arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 1,423 records · Page 79Linked to original sources

arXiv2021

A Novel Mathematical Model for Infrastructure Planning of Dynamic Wireless Power Transfer Systems for Electric Vehicles

About 26% of total U.S. energy consumption is used in the transportation sector. Conventional vehicles use fuels such as gasoline, emit harmful gases, and have adverse effects on the environment. Electric vehicles (EVs) provide an alternative solution that decreases the dependency on traditional fuels such as gasoline and reduces hazardous gas emissions. EVs can drive longer distances by employing dynamic wireless power transfer systems (DWPT) without increasing their battery size or having stopovers. Additionally, developing a decision system that avoids an excessive load on the power grid is essential. These decision systems are particularly beneficial for autonomous driving for personal and public transportation. This study briefly reviews the available literature in dynamic wireless power transfer systems and proposes a novel system-level mathematical decision model to find the optimal profile for wireless charging infrastructures. We analyze the role of renewable energy integration on DWPT systems and identify the framework, benefits, and challenges in implementing DWPT for EVs. The mathematical model is mixed-integer, multi-period, and linear, minimizing the total system cost while satisfying the systems requirements. The proposed model and the case study analysis in this research determine the near-optimal plan for DWPT infrastructure allocations and pave the road toward a more detailed power grid and renewable energy integration. Our result indicates that renewable energies can significantly decrease the DWPT total system cost, infrastructure requirements and increase the EVs' reliability. Keywords: Dynamic wireless power transfer, Renewable energy integration, Electric vehicles, Power grid planning, Wireless charging allocation, Infrastructure planning, Mixed-integer optimization.

eess.SY↗

arXiv2021

STRODE: Stochastic Boundary Ordinary Differential Equation

Perception of time from sequentially acquired sensory inputs is rooted in everyday behaviors of individual organisms. Yet, most algorithms for time-series modeling fail to learn dynamics of random event timings directly from visual or audio inputs, requiring timing annotations during training that are usually unavailable for real-world applications. For instance, neuroscience perspectives on postdiction imply that there exist variable temporal ranges within which the incoming sensory inputs can affect the earlier perception, but such temporal ranges are mostly unannotated for real applications such as automatic speech recognition (ASR). In this paper, we present a probabilistic ordinary differential equation (ODE), called STochastic boundaRy ODE (STRODE), that learns both the timings and the dynamics of time series data without requiring any timing annotations during training. STRODE allows the usage of differential equations to sample from the posterior point processes, efficiently and analytically. We further provide theoretical guarantees on the learning of STRODE. Our empirical results show that our approach successfully infers event timings of time series data. Our method achieves competitive or superior performances compared to existing state-of-the-art methods for both synthetic and real-world datasets.

cs.LG↗

arXiv2021

Schrodinger's Red Pixel by Quasi Bound-State-In-Continuum

While structural colors are ubiquitous in nature, saturated reds are mysteriously absent. Hence, a longstanding problem is in fabricating nanostructured surfaces that exhibit reflectance approaching the theoretical limit. This limit is termed the Schrodinger red and demands sharp spectral transitions from "stopband" to a high reflectance "passband" with total suppression of higher-order resonances at blue and green wavelengths. Current approaches based on metallic or dielectric nanoantennas are insufficient to simultaneously meet these conditions. Here, for the 1st time, we designed and fabricated tall Si nanoantenna arrays on quartz substrate to support two partially overlapping y polarized quasi bound-state-in-the-continuum (q-BIC) modes in the red wavelengths with sharp spectral edges. These structures produce possibly the most saturated and brightest reds with ~80% reflectance, exceeding the red vertex in sRGB and even the cadmium red pigment. We employed a gradient descent algorithm with structures supporting q BIC as the starting point. Although the current design is polarization dependent, the proposed paradigm has enabled us to achieve the elusive structural red and the design principle could be generalized to Schrodinger's pixels of other colors. The design is suitable for scale up using other nanofabrication techniques for larger area applications, such as red pixels in displays, decorative coatings, and miniaturized spectrometers with high wavelength selectivity.

