arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 1,351 records · Page 75Linked to original sources

arXiv2022

Decomposing Generation Networks with Structure Prediction for Recipe Generation

Recipe generation from food images and ingredients is a challenging task, which requires the interpretation of the information from another modality. Different from the image captioning task, where the captions usually have one sentence, cooking instructions contain multiple sentences and have obvious structures. To help the model capture the recipe structure and avoid missing some cooking details, we propose a novel framework: Decomposing Generation Networks (DGN) with structure prediction, to get more structured and complete recipe generation outputs. Specifically, we split each cooking instruction into several phases, and assign different sub-generators to each phase. Our approach includes two novel ideas: (i) learning the recipe structures with the global structure prediction component and (ii) producing recipe phases in the sub-generator output component based on the predicted structure. Extensive experiments on the challenging large-scale Recipe1M dataset validate the effectiveness of our proposed model, which improves the performance over the state-of-the-art results.

cs.CV↗

arXiv2022

Context Uncertainty in Contextual Bandits with Applications to Recommender Systems

Recurrent neural networks have proven effective in modeling sequential user feedbacks for recommender systems. However, they usually focus solely on item relevance and fail to effectively explore diverse items for users, therefore harming the system performance in the long run. To address this problem, we propose a new type of recurrent neural networks, dubbed recurrent exploration networks (REN), to jointly perform representation learning and effective exploration in the latent space. REN tries to balance relevance and exploration while taking into account the uncertainty in the representations. Our theoretical analysis shows that REN can preserve the rate-optimal sublinear regret even when there exists uncertainty in the learned representations. Our empirical study demonstrates that REN can achieve satisfactory long-term rewards on both synthetic and real-world recommendation datasets, outperforming state-of-the-art models.

cs.LG↗

arXiv2022

Constrained Optimization Involving Nonconvex $\ell_p$ Norms: Optimality Conditions, Algorithm and Convergence

This paper investigates the optimality conditions for characterizing the local minimizers of the constrained optimization problems involving an $\ell_p$ norm ($0<p<1$) of the variables, which may appear in either the objective or the constraint. This kind of problems have strong applicability to a wide range of areas since usually the $\ell_p$ norm can promote sparse solutions. However, the nonsmooth and non-Lipschtiz nature of the $\ell_p$ norm often cause these problems difficult to analyze and solve. We provide the calculation of the subgradients of the $\ell_p$ norm and the normal cones of the $\ell_p$ ball. For both problems, we derive the first-order necessary conditions under various constraint qualifications. We also derive the sequential optimality conditions for both problems and study the conditions under which these conditions imply the first-order necessary conditions. We point out that the sequential optimality conditions can be easily satisfied for iteratively reweighted algorithms and show that the global convergence can be easily derived using sequential optimality conditions.

math.OC↗

arXiv2022

Privacy protection based on mask template

Powerful recognition algorithms are widely used in the Internet or important medical systems, which poses a serious threat to personal privacy. Although the law provides for diversity protection, e.g. The General Data Protection Regulation (GDPR) in Europe and Articles 1032 to 1039 of the civil code in China. However, as an important privacy disclosure event, biometric data is often hidden, which is difficult for the owner to detect and trace to the source. Human biometrics generally exist in images. In order to avoid the disclosure of personal privacy, we should prevent unauthorized recognition algorithms from acquiring the real features of the original image.

cs.CR↗

arXiv2022

Application of Color Block Code in Image Scaling

Aiming at the high cost of embedding annotation watermark in a narrow small area and the information distortion caused by the change of annotation watermark image resolution, this paper proposes a color block code technology, which uses location information and color code to form recognizable graphics, which can not only simplify the annotation graphics, but also ensure the recognition efficiency. First, the constituent elements of color block code are designed, and then the coding and decoding method of color block code is proposed. Experiments show that color block code has high anti-scaling and anti-interference, and can be widely used in the labeling of small object surface and low resolution image.

