arXiv subjects

Wei Huang

Publications and source records attributed to Wei Huang.

At least 379 records · Page 21Linked to original sources

arXiv2021

JOET: Sustainable Vehicle-assisted Edge Computing for Internet of Vehicles

Task offloading in Internet of Vehicles (IoV) involves numerous steps and optimization variables such as: where to offload tasks, how to allocate computation resources, how to adjust offloading ratio and transmit power for offloading, and such optimization variables and hybrid combination features are highly coupled with each other. Thus, this is a fully challenge issue to optimize these variables for task offloading to sustainably reduce energy consumption with load balancing while ensuring that a task is completed before its deadline. In this paper, we first provide a Mixed Integer Nonlinear Programming Problem (MINLP) formulation for such task offloading under energy and deadline constraints in IoV. Furthermore, in order to efficiently solve the formulated MINLP, we decompose it into two subproblems, and design a low-complexity Joint Optimization for Energy Consumption and Task Processing Delay (JOET) algorithm to optimize selection decisions, resource allocation, offloading ratio and transmit power adjustment. We carry out extensive simulation experiments to validate JOET. Simulation results demonstrate that JOET outperforms many representative existing approaches in quickly converge and effectively reduce energy consumption and delay. Specifically, average energy consumption and task processing delay have been reduced by 15.93% and 15.78%, respectively, and load balancing efficiency has increased by 10.20%.

cs.OH↗

arXiv2021

Hybrid Quantum-Classical Convolutional Neural Networks

Deep learning has been shown to be able to recognize data patterns better than humans in specific circumstances or contexts. In parallel, quantum computing has demonstrated to be able to output complex wave functions with a few number of gate operations, which could generate distributions that are hard for a classical computer to produce. Here we propose a hybrid quantum-classical convolutional neural network (QCCNN), inspired by convolutional neural networks (CNNs) but adapted to quantum computing to enhance the feature mapping process. QCCNN is friendly to currently noisy intermediate-scale quantum computers, in terms of both number of qubits as well as circuit's depths, while retaining important features of classical CNN, such as nonlinearity and scalability. We also present a framework to automatically compute the gradients of hybrid quantum-classical loss functions which could be directly applied to other hybrid quantum-classical algorithms. We demonstrate the potential of this architecture by applying it to a Tetris dataset, and show that QCCNN can accomplish classification tasks with learning accuracy surpassing that of classical CNN.

quant-ph↗

arXiv2021

Tutorials on Testing Neural Networks

Deep learning achieves remarkable performance on pattern recognition, but can be vulnerable to defects of some important properties such as robustness and security. This tutorial is based on a stream of research conducted since the summer of 2018 at a few UK universities, including the University of Liverpool, University of Oxford, Queen's University Belfast, University of Lancaster, University of Loughborough, and University of Exeter. The research aims to adapt software engineering methods, in particular software testing methods, to work with machine learning models. Software testing techniques have been successful in identifying software bugs, and helping software developers in validating the software they design and implement. It is for this reason that a few software testing techniques -- such as the MC/DC coverage metric -- have been mandated in industrial standards for safety critical systems, including the ISO26262 for automotive systems and the RTCA DO-178B/C for avionics systems. However, these techniques cannot be directly applied to machine learning models, because the latter are drastically different from traditional software, and their design follows a completely different development life-cycle. As the outcome of this thread of research, the team has developed a series of methods that adapt the software testing techniques to work with a few classes of machine learning models. The latter notably include convolutional neural networks, recurrent neural networks, and random forest. The tools developed from this research are now collected, and publicly released, in a GitHub repository: \url{https://github.com/TrustAI/DeepConcolic}, with the BSD 3-Clause licence. This tutorial is to go through the major functionalities of the tools with a few running examples, to exhibit how the developed techniques work, what the results are, and how to interpret them.

cs.SE↗

arXiv2021

Unsupervised Cross-Modal Distillation for Thermal Infrared Tracking

The target representation learned by convolutional neural networks plays an important role in Thermal Infrared (TIR) tracking. Currently, most of the top-performing TIR trackers are still employing representations learned by the model trained on the RGB data. However, this representation does not take into account the information in the TIR modality itself, limiting the performance of TIR tracking. To solve this problem, we propose to distill representations of the TIR modality from the RGB modality with Cross-Modal Distillation (CMD) on a large amount of unlabeled paired RGB-TIR data. We take advantage of the two-branch architecture of the baseline tracker, i.e. DiMP, for cross-modal distillation working on two components of the tracker. Specifically, we use one branch as a teacher module to distill the representation learned by the model into the other branch. Benefiting from the powerful model in the RGB modality, the cross-modal distillation can learn the TIR-specific representation for promoting TIR tracking. The proposed approach can be incorporated into different baseline trackers conveniently as a generic and independent component. Furthermore, the semantic coherence of paired RGB and TIR images is utilized as a supervised signal in the distillation loss for cross-modal knowledge transfer. In practice, three different approaches are explored to generate paired RGB-TIR patches with the same semantics for training in an unsupervised way. It is easy to extend to an even larger scale of unlabeled training data. Extensive experiments on the LSOTB-TIR dataset and PTB-TIR dataset demonstrate that our proposed cross-modal distillation method effectively learns TIR-specific target representations transferred from the RGB modality. Our tracker outperforms the baseline tracker by achieving absolute gains of 2.3% Success, 2.7% Precision, and 2.5% Normalized Precision respectively.

