorithms against state-adversarial attacks. Still, there has yet to be much work on robust multi-agent reinforcement learning. Using QMIX, one of the popular cooperative multi-agent reinforcement algorithms, as an example, we discuss four techniques to improve the robustness of SARL algorithms and extend them to multi-agent scenarios. To increase the robustness of multi-agent reinforcement learning (MARL) algorithms, we train models using a variety of attacks in this research. We then test the models taught using the other attacks by subjecting them to the corresponding attacks throughout the training phase. In this way, we organize and summarize techniques for enhancing robustness when used with MARL.

cs.LG↗

arXiv2023

MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks

Meta-learning algorithms are able to learn a new task using previously learned knowledge, but they often require a large number of meta-training tasks which may not be readily available. To address this issue, we propose a method for few-shot learning with fewer tasks, which we call MetaModulation. The key idea is to use a neural network to increase the density of the meta-training tasks by modulating batch normalization parameters during meta-training. Additionally, we modify parameters at various network levels, rather than just a single layer, to increase task diversity. To account for the uncertainty caused by the limited training tasks, we propose a variational MetaModulation where the modulation parameters are treated as latent variables. We also introduce learning variational feature hierarchies by the variational MetaModulation, which modulates features at all layers and can consider task uncertainty and generate more diverse tasks. The ablation studies illustrate the advantages of utilizing a learnable task modulation at different levels and demonstrate the benefit of incorporating probabilistic variants in few-task meta-learning. Our MetaModulation and its variational variants consistently outperform state-of-the-art alternatives on four few-task meta-learning benchmarks.

cs.LG↗

arXiv2023

Liouville theorems for a class of degenerate or singular Monge-Ampère equations

In this note, we classify solutions to a class of Monge-Ampère equations whose right hand side may be degenerate or singular in the half space. Solutions to these equations are special solutions to a class of fourth order equations, including the affine maximal hypersurface equation, in the half space. Both the Dirichlet boundary value and Neumann boundary value cases are considered.

math.AP↗

arXiv2023

VPU-EM: An Event-based Modeling Framework to Evaluate NPU Performance and Power Efficiency at Scale

State-of-art NPUs are typically architected as a self-contained sub-system with multiple heterogeneous hardware computing modules, and a dataflow-driven programming model. There lacks well-established methodology and tools in the industry to evaluate and compare the performance of NPUs from different architectures. We present an event-based performance modeling framework, VPU-EM, targeting scalable performance evaluation of modern NPUs across diversified AI workloads. The framework adopts high-level event-based system-simulation methodology to abstract away design details for speed, while maintaining hardware pipelining, concurrency and interaction with software task scheduling. It is natively developed in Python and built to interface directly with AI frameworks such as Tensorflow, PyTorch, ONNX and OpenVINO, linking various in-house NPU graph compilers to achieve optimized full model performance. Furthermore, VPU-EM also provides the capability to model power characteristics of NPU in Power-EM mode to enable joint performance/power analysis. Using VPU-EM, we conduct performance/power analysis of models from representative neural network architecture. We demonstrate that even though this framework is developed for Intel VPU, an Intel in-house NPU IP technology, the methodology can be generalized for analysis of modern NPUs.

cs.AR↗

arXiv2023

STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation

Self-supervised depth estimation draws a lot of attention recently as it can promote the 3D sensing capabilities of self-driving vehicles. However, it intrinsically relies upon the photometric consistency assumption, which hardly holds during nighttime. Although various supervised nighttime image enhancement methods have been proposed, their generalization performance in challenging driving scenarios is not satisfactory. To this end, we propose the first method that jointly learns a nighttime image enhancer and a depth estimator, without using ground truth for either task. Our method tightly entangles two self-supervised tasks using a newly proposed uncertain pixel masking strategy. This strategy originates from the observation that nighttime images not only suffer from underexposed regions but also from overexposed regions. By fitting a bridge-shaped curve to the illumination map distribution, both regions are suppressed and two tasks are bridged naturally. We benchmark the method on two established datasets: nuScenes and RobotCar and demonstrate state-of-the-art performance on both of them. Detailed ablations also reveal the mechanism of our proposal. Last but not least, to mitigate the problem of sparse ground truth of existing datasets, we provide a new photo-realistically enhanced nighttime dataset based upon CARLA. It brings meaningful new challenges to the community. Codes, data, and models are available at https://github.com/ucaszyp/STEPS.