cs.GR↗

arXiv2022

ABG: A Multi-Party Mixed Protocol Framework for Privacy-Preserving Cooperative Learning

Cooperative learning, that enables two or more data owners to jointly train a model, has been widely adopted to solve the problem of insufficient training data in machine learning. Nowadays, there is an urgent need for institutions and organizations to train a model cooperatively while keeping each other's data privately. To address the issue of privacy-preserving in collaborative learning, secure outsourced computation and federated learning are two typical methods. Nevertheless, there are many drawbacks for these two methods when they are leveraged in cooperative learning. For secure outsourced computation, semi-honest servers need to be introduced. Once the outsourced servers collude or perform other active attacks, the privacy of data will be disclosed. For federated learning, it is difficult to apply to the scenarios where vertically partitioned data are distributed over multiple parties. In this work, we propose a multi-party mixed protocol framework, ABG$^n$, which effectively implements arbitrary conversion between Arithmetic sharing (A), Boolean sharing (B) and Garbled-Circuits sharing (G) for $n$-party scenarios. Based on ABG$^n$, we design a privacy-preserving multi-party cooperative learning system, which allows different data owners to cooperate in machine learning in terms of data security and privacy-preserving. Additionally, we design specific privacy-preserving computation protocols for some typical machine learning methods such as logistic regression and neural networks. Compared with previous work, the proposed method has a wider scope of application and does not need to rely on additional servers. Finally, we evaluate the performance of ABG$^n$ on the local setting and on the public cloud setting. The experiments indicate that ABG$^n$ has excellent performance, especially in the network environment with low latency.

cs.CR↗

arXiv2022

Temporal Logic Guided Motion Primitives for Complex Manipulation Tasks with User Preferences

Dynamic movement primitives (DMPs) are a flexible trajectory learning scheme widely used in motion generation of robotic systems. However, existing DMP-based methods mainly focus on simple go-to-goal tasks. Motivated to handle tasks beyond point-to-point motion planning, this work presents temporal logic guided optimization of motion primitives, namely PIBB-TL algorithm, for complex manipulation tasks with user preferences. In particular, weighted truncated linear temporal logic (wTLTL) is incorporated in the PIBB-TL algorithm, which not only enables the encoding of complex tasks that involve a sequence of logically organized action plans with user preferences, but also provides a convenient and efficient means to design the cost function. The black-box optimization is then adapted to identify optimal shape parameters of DMPs to enable motion planning of robotic systems. The effectiveness of the PIBB-TL algorithm is demonstrated via simulation and experime

cs.RO↗

arXiv2022

Hyperparameter-free and Explainable Whole Graph Embedding

Graphs can be used to describe complex systems. Recently, whole graph embedding (graph representation learning) can compress a graph into a compact lower-dimension vector while preserving intrinsic properties, earning much attention. However, most graph embedding methods have problems such as tedious parameter tuning or poor explanation. This paper presents a simple and hyperparameter-free whole graph embedding method based on the DHC (Degree, H-index, and Coreness) theorem and Shannon Entropy (E), abbreviated as DHC-E. The DHC-E can provide a trade-off between simplicity and quality for supervised classification learning tasks involving molecular, social, and brain networks. Moreover, it performs well in lower-dimensional graph visualization. Overall, the DHC-E is simple, hyperparameter-free, and explainable for whole graph embedding with promising potential for exploring graph classification and lower-dimensional graph visualization.