cs.CV↗

arXiv2021

On the Neural Tangent Kernel of Deep Networks with Orthogonal Initialization

The prevailing thinking is that orthogonal weights are crucial to enforcing dynamical isometry and speeding up training. The increase in learning speed that results from orthogonal initialization in linear networks has been well-proven. However, while the same is believed to also hold for nonlinear networks when the dynamical isometry condition is satisfied, the training dynamics behind this contention have not been thoroughly explored. In this work, we study the dynamics of ultra-wide networks across a range of architectures, including Fully Connected Networks (FCNs) and Convolutional Neural Networks (CNNs) with orthogonal initialization via neural tangent kernel (NTK). Through a series of propositions and lemmas, we prove that two NTKs, one corresponding to Gaussian weights and one to orthogonal weights, are equal when the network width is infinite. Further, during training, the NTK of an orthogonally-initialized infinite-width network should theoretically remain constant. This suggests that the orthogonal initialization cannot speed up training in the NTK (lazy training) regime, contrary to the prevailing thoughts. In order to explore under what circumstances can orthogonality accelerate training, we conduct a thorough empirical investigation outside the NTK regime. We find that when the hyper-parameters are set to achieve a linear regime in nonlinear activation, orthogonal initialization can improve the learning speed with a large learning rate or large depth.

cs.LG↗

arXiv2021

Heterogeneous network-based drug repurposing for COVID-19

The Corona Virus Disease 2019 (COVID-19) belongs to human coronaviruses (HCoVs), which spreads rapidly around the world. Compared with new drug development, drug repurposing may be the best shortcut for treating COVID-19. Therefore, we constructed a comprehensive heterogeneous network based on the HCoVs-related target proteins and use the previously proposed deepDTnet, to discover potential drug candidates for COVID-19. We obtain high performance in predicting the possible drugs effective for COVID-19 related proteins. In summary, this work utilizes a powerful heterogeneous network-based deep learning method, which may be beneficial to quickly identify candidate repurposable drugs toward future clinical trials for COVID-19. The code and data are available at https://github.com/stjin-XMU/HnDR-COVID.

cs.LG↗

arXiv2021

Population transfer under local dephasing

Stimulated Raman adiabatic passage is a well-known technique for quantum population transfer due to its robustness again various sources of noises. Here we consider quantum population transfer from one spin to another via an intermediate spin which subjects to dephasing noise. We obtain an analytic expression for the transfer efficiency under a specific driving protocol, showing that dephasing could reduce the transfer efficiency, but the effect of dephasing could also be suppressed with a stronger laser coupling or a longer laser duration. We also consider another commonly used driving protocol, which shows that this analytic picture is still qualitatively correct.

quant-ph↗

arXiv2021

Transferability of Spectral Graph Convolutional Neural Networks

This paper focuses on spectral graph convolutional neural networks (ConvNets), where filters are defined as elementwise multiplication in the frequency domain of a graph. In machine learning settings where the dataset consists of signals defined on many different graphs, the trained ConvNet should generalize to signals on graphs unseen in the training set. It is thus important to transfer ConvNets between graphs. Transferability, which is a certain type of generalization capability, can be loosely defined as follows: if two graphs describe the same phenomenon, then a single filter or ConvNet should have similar repercussions on both graphs. This paper aims at debunking the common misconception that spectral filters are not transferable. We show that if two graphs discretize the same "continuous" space, then a spectral filter or ConvNet has approximately the same repercussion on both graphs. Our analysis is more permissive than the standard analysis. Transferability is typically described as the robustness of the filter to small graph perturbations and re-indexing of the vertices. Our analysis accounts also for large graph perturbations. We prove transferability between graphs that can have completely different dimensions and topologies, only requiring that both graphs discretize the same underlying space in some generic sense.

