Searcharxiv⌕ Search

arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 1,441 records · Page 80Linked to original sources
arXiv2021

Describing traveler choice behavior using the free utility model

Travel demand forecasting is an essential part of transportation planning and management. The four-step travel model is the traditional and most-common procedure utilized for travel demand forecasting, and many models have been proposed in the literature to describe each step separately. However, there is still a lack of a unified modeling framework that can successfully describe the collective choice behavior of travelers interacting with each other at different steps. This study uses the free utility model, whose objective function is mathematically consistent with the Helmholtz free energy in physics, to separately and simultaneously describe travelers' mode, destination, and route choice behaviors. The free utility model's basic assumption is that the travelers will trade off the expected utility and information-processing cost to maximize their own utility. This model provides not only a unified modeling framework for traveler choice behavior, but also provides a new perspective for understanding the user equilibrium model in transportation science and the potential game model in game theory.

physics.soc-ph↗
arXiv2021

Quantifying the Impact of Boundary Constraint Handling Methods on Differential Evolution

Constraint handling is one of the most influential aspects of applying metaheuristics to real-world applications, which can hamper the search progress if treated improperly. In this work, we focus on a particular case - the box constraints, for which many boundary constraint handling methods (BCHMs) have been proposed. We call for the necessity of studying the impact of BCHMs on metaheuristics' performance and behavior, which receives seemingly little attention in the field. We target quantifying such impacts through systematic benchmarking by investigating 28 major variants of Differential Evolution (DE) taken from the modular DE framework (by combining different mutation and crossover operators) and $13$ commonly applied BCHMs, resulting in $28 \times 13 = 364$ algorithm instances after pairing DE variants with BCHMs. After executing the algorithm instances on the well-known BBOB/COCO problem set, we analyze the best-reached objective function value (performance-wise) and the percentage of repaired solutions (behavioral) using statistical ranking methods for each combination of mutation, crossover, and BBOB function group. Our results clearly show that the choice of BCHMs substantially affects the empirical performance as well as the number of generated infeasible solutions, which allows us to provide general guidelines for selecting an appropriate BCHM for a given scenario.

cs.NE↗
arXiv2021

Delving into Deep Imbalanced Regression

Real-world data often exhibit imbalanced distributions, where certain target values have significantly fewer observations. Existing techniques for dealing with imbalanced data focus on targets with categorical indices, i.e., different classes. However, many tasks involve continuous targets, where hard boundaries between classes do not exist. We define Deep Imbalanced Regression (DIR) as learning from such imbalanced data with continuous targets, dealing with potential missing data for certain target values, and generalizing to the entire target range. Motivated by the intrinsic difference between categorical and continuous label space, we propose distribution smoothing for both labels and features, which explicitly acknowledges the effects of nearby targets, and calibrates both label and learned feature distributions. We curate and benchmark large-scale DIR datasets from common real-world tasks in computer vision, natural language processing, and healthcare domains. Extensive experiments verify the superior performance of our strategies. Our work fills the gap in benchmarks and techniques for practical imbalanced regression problems. Code and data are available at https://github.com/YyzHarry/imbalanced-regression.

cs.LG↗
arXiv2021

Covariance Matrix Adaptation Evolution Strategy Assisted by Principal Component Analysis

Over the past decades, more and more methods gain a giant development due to the development of technology. Evolutionary Algorithms are widely used as a heuristic method. However, the budget of computation increases exponentially when the dimensions increase. In this paper, we will use the dimensionality reduction method Principal component analysis (PCA) to reduce the dimension during the iteration of Covariance Matrix Adaptation Evolution Strategy (CMA-ES), which is a good Evolutionary Algorithm that is presented as the numeric type and useful for different kinds of problems. We assess the performance of our new methods in terms of convergence rate on multi-modal problems from the Black-Box Optimization Benchmarking (BBOB) problem set and we also use the framework COmparing Continuous Optimizers (COCO) to see how the new method going and compare it to the other algorithms