cs.LG↗

arXiv2022

Adaptive 3D descattering with a dynamic synthesis network

Deep learning has been broadly applied to imaging in scattering applications. A common framework is to train a descattering network for image recovery by removing scattering artifacts. To achieve the best results on a broad spectrum of scattering conditions, individual "expert" networks need to be trained for each condition. However, the expert's performance sharply degrades when the testing condition differs from the training. An alternative brute-force approach is to train a "generalist" network using data from diverse scattering conditions. It generally requires a larger network to encapsulate the diversity in the data and a sufficiently large training set to avoid overfitting. Here, we propose an adaptive learning framework, termed dynamic synthesis network (DSN), which dynamically adjusts the model weights and adapts to different scattering conditions. The adaptability is achieved by a novel "mixture of experts" architecture that enables dynamically synthesizing a network by blending multiple experts using a gating network. We demonstrate the DSN in holographic 3D particle imaging for a variety of scattering conditions. We show in simulation that our DSN provides generalization across a continuum of scattering conditions. In addition, we show that by training the DSN entirely on simulated data, the network can generalize to experiments and achieve robust 3D descattering. We expect the same concept can find many other applications, such as denoising and imaging in scattering media. Broadly, our dynamic synthesis framework opens up a new paradigm for designing highly adaptive deep learning and computational imaging techniques.

eess.IV↗

arXiv2022

Evidence for mechanical softening-hardening dual anomaly in transition metals from shock compressed vanadium

Solid usually becomes harder and tougher under compression, and turns softer at elevated temperature. Recently, compression-induced softening and heating-induced hardening (CISHIH) dual anomaly was predicted in group VB elements such as vanadium. Here, the evidence for this counterintuitive phenomenon is reported. By using accurate high-temperature high-pressure sound velocities measured at Hugoniot states generated by shock-waves, together with first-principles calculations, we observe not only the prominent compression-induced sound velocity reduction, but also strong heating-induced sound velocity enhancement, in shocked vanadium. The former corresponds to the softening in shear modulus by compression, whereas the latter reflects the reverse hardening by heat. These experiments also unveil another anomaly in Young's modulus that wasn't reported before. Based on the experimental and theoretical data, we infer that vanadium might transition from BCC into two different rhombohedral (RH1 and RH2) phases at about 79GPa and 116GPa along the Hugoniot, respectively, which implies a dramatic difference in static and dynamic loading, as well as the significance of deviatoric stress and rate-relevant effects in high-pressure phase transition dynamics.

cond-mat.mtrl-sci↗

arXiv2022

Improved normal-boundary intersection algorithm: a method for energy optimization strategy in smart buildings

With the widespread use of distributed energy sources, the advantages of smart buildings over traditional buildings are becoming increasingly obvious. Subsequently, its energy optimal scheduling and multi-objective optimization have become more and more complex and need to be solved urgently. This paper presents a novel method to optimize energy utilization in smart buildings. Firstly, multiple transfer-retention ratio (TRR) parameters are added to the evaluation of distributed renewable energy. Secondly, the normal-boundary intersection (NBI) algorithm is improved by the adaptive weight sum, the adjust uniform axes method, and Mahalanobis distance to form the improved normal-boundary intersection (INBI) algorithm. The multi-objective optimization problem in smart buildings is solved by the parameter TRR and INBI algorithm to improve the regulation efficiency. In response to the needs of decision-makers with evaluation indicators, the average deviation is reduced by 60% compared with the previous case. Numerical examples show that the proposed method is superior to the existing technologies in terms of three optimization objectives. The objectives include 8.2% reduction in equipment costs, 7.6% reduction in power supply costs, and 1.6% improvement in occupants' comfort.