cs.LG↗

arXiv2021

Sequential Random Network for Fine-grained Image Classification

Deep Convolutional Neural Network (DCNN) and Transformer have achieved remarkable successes in image recognition. However, their performance in fine-grained image recognition is still difficult to meet the requirements of actual needs. This paper proposes a Sequence Random Network (SRN) to enhance the performance of DCNN. The output of DCNN is one-dimensional features. This one-dimensional feature abstractly represents image information, but it does not express well the detailed information of image. To address this issue, we use the proposed SRN which composed of BiLSTM and several Tanh-Dropout blocks (called BiLSTM-TDN), to further process DCNN one-dimensional features for highlighting the detail information of image. After the feature transform by BiLSTM-TDN, the recognition performance has been greatly improved. We conducted the experiments on six fine-grained image datasets. Except for FGVC-Aircraft, the accuracies of the proposed methods on the other datasets exceeded 99%. Experimental results show that BiLSTM-TDN is far superior to the existing state-of-the-art methods. In addition to DCNN, BiLSTM-TDN can also be extended to other models, such as Transformer.

cs.CV↗

arXiv2021

Assessing the Reliability of Deep Learning Classifiers Through Robustness Evaluation and Operational Profiles

The utilisation of Deep Learning (DL) is advancing into increasingly more sophisticated applications. While it shows great potential to provide transformational capabilities, DL also raises new challenges regarding its reliability in critical functions. In this paper, we present a model-agnostic reliability assessment method for DL classifiers, based on evidence from robustness evaluation and the operational profile (OP) of a given application. We partition the input space into small cells and then "assemble" their robustness (to the ground truth) according to the OP, where estimators on the cells' robustness and OPs are provided. Reliability estimates in terms of the probability of misclassification per input (pmi) can be derived together with confidence levels. A prototype tool is demonstrated with simplified case studies. Model assumptions and extension to real-world applications are also discussed. While our model easily uncovers the inherent difficulties of assessing the DL dependability (e.g. lack of data with ground truth and scalability issues), we provide preliminary/compromised solutions to advance in this research direction.

cs.LG↗

arXiv2021

BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations

Given the pressing need for assuring algorithmic transparency, Explainable AI (XAI) has emerged as one of the key areas of AI research. In this paper, we develop a novel Bayesian extension to the LIME framework, one of the most widely used approaches in XAI -- which we call BayLIME. Compared to LIME, BayLIME exploits prior knowledge and Bayesian reasoning to improve both the consistency in repeated explanations of a single prediction and the robustness to kernel settings. BayLIME also exhibits better explanation fidelity than the state-of-the-art (LIME, SHAP and GradCAM) by its ability to integrate prior knowledge from, e.g., a variety of other XAI techniques, as well as verification and validation (V&V) methods. We demonstrate the desirable properties of BayLIME through both theoretical analysis and extensive experiments.

cs.AI↗

arXiv2021

Efficient sorting of orbital-angular-momentum states with large topological charges and their unknown superpositions via machine learning

Light beams carrying orbital-angular-momentum (OAM) play an important role in optical manipulation and communication owing to their unbounded state space. However, it is still challenging to efficiently discriminate OAM modes with large topological charges and thus only a small part of the OAM states have been usually used. Here we demonstrate that neural networks can be trained to sort OAM modes with large topological charges and unknown superpositions. Using intensity images of OAM modes generalized in simulations and experiments as the input data, we illustrate that our neural network has great generalization power to recognize OAM modes of large topological charges beyond training areas with high accuracy. Moreover, the trained neural network can correctly classify and predict arbitrary superpositions of two OAM modes with random topological charges. Our machine learning approach only requires a small portion of experimental samples and significantly reduces the cost in experiments, which paves the way to study the OAM physics and increase the state space of OAM beams in practical applications.

physics.optics↗

arXiv2021

Coverage Guided Testing for Recurrent Neural Networks

Recurrent neural networks (RNNs) have been applied to a broad range of applications, including natural language processing, drug discovery, and video recognition. Their vulnerability to input perturbation is also known. Aligning with a view from software defect detection, this paper aims to develop a coverage guided testing approach to systematically exploit the internal behaviour of RNNs, with the expectation that such testing can detect defects with high possibility. Technically, the long short term memory network (LSTM), a major class of RNNs, is thoroughly studied. A family of three test metrics are designed to quantify not only the values but also the temporal relations (including both step-wise and bounded-length) exhibited when LSTM processing inputs. A genetic algorithm is applied to efficiently generate test cases. The test metrics and test case generation algorithm are implemented into a tool TestRNN, which is then evaluated on a set of LSTM benchmarks. Experiments confirm that TestRNN has advantages over the state-of-art tool DeepStellar and attack-based defect detection methods, owing to its working with finer temporal semantics and the consideration of the naturalness of input perturbation. Furthermore, TestRNN enables meaningful information to be collected and exhibited for users to understand the testing results, which is an important step towards interpretable neural network testing.