physics.optics↗

arXiv2021

Domain-Smoothing Network for Zero-Shot Sketch-Based Image Retrieval

Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) is a novel cross-modal retrieval task, where abstract sketches are used as queries to retrieve natural images under zero-shot scenario. Most existing methods regard ZS-SBIR as a traditional classification problem and employ a cross-entropy or triplet-based loss to achieve retrieval, which neglect the problems of the domain gap between sketches and natural images and the large intra-class diversity in sketches. Toward this end, we propose a novel Domain-Smoothing Network (DSN) for ZS-SBIR. Specifically, a cross-modal contrastive method is proposed to learn generalized representations to smooth the domain gap by mining relations with additional augmented samples. Furthermore, a category-specific memory bank with sketch features is explored to reduce intra-class diversity in the sketch domain. Extensive experiments demonstrate that our approach notably outperforms the state-of-the-art methods in both Sketchy and TU-Berlin datasets. Our source code is publicly available at https://github.com/haowang1992/DSN.

cs.CV↗

arXiv2021

Enhancing Question Generation with Commonsense Knowledge

Question generation (QG) is to generate natural and grammatical questions that can be answered by a specific answer for a given context. Previous sequence-to-sequence models suffer from a problem that asking high-quality questions requires commonsense knowledge as backgrounds, which in most cases can not be learned directly from training data, resulting in unsatisfactory questions deprived of knowledge. In this paper, we propose a multi-task learning framework to introduce commonsense knowledge into question generation process. We first retrieve relevant commonsense knowledge triples from mature databases and select triples with the conversion information from source context to question. Based on these informative knowledge triples, we design two auxiliary tasks to incorporate commonsense knowledge into the main QG model, where one task is Concept Relation Classification and the other is Tail Concept Generation. Experimental results on SQuAD show that our proposed methods are able to noticeably improve the QG performance on both automatic and human evaluation metrics, demonstrating that incorporating external commonsense knowledge with multi-task learning can help the model generate human-like and high-quality questions.

cs.CL↗

arXiv2021

Correcting Exposure Bias for Link Recommendation

Link prediction methods are frequently applied in recommender systems, e.g., to suggest citations for academic papers or friends in social networks. However, exposure bias can arise when users are systematically underexposed to certain relevant items. For example, in citation networks, authors might be more likely to encounter papers from their own field and thus cite them preferentially. This bias can propagate through naively trained link predictors, leading to both biased evaluation and high generalization error (as assessed by true relevance). Moreover, this bias can be exacerbated by feedback loops. We propose estimators that leverage known exposure probabilities to mitigate this bias and consequent feedback loops. Next, we provide a loss function for learning the exposure probabilities from data. Finally, experiments on semi-synthetic data based on real-world citation networks, show that our methods reliably identify (truly) relevant citations. Additionally, our methods lead to greater diversity in the recommended papers' fields of study. The code is available at https://github.com/shantanu95/exposure-bias-link-rec.

cs.LG↗

arXiv2021

DMBGN: Deep Multi-Behavior Graph Networks for Voucher Redemption Rate Prediction

In E-commerce, vouchers are important marketing tools to enhance users' engagement and boost sales and revenue. The likelihood that a user redeems a voucher is a key factor in voucher distribution decision. User-item Click-Through-Rate (CTR) models are often applied to predict the user-voucher redemption rate. However, the voucher scenario involves more complicated relations among users, items and vouchers. The users' historical behavior in a voucher collection activity reflects users' voucher usage patterns, which is nevertheless overlooked by the CTR-based solutions. In this paper, we propose a Deep Multi-behavior Graph Networks (DMBGN) to shed light on this field for the voucher redemption rate prediction. The complex structural user-voucher-item relationships are captured by a User-Behavior Voucher Graph (UVG). User behavior happening both before and after voucher collection is taken into consideration, and a high-level representation is extracted by Higher-order Graph Neural Networks. On top of a sequence of UVGs, an attention network is built which can help to learn users' long-term voucher redemption preference. Extensive experiments on three large-scale production datasets demonstrate the proposed DMBGN model is effective, with 10% to 16% relative AUC improvement over Deep Neural Networks (DNN), and 2% to 4% AUC improvement over Deep Interest Network (DIN). Source code and a sample dataset are made publicly available to facilitate future research.