eess.SY↗

arXiv2022

High-order Photonic Cavity Modes Enabled 3D Structural Color

It remains a challenge to directly print three-dimensional arbitrary shapes that exhibit structural colors at the micrometer scale. Woodpile photonic crystals (WPCs) fabricated via two-photon lithography (TPL) are promising as building blocks to produce 3D geometries that generate structural colors due to their ability to exhibit either omnidirectional or anisotropic photonic stopbands. However, existing approaches have focused on achieving structural colors when illuminating WPCs from the top, which necessitates print resolutions beyond the limit of commercial TPL and/or post-processing techniques. Here, we devised a new strategy to support high-order photonic cavity modes upon side-illumination on WPCs that surprisingly generate large reflectance peaks in the visible spectrum. Based on that, we demonstrate one-step printing of 3D photonic structural colors without requiring post-processing or subwavelength features. Vivid colors with reflectance peaks exhibiting a full width at half maximum of ~25 nm, a maximum reflectance of 50%, gamut of ~85% of sRGB, and large viewing angles, were achieved. In addition, we also demonstrated voxel-level manipulation and control of colors in arbitrary-shaped 3D objects constituted with WPCs as unit cells, which has great potential for applications in dynamic color displays, colorimetric sensing, anti-counterfeiting, and light-matter interaction platforms.

physics.optics↗

arXiv2022

Mutations make pandemics worse or better: modeling SARS-CoV-2 variants and imperfect vaccination

Since December 2020, variants of COVID-19 (especially Delta and Omicron) appeared with different characteristics that influenced death and transmissibility emerged around the world. To address the novel dynamics of the disease, we propose a dynamical model of two strains, namely native and mutant, transmission dynamics with mutation and imperfect vaccination. It is also assumed that the recuperated individuals from the native strain can be infected with mutant strain through the direct contact with individual or contaminated surfaces or aerosols. We compute the basic reproduction number for each strain independently and take the maximum for $R_0$. We prove the nonexistence of backward bifurcation using the center manifold theory, and global stability of disease-free equilibrium when the basic reproduction number $R_0<1. An intermediate mutation rate $ν_1$ leads to oscillations. When $ν_1$ increases over a threshold, the system regains its stability and exhibits an interesting dynamics called endemic bubble. An analytical expression for vaccine-induced herd immunity is derived. The model is parameterized using the Indian data of the cumulative number of confirmed cases and deaths of COVID-19 from March 1 to September 27 in 2021, using MCMC method. The cumulative cases and deaths can be reduced by increasing the vaccine efficacies to both native and mutant strains. We observe that by considering the vaccine efficacy to native strain as 90\%, the cumulative cases and deaths would be reduced by 3.27\% and 5.2\%, respectively; and by considering the vaccine efficacy to mutant strain as 90\%, the cumulative cases and deaths would be reduced by 0.9\% and 2.5\%, respectively. Our study demonstrates that the COVID-19 pandemic may be worse due to the occurrence of oscillations for certain mutation rates but better due to stability at a lower infection level with a larger mutation rate.

q-bio.PE↗

arXiv2022

Efficient Data-Plane Memory Scheduling for In-Network Aggregation

As the scale of distributed training grows, communication becomes a bottleneck. To accelerate the communication, recent works introduce In-Network Aggregation (INA), which moves the gradients summation into network middle-boxes, e.g., programmable switches to reduce the traffic volume. However, switch memory is scarce compared to the volume of gradients transmitted in distributed training. Although literature applies methods like pool-based streaming or dynamic sharing to tackle the mismatch, switch memory is still a potential performance bottleneck. Furthermore, we observe the under-utilization of switch memory due to the synchronization requirement for aggregator deallocation in recent works. To improve the switch memory utilization, we propose ESA, an $\underline{E}$fficient Switch Memory $\underline{S}$cheduler for In-Network $\underline{A}$ggregation. At its cores, ESA enforces the preemptive aggregator allocation primitive and introduces priority scheduling at the data-plane, which improves the switch memory utilization and average job completion time (JCT). Experiments show that ESA can improve the average JCT by up to $1.35\times$.

cs.DC↗

arXiv2022

From policy to prediction: Forecasting COVID-19 dynamics under imperfect vaccination