cs.CV↗

arXiv2022

Coevolutionary Framework for Generalized Multimodal Multi-objective Optimization

Most multimodal multi-objective evolutionary algorithms (MMEAs) aim to find all global Pareto optimal sets (PSs) for a multimodal multi-objective optimization problem (MMOP). However, in real-world problems, decision makers (DMs) may be also interested in local PSs. Also, searching for both global and local PSs is more general in view of dealing with MMOPs, which can be seen as a generalized MMOP. In addition, the state-of-the-art MMEAs exhibit poor convergence on high-dimension MMOPs. To address the above two issues, in this study, a novel coevolutionary framework termed CoMMEA for multimodal multi-objective optimization is proposed to better obtain both global and local PSs, and simultaneously, to improve the convergence performance in dealing with high-dimension MMOPs. Specifically, the CoMMEA introduces two archives to the search process, and coevolves them simultaneously through effective knowledge transfer. The convergence archive assists the CoMMEA to quickly approaching the Pareto optimal front (PF). The knowledge of the converged solutions is then transferred to the diversity archive which utilizes the local convergence indicator and the $ε$-dominance-based method to obtain global and local PSs effectively. Experimental results show that CoMMEA is competitive compared to seven state-of-the-art MMEAs on fifty-four complex MMOPs.

cs.NE↗

arXiv2022

VDDB: a comprehensive resource and machine learning platform for antiviral drug discovery

Virus infection is one of the major diseases that seriously threaten human health. To meet the growing demand for mining and sharing data resources related to antiviral drugs and to accelerate the design and discovery of new antiviral drugs, we presented an open-access antiviral drug resource and machine learning platform (VDDB), which, to the best of our knowledge, is the first comprehensive dedicated resource for experimentally verified potential drugs/molecules based on manually curated data. Currently, VDDB highlights 848 clinical vaccines, 199 clinical antibodies, as well as over 710,000 small molecules targeting 39 medically important viruses including SARS-CoV-2. Furthermore, VDDB stores approximately 3 million records of pharmacological data for these collected potential antiviral drugs/molecules, involving 314 cell infection-based phenotypic and 234 target-based genotypic assays. Based on these annotated pharmacological data, VDDB allows users to browse, search and download reliable information about these collects for various viruses of interest. In particular, VDDB also integrates 57 cell infection- and 117 target-based associated high-accuracy machine learning models to support various antivirals identification-related tasks, such as compound activity prediction, virtual screening, drug repositioning and target fishing. VDDB is freely accessible at http://vddb.idruglab.cn.

q-bio.BM↗

arXiv2022

HiGNN: Hierarchical Informative Graph Neural Networks for Molecular Property Prediction Equipped with Feature-Wise Attention

Elucidating and accurately predicting the druggability and bioactivities of molecules plays a pivotal role in drug design and discovery and remains an open challenge. Recently, graph neural networks (GNN) have made remarkable advancements in graph-based molecular property prediction. However, current graph-based deep learning methods neglect the hierarchical information of molecules and the relationships between feature channels. In this study, we propose a well-designed hierarchical informative graph neural networks framework (termed HiGNN) for predicting molecular property by utilizing a co-representation learning of molecular graphs and chemically synthesizable BRICS fragments. Furthermore, a plug-and-play feature-wise attention block is first designed in HiGNN architecture to adaptively recalibrate atomic features after the message passing phase. Extensive experiments demonstrate that HiGNN achieves state-of-the-art predictive performance on many challenging drug discovery-associated benchmark datasets. In addition, we devise a molecule-fragment similarity mechanism to comprehensively investigate the interpretability of HiGNN model at the subgraph level, indicating that HiGNN as a powerful deep learning tool can help chemists and pharmacists identify the key components of molecules for designing better molecules with desired properties or functions. The source code is publicly available at https://github.com/idruglab/hignn.

cs.LG↗

arXiv2022

Interior estimates for Monge-Ampère type fourth order equations

In this paper, we give several new approaches to study interior estimates for a class of fourth order equations of Monge-Ampère type. First, we prove interior estimates for the homogeneous equation in dimension two by using the partial Legendre transform. As an application, we obtain a new proof of the Bernstein theorem without using Caffarelli-Gutiérrez's estimate, including the Chern conjecture on affine maximal surfaces. For the inhomogeneous equation, we also obtain a new proof in dimension two by an integral method relying on the Monge-Ampère Sobolev inequality. This proof works even when the right hand side is singular. In higher dimensions, we obtain the interior regularity in terms of integral bounds on the second derivatives and the inverse of the determinant.

math.AP↗

arXiv2022

Large-scale matrix optimization based multi microgrid topology design with a constrained differential evolution algorithm

Binary matrix optimization commonly arise in the real world, e.g., multi-microgrid network structure design problem (MGNSDP), which is to minimize the total length of the power supply line under certain constraints. Finding the global optimal solution for these problems faces a great challenge since such problems could be large-scale, sparse and multimodal. Traditional linear programming is time-consuming and cannot solve nonlinear problems. To address this issue, a novel improved feasibility rule based differential evolution algorithm, termed LBMDE, is proposed. To be specific, a general heuristic solution initialization method is first proposed to generate high-quality solutions. Then, a binary-matrix-based DE operator is introduced to produce offspring. To deal with the constraints, we proposed an improved feasibility rule based environmental selection strategy. The performance and searching behaviors of LBMDE are examined by a set of benchmark problems.