cs.IR↗

arXiv2021

Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion

Aiming at expanding few-shot relations' coverage in knowledge graphs (KGs), few-shot knowledge graph completion (FKGC) has recently gained more research interests. Some existing models employ a few-shot relation's multi-hop neighbor information to enhance its semantic representation. However, noise neighbor information might be amplified when the neighborhood is excessively sparse and no neighbor is available to represent the few-shot relation. Moreover, modeling and inferring complex relations of one-to-many (1-N), many-to-one (N-1), and many-to-many (N-N) by previous knowledge graph completion approaches requires high model complexity and a large amount of training instances. Thus, inferring complex relations in the few-shot scenario is difficult for FKGC models due to limited training instances. In this paper, we propose a few-shot relational learning with global-local framework to address the above issues. At the global stage, a novel gated and attentive neighbor aggregator is built for accurately integrating the semantics of a few-shot relation's neighborhood, which helps filtering the noise neighbors even if a KG contains extremely sparse neighborhoods. For the local stage, a meta-learning based TransH (MTransH) method is designed to model complex relations and train our model in a few-shot learning fashion. Extensive experiments show that our model outperforms the state-of-the-art FKGC approaches on the frequently-used benchmark datasets NELL-One and Wiki-One. Compared with the strong baseline model MetaR, our model achieves 5-shot FKGC performance improvements of 8.0% on NELL-One and 2.8% on Wiki-One by the metric Hits@10.

cs.AI↗

arXiv2021

GraphMI: Extracting Private Graph Data from Graph Neural Networks

As machine learning becomes more widely used for critical applications, the need to study its implications in privacy turns to be urgent. Given access to the target model and auxiliary information, the model inversion attack aims to infer sensitive features of the training dataset, which leads to great privacy concerns. Despite its success in grid-like domains, directly applying model inversion techniques on non-grid domains such as graph achieves poor attack performance due to the difficulty to fully exploit the intrinsic properties of graphs and attributes of nodes used in Graph Neural Networks (GNN). To bridge this gap, we present \textbf{Graph} \textbf{M}odel \textbf{I}nversion attack (GraphMI), which aims to extract private graph data of the training graph by inverting GNN, one of the state-of-the-art graph analysis tools. Specifically, we firstly propose a projected gradient module to tackle the discreteness of graph edges while preserving the sparsity and smoothness of graph features. Then we design a graph auto-encoder module to efficiently exploit graph topology, node attributes, and target model parameters for edge inference. With the proposed methods, we study the connection between model inversion risk and edge influence and show that edges with greater influence are more likely to be recovered. Extensive experiments over several public datasets demonstrate the effectiveness of our method. We also show that differential privacy in its canonical form can hardly defend our attack while preserving decent utility.

cs.LG↗

arXiv2021

Blockchain for Transactive Energy Management of Distributed Energy Resources in Smart Grid

This work presents the design and implementation of a blockchain system that enables the trustable transactive energy management for distributed energy resources (DERs). We model the interactions among DERs, including energy trading and flexible appliance scheduling, as a cost minimization problem. Considering the dispersed nature and diverse ownership of DERs, we develop a distributed algorithm to solve the optimization problem using the alternating direction method of multipliers (ADMM) method. Furthermore, we develop a blockchain system, on which we implement the proposed algorithm with the smart contract, to guarantee the transparency and correctness of the energy management. We prototype the blockchain in a small-scale test network and evaluate it through experiments using real-world data. The experimental results validate the feasibility and effectiveness of our design.

cs.DC↗

arXiv2021

Characterizing Residential Load Patterns by Household Demographic and Socioeconomic Factors

The wide adoption of smart meters makes residential load data available and thus improves the understanding of the energy consumption behavior. Many existing studies have focused on smart-meter data analysis, but the drivers of energy consumption behaviors are not well understood. This paper aims to characterize and estimate users' load patterns based on their demographic and socioeconomic information. We adopt the symbolic aggregate approximation (SAX) method to process the load data and use the K-Means method to extract key load patterns. We develop a deep neural network (DNN) to analyze the relationship between users' load patterns and their demographic and socioeconomic features. Using real-world load data, we validate our framework and demonstrate the connections between load patterns and household demographic and socioeconomic features. We also take two regression models as benchmarks for comparisons.

cs.LG↗

arXiv2021

Smart Online Charging Algorithm for Electric Vehicles via Customized Actor-Critic Learning