Understanding the joint impact of vaccination and non-pharmaceutical interventions on COVID-19 development is important for making public health decisions that control the pandemic. Recently, we created a method in forecasting the daily number of confirmed cases of infectious diseases by combining a mechanistic ordinary differential equation (ODE) model for infectious classes and a generalized boosting machine learning model (GBM) for predicting how public health policies and mobility data affect the transmission rate in the ODE model [WWR+]. In this paper, we extend the method to the post-vaccination period, accordingly obtain a retrospective forecast of COVID-19 daily confirmed cases in the US, and identify the relative influence of the policies used as the predictor variables. In particular, our ODE model contains both partially and fully vaccinated compartments and accounts for the breakthrough cases, that is, vaccinated individuals can still get infected. Our results indicate that the inclusion of data on non-pharmaceutical interventions can significantly improve the accuracy of the predictions. With the use of policy data, the model predicts the number of daily infected cases up to 35 days in the future, with an average mean absolute percentage error of 34%, which is further improved to 21% if combined with human mobility data. Moreover, similar to the pre-vaccination study, the most influential predictor variable remains the policy of restrictions on gatherings. The modeling approach used in this work can help policymakers design control measures as variant strains threaten public health in the future.

q-bio.QM↗

arXiv2022

A Fisher-KPP model with a nonlocal weighted free boundary: analysis of how habitat boundaries expand, balance or shrink

In this paper, we propose a novel free boundary problem to model the movement of single species with a range boundary. The spatial movement and birth/death processes of the species found within the range boundary are assumed to be governed by the classic Fisher-KPP reaction-diffusion equation, while the movement of a free boundary describing the range limit is assumed to be influenced by the weighted total population inside the range boundary and is described by an integro-differential equation. Our free boundary equation is a generalization of the classical Stefan problem that allows for nonlocal influences on the boundary movement so that range expansion and shrinkage are both possible. In this paper we prove that the new model is well posed and possesses steady state. We show that the spreading speed of the range boundary is smaller than that for the equivalent problem with a Stefan condition. This implies that the nonlocal effect of the weighted total population on the boundary movement slows down the spreading speed of the population. While the classical Stefan condition categorizes asymptotic behavior via a spreading-vanishing dichotomy, the new model extends this dichotomy to a spreading-balancing-vanishing trichotomy. We specifically analyze how habitat boundaries expand, balance or shrink. When the model is extended to have two free boundaries, we observe the steady state scenario, asymmetric shifts, or even boundaries moving synchronously in the same direction. These are newly discovered phenomena in the free boundary problems for animal movement.

math.AP↗

arXiv2022

Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogate

Uncertainty estimation is an essential step in the evaluation of the robustness for deep learning models in computer vision, especially when applied in risk-sensitive areas. However, most state-of-the-art deep learning models either fail to obtain uncertainty estimation or need significant modification (e.g., formulating a proper Bayesian treatment) to obtain it. Most previous methods are not able to take an arbitrary model off the shelf and generate uncertainty estimation without retraining or redesigning it. To address this gap, we perform a systematic exploration into training-free uncertainty estimation for dense regression, an unrecognized yet important problem, and provide a theoretical construction justifying such estimations. We propose three simple and scalable methods to analyze the variance of outputs from a trained network under tolerable perturbations: infer-transformation, infer-noise, and infer-dropout. They operate solely during the inference, without the need to re-train, re-design, or fine-tune the models, as typically required by state-of-the-art uncertainty estimation methods. Surprisingly, even without involving such perturbations in training, our methods produce comparable or even better uncertainty estimation when compared to training-required state-of-the-art methods.

cs.CV↗

arXiv2022

Electromagnetic Vortex Topologies from Sparse Circular Phased Arrays

Structured vortex waves have numerous applications in optics, plasmonics, radio-wave technologies and acoustics. We present a theoretical study of a method for generating vortex states based on coherent superposition of waves from discrete elements of planar phased arrays, given limitations on an element number. Using Jacobi-Anger expansion, we analyze emerging vortex topologies and derive a constraint for the least number of elements needed to generate a vortex with a given leading-order topological charge.

physics.class-ph↗