cs.LG↗

arXiv2021

Conformer: Local Features Coupling Global Representations for Visual Recognition

Within Convolutional Neural Network (CNN), the convolution operations are good at extracting local features but experience difficulty to capture global representations. Within visual transformer, the cascaded self-attention modules can capture long-distance feature dependencies but unfortunately deteriorate local feature details. In this paper, we propose a hybrid network structure, termed Conformer, to take advantage of convolutional operations and self-attention mechanisms for enhanced representation learning. Conformer roots in the Feature Coupling Unit (FCU), which fuses local features and global representations under different resolutions in an interactive fashion. Conformer adopts a concurrent structure so that local features and global representations are retained to the maximum extent. Experiments show that Conformer, under the comparable parameter complexity, outperforms the visual transformer (DeiT-B) by 2.3% on ImageNet. On MSCOCO, it outperforms ResNet-101 by 3.7% and 3.6% mAPs for object detection and instance segmentation, respectively, demonstrating the great potential to be a general backbone network. Code is available at https://github.com/pengzhiliang/Conformer.

cs.CV↗

arXiv2021

Adiabatic following of terahertz surface plasmon-polaritons coupler via two waveguides structure

Most recently, two remarkable papers [New J. Phys. 21, 113004 (2019); IEEE J. Sel. Top. Quantum Electron 27, 1 (2020)] propose broadband complete transfer terahertz (THz) surface plasmon polaritons (SPPs) waveguide coupler by applying coherent quantum control -- Stimulated Raman adiabatic passage (STIRAP). However, previous researches request three SPPs waveguides coupler. In this paper, we propose a new design of a broadband complete transfer THz SPPs coupler with an innovative structure of two waveguides by employing two state adiabatic following. In order to realize this design, we introduce the detuning parameter into the coupling equation of SPPs waveguides for the first time. We believe that this finding will improve the THz communication domain.

physics.optics↗

arXiv2021

PD-GAN: Probabilistic Diverse GAN for Image Inpainting

We propose PD-GAN, a probabilistic diverse GAN for image inpainting. Given an input image with arbitrary hole regions, PD-GAN produces multiple inpainting results with diverse and visually realistic content. Our PD-GAN is built upon a vanilla GAN which generates images based on random noise. During image generation, we modulate deep features of input random noise from coarse-to-fine by injecting an initially restored image and the hole regions in multiple scales. We argue that during hole filling, the pixels near the hole boundary should be more deterministic (i.e., with higher probability trusting the context and initially restored image to create natural inpainting boundary), while those pixels lie in the center of the hole should enjoy more degrees of freedom (i.e., more likely to depend on the random noise for enhancing diversity). To this end, we propose spatially probabilistic diversity normalization (SPDNorm) inside the modulation to model the probability of generating a pixel conditioned on the context information. SPDNorm dynamically balances the realism and diversity inside the hole region, making the generated content more diverse towards the hole center and resemble neighboring image content more towards the hole boundary. Meanwhile, we propose a perceptual diversity loss to further empower PD-GAN for diverse content generation. Experiments on benchmark datasets including CelebA-HQ, Places2 and Paris Street View indicate that PD-GAN is effective for diverse and visually realistic image restoration.

cs.CV↗

arXiv2021

Universal coupled theory for metamaterial Bound states in the continuum

In this paper, we present a novel universal coupled theory for metamaterial Bound states in the continuum (BIC) or quasi-Bound states in the continuum (quasi-BIC) which provides ultra-high Q resonance for metamaterial devices. Our theory analytically calculates the coupling of two bright modes with phase. Our method has much more accuracy for ultra-strong coupling comparing with the previous theory (the coupling of one bright mode and one dark mode). Therefore, our theory is much more suitable for BIC or quasi-BIC and we can accurately predict the transmission spectrum of metamaterial BIC or quasi-BIC for the first time.

physics.optics↗

arXiv2021

Detecting Operational Adversarial Examples for Reliable Deep Learning

The utilisation of Deep Learning (DL) raises new challenges regarding its dependability in critical applications. Sound verification and validation methods are needed to assure the safe and reliable use of DL. However, state-of-the-art debug testing methods on DL that aim at detecting adversarial examples (AEs) ignore the operational profile, which statistically depicts the software's future operational use. This may lead to very modest effectiveness on improving the software's delivered reliability, as the testing budget is likely to be wasted on detecting AEs that are unrealistic or encountered very rarely in real-life operation. In this paper, we first present the novel notion of "operational AEs" which are AEs that have relatively high chance to be seen in future operation. Then an initial design of a new DL testing method to efficiently detect "operational AEs" is provided, as well as some insights on our prospective research plan.

cs.SE↗