With the advances in the Internet of Things technology, electric vehicles (EVs) have become easier to schedule in daily life, which is reshaping the electric load curve. It is important to design efficient charging algorithms to mitigate the negative impact of EV charging on the power grid. This paper investigates an EV charging scheduling problem to reduce the charging cost while shaving the peak charging load, under unknown future information about EVs, such as arrival time, departure time, and charging demand. First, we formulate an EV charging problem to minimize the electricity bill of the EV fleet and study the EV charging problem in an online setting without knowing future information. We develop an actor-critic learning-based smart charging algorithm (SCA) to schedule the EV charging against the uncertainties in EV charging behaviors. The SCA learns an optimal EV charging strategy with continuous charging actions instead of discrete approximation of charging. We further develop a more computationally efficient customized actor-critic learning charging algorithm (CALC) by reducing the state dimension and thus improving the computational efficiency. Finally, simulation results show that our proposed SCA can reduce EVs' expected cost by 24.03%, 21.49%, 13.80%, compared with the Eagerly Charging Algorithm, Online Charging Algorithm, RL-based Adaptive Energy Management Algorithm, respectively. CALC is more computationally efficient, and its performance is close to that of SCA with only a gap of 5.56% in the cost.

eess.SY↗

arXiv2021

When Homomorphic Encryption Marries Secret Sharing: Secure Large-Scale Sparse Logistic Regression and Applications in Risk Control

Logistic Regression (LR) is the most widely used machine learning model in industry for its efficiency, robustness, and interpretability. Due to the problem of data isolation and the requirement of high model performance, many applications in industry call for building a secure and efficient LR model for multiple parties. Most existing work uses either Homomorphic Encryption (HE) or Secret Sharing (SS) to build secure LR. HE based methods can deal with high-dimensional sparse features, but they incur potential security risks. SS based methods have provable security, but they have efficiency issue under high-dimensional sparse features. In this paper, we first present CAESAR, which combines HE and SS to build secure large-scale sparse logistic regression model and achieves both efficiency and security. We then present the distributed implementation of CAESAR for scalability requirement. We have deployed CAESAR in a risk control task and conducted comprehensive experiments. Our experimental results show that CAESAR improves the state-of-the-art model by around 130 times.

cs.CR↗

arXiv2021

Blockchain-Based Decentralized Energy Management Platform for Residential Distributed Energy Resources in A Virtual Power Plant

The advent of distributed energy resources (DERs), such as distributed renewables, energy storage, electric vehicles, and controllable loads, \rv{brings} a significantly disruptive and transformational impact on the centralized power system. It is widely accepted that a paradigm shift to a decentralized power system with bidirectional power flow is necessary to the integration of DERs. The virtual power plant (VPP) emerges as a promising paradigm for managing DERs to participate in the power system. In this paper, we develop a blockchain-based VPP energy management platform to facilitate a rich set of transactive energy activities among residential users with renewables, energy storage, and flexible loads in a VPP. Specifically, users can interact with each other to trade energy for mutual benefits and provide network services, such as feed-in energy, reserve, and demand response, through the VPP. To respect the users' independence and preserve their privacy, we design a decentralized optimization algorithm to optimize the users' energy scheduling, energy trading, and network services. Then we develop a prototype blockchain network for VPP energy management and implement the proposed algorithm on the blockchain network. By experiments using real-world data-trace, we validated the feasibility and effectiveness of our algorithm and the blockchain system. The simulation results demonstrate that our blockchain-based VPP energy management platform reduces the users' cost by up to 38.6% and reduces the overall system cost by 11.2%.

eess.SY↗

arXiv2021

Distributed Energy Trading Management for Renewable Prosumers with HVAC and Energy Storage