cs.NE↗

arXiv2022

Quantum spin liquid phase in the Shastry-Sutherland model detected by an improved level spectroscopic method

We study the spin-$1/2$ two-dimensional Shastry-Sutherland spin model by exact diagonalization of clusters with periodic boundary conditions. We develop an improved level spectroscopic technique using energy gaps between states with different quantum numbers. The crossing points of some of the relative (composite) gaps have much weaker finite-size drifts than the normally used gaps defined only with respect to the ground state, thus allowing precise determination of quantum critical points even with small clusters. Our results support the picture of a spin liquid phase intervening between the well known plaquette-singlet and antiferromagnetic ground states, with phase boundaries in almost perfect agreement with a recent density matrix renormalization group study, where much larger cylindrical lattices were used [J. Yang et al., Phys. Rev. B {\bf 105}, L060409 (2022)]. The method of using composite low-energy gaps to reduce scaling corrections has potentially broad applications in numerical studies of quantum critical phenomena.

cond-mat.str-el↗

arXiv2022

FP-GNN: a versatile deep learning architecture for enhanced molecular property prediction

Deep learning is an important method for molecular design and exhibits considerable ability to predict molecular properties, including physicochemical, bioactive, and ADME/T (absorption, distribution, metabolism, excretion, and toxicity) properties. In this study, we advanced a novel deep learning architecture, termed FP-GNN, which combined and simultaneously learned information from molecular graphs and fingerprints. To evaluate the FP-GNN model, we conducted experiments on 13 public datasets, an unbiased LIT-PCBA dataset, and 14 phenotypic screening datasets for breast cell lines. Extensive evaluation results showed that compared to advanced deep learning and conventional machine learning algorithms, the FP-GNN algorithm achieved state-of-the-art performance on these datasets. In addition, we analyzed the influence of different molecular fingerprints, and the effects of molecular graphs and molecular fingerprints on the performance of the FP-GNN model. Analysis of the anti-noise ability and interpretation ability also indicated that FP-GNN was competitive in real-world situations.

q-bio.MN↗

arXiv2022

LAI Estimation of Cucumber Crop Based on Improved Fully Convolutional Network

LAI (Leaf Area Index) is of great importance for crop yield estimation in agronomy. It is directly related to plant growth status, net assimilation rate, plant photosynthesis, and carbon dioxide in the environment. How to measure LAI accurately and efficiently is the key to the crop yield estimation problem. Manual measurement consumes a lot of human resources and material resources. Remote sensing technology is not suitable for near-Earth LAI measurement. Besides, methods based on traditional digital image processing are greatly affected by environmental noise and image exposure. Nowadays, deep learning is widely used in many fields. The improved FCN (Fully Convolutional Network) is proposed in our study for LAI measure task. Eighty-two cucumber images collected from our greenhouse are labeled to fine-tuning the pre-trained model. The result shows that the improved FCN model performs well on our dataset. Our method's mean IoU can reach 0.908, which is 11% better than conventional methods and 4.7% better than the basic FCN model.

cs.CV↗

arXiv2022

Deep Reinforcement Learning for Online Routing of Unmanned Aerial Vehicles with Wireless Power Transfer

The unmanned aerial vehicle (UAV) plays an vital role in various applications such as delivery, military mission, disaster rescue, communication, etc., due to its flexibility and versatility. This paper proposes a deep reinforcement learning method to solve the UAV online routing problem with wireless power transfer, which can charge the UAV remotely without wires, thus extending the capability of the battery-limited UAV. Our study considers the power consumption of the UAV and the wireless charging process. Unlike the previous works, we solve the problem by a designed deep neural network. The model is trained using a deep reinforcement learning method offline, and is used to optimize the UAV routing problem online. On small and large scale instances, the proposed model runs from four times to 500 times faster than Google OR-tools, the state-of-the-art combinatorial optimization solver, with identical solution quality. It also outperforms different types of heuristic and local search methods in terms of both run-time and optimality. In addition, once the model is trained, it can scale to new generated problem instances with arbitrary topology that are not seen during training. The proposed method is practically applicable when the problem scale is large and the response time is crucial.

cs.LG↗

arXiv2022

Crystal growth engineering and origin of the weak ferromagnetism in antiferromagnetic matrix of orthochromates from $t$-$e$ orbital hybridization