Heating, ventilating, and air-conditioning (HVAC) systems consume a large amount of energy in residential houses and buildings. Effective energy management of HVAC is a cost-effective way to improve energy efficiency and reduce the energy cost of residential users. This work develops a novel distributed method for the residential transactive energy system that enables multiple users to interactively optimize their energy management of HVAC systems and behind-the-meter batteries. Specifically, this method effectively reduces the cost of smart homes by employing energy trading among users to leverage their power usage flexibility without compromising the users' privacy. To achieve this goal, we design a distributed optimization algorithm based on the alternating direction method of multipliers (ADMM) to automatically operate the HVAC system and batteries, which minimizes the energy costs of users. Specifically, we decouple the optimization problem into a primal subproblem and a dual subproblem. The primal subproblem is solved by the users, and the dual subproblem is solved by the grid operator. Unlike the existing centralized method, our approach only uses the users' private information locally for solving the primal subproblem hence preserves the users' privacy. Using real-world data, we validate our proposed algorithm through extensive simulations in Matlab. The results demonstrate that our method effectively incentivizes the energy trading among the users to reduce users' peak load and reduce the overall energy cost of the system by 23% on average.

eess.SY↗

arXiv2021

Deep High-Resolution Representation Learning for Cross-Resolution Person Re-identification

Person re-identification (re-ID) tackles the problem of matching person images with the same identity from different cameras. In practical applications, due to the differences in camera performance and distance between cameras and persons of interest, captured person images usually have various resolutions. We name this problem as Cross-Resolution Person Re-identification which brings a great challenge for matching correctly. In this paper, we propose a Deep High-Resolution Pseudo-Siamese Framework (PS-HRNet) to solve the above problem. Specifically, in order to restore the resolution of low-resolution images and make reasonable use of different channel information of feature maps, we introduce and innovate VDSR module with channel attention (CA) mechanism, named as VDSR-CA. Then we reform the HRNet by designing a novel representation head to extract discriminating features, named as HRNet-ReID. In addition, a pseudo-siamese framework is constructed to reduce the difference of feature distributions between low-resolution images and high-resolution images. The experimental results on five cross-resolution person datasets verify the effectiveness of our proposed approach. Compared with the state-of-the-art methods, our proposed PS-HRNet improves 3.4\%, 6.2\%, 2.5\%,1.1\% and 4.2\% at Rank-1 on MLR-Market-1501, MLR-CUHK03, MLR-VIPeR, MLR-DukeMTMC-reID, and CAVIAR datasets, respectively. Our code is available at \url{https://github.com/zhguoqing}.

cs.CV↗

arXiv2021

Large-scale holographic particle 3D imaging with the beam propagation model

We develop a novel algorithm for large-scale holographic reconstruction of 3D particle fields. Our method is based on a multiple-scattering beam propagation method (BPM) combined with sparse regularization that enables recovering dense 3D particles of high refractive index contrast from a single hologram. We show that the BPM-computed hologram generates intensity statistics closely matching with the experimental measurements and provides up to 9$\times$ higher accuracy than the single-scattering model. To solve the inverse problem, we devise a computationally efficient algorithm, which reduces the computation time by two orders of magnitude as compared to the state-of-the-art multiple-scattering-based technique. We demonstrate superior reconstruction accuracy in both simulations and experiments under different scattering strengths. We show that the BPM reconstruction significantly outperforms the single-scattering method in particular for deep imaging depths and high particle densities.

physics.optics↗

arXiv2021

KECRS: Towards Knowledge-Enriched Conversational Recommendation System

The chit-chat-based conversational recommendation systems (CRS) provide item recommendations to users through natural language interactions. To better understand user's intentions, external knowledge graphs (KG) have been introduced into chit-chat-based CRS. However, existing chit-chat-based CRS usually generate repetitive item recommendations, and they cannot properly infuse knowledge from KG into CRS to generate informative responses. To remedy these issues, we first reformulate the conversational recommendation task to highlight that the recommended items should be new and possibly interested by users. Then, we propose the Knowledge-Enriched Conversational Recommendation System (KECRS). Specifically, we develop the Bag-of-Entity (BOE) loss and the infusion loss to better integrate KG with CRS for generating more diverse and informative responses. BOE loss provides an additional supervision signal to guide CRS to learn from both human-written utterances and KG. Infusion loss bridges the gap between the word embeddings and entity embeddings by minimizing distances of the same words in these two embeddings. Moreover, we facilitate our study by constructing a high-quality KG, \ie The Movie Domain Knowledge Graph (TMDKG). Experimental results on a large-scale dataset demonstrate that KECRS outperforms state-of-the-art chit-chat-based CRS, in terms of both recommendation accuracy and response generation quality.

cs.CL↗