We report a combined experimental and theoretical study on intriguing magnetic properties of quasiferroelectric orthochromates. Large single crystals of the family of RECrO$_3$ (RE = Y, Eu, Gd, Tb, Dy, Ho, Er, Tm, Yb, and Lu) compounds were successfully grown. Neutron Laue study indicates a good quality of the obtained single crystals. Applied magnetic-field and temperature dependent magnetization measurements reveal their intrinsic magnetic properties, especially the antiferromagnetic (AFM) transition temperatures. Density functional theory studies of the electronic structures were carried out using the Perdew-Burke-Ernzerhof functional plus Hubbard $U$ method. Crystallographic information and magnetism were theoretically optimized systematically. When RE$^{3+}$ cations vary from Y$^{3+}$ and Eu$^{3+}$ to Lu$^{3+}$ ions, the calculated $t$-$e$ orbital hybridization degree and Néel temperature behave similarly to the experimentally-determined AFM transition temperature with variation in cationic radius. We found that the $t$-$e$ hybridization is anisotropic, causing a magnetic anisotropy of Cr$^{3+}$ sublattices. This was evaluated with the nearest-neighbour $J_1$-$J_2$ model. Our research provides a picture of the electronic structures during the $t$-$e$ hybridization process while changing RE ions and sheds light on the nature of the weak ferromagnetism coexisting with predominated antiferromagnetism. The available large RECrO$_3$ single crystals build a platform for further studies of orthochromates.

cond-mat.str-el↗

arXiv2022

Quantum Criticality and Spin Liquid Phase in the Shastry-Sutherland model

Using the density-matrix renormalization group method for the ground state and excitations of the Shastry- Sutherland spin model, we demonstrate the existence of a narrow quantum spin liquid phase between the previously known plaquette-singlet and antiferromagnetic states. Our conclusions are based on finite-size scaling of excited level crossings and order parameters. Together with previous results on candidate models for deconfined quantum criticality and spin liquid phases, our results point to a unified quantum phase diagram where the deconfined quantum-critical point separates a line of first-order transitions and a gapless spin liquid phase. The frustrated Shastry-Sutherland model is close to the critical point but slightly inside the spin liquid phase, while previously studied unfrustrated models cross the first-order line. We also argue that recent heat capacity measurements in SrCu2(BO3)2 show evidence of the proposed spin liquid at pressures between 2.6 and 3 GPa.

cond-mat.str-el↗

arXiv2022

Temporal Convolution Domain Adaptation Learning for Crops Growth Prediction

Existing Deep Neural Nets on crops growth prediction mostly rely on availability of a large amount of data. In practice, it is difficult to collect enough high-quality data to utilize the full potential of these deep learning models. In this paper, we construct an innovative network architecture based on domain adaptation learning to predict crops growth curves with limited available crop data. This network architecture overcomes the challenge of data availability by incorporating generated data from the developed crops simulation model. We are the first to use the temporal convolution filters as the backbone to construct a domain adaptation network architecture which is suitable for deep learning regression models with very limited training data of the target domain. We conduct experiments to test the performance of the network and compare our proposed architecture with other state-of-the-art methods, including a recent LSTM-based domain adaptation network architecture. The results show that the proposed temporal convolution-based network architecture outperforms all benchmarks not only in accuracy but also in model size and convergence rate.

cs.LG↗

arXiv2021

Explainable Artificial Intelligence for Pharmacovigilance: What Features Are Important When Predicting Adverse Outcomes?

Explainable Artificial Intelligence (XAI) has been identified as a viable method for determining the importance of features when making predictions using Machine Learning (ML) models. In this study, we created models that take an individual's health information (e.g. their drug history and comorbidities) as inputs, and predict the probability that the individual will have an Acute Coronary Syndrome (ACS) adverse outcome. Using XAI, we quantified the contribution that specific drugs had on these ACS predictions, thus creating an XAI-based technique for pharmacovigilance monitoring, using ACS as an example of the adverse outcome to detect. Individuals aged over 65 who were supplied Musculo-skeletal system (anatomical therapeutic chemical (ATC) class M) or Cardiovascular system (ATC class C) drugs between 1993 and 2009 were identified, and their drug histories, comorbidities, and other key features were extracted from linked Western Australian datasets. Multiple ML models were trained to predict if these individuals would have an ACS related adverse outcome (i.e., death or hospitalisation with a discharge diagnosis of ACS), and a variety of ML and XAI techniques were used to calculate which features -- specifically which drugs -- led to these predictions. The drug dispensing features for rofecoxib and celecoxib were found to have a greater than zero contribution to ACS related adverse outcome predictions (on average), and it was found that ACS related adverse outcomes can be predicted with 72% accuracy. Furthermore, the XAI libraries LIME and SHAP were found to successfully identify both important and unimportant features, with SHAP slightly outperforming LIME. ML models trained on linked administrative health datasets in tandem with XAI algorithms can successfully quantify feature importance, and with further development, could potentially be used as pharmacovigilance monitoring techniques.

q-bio.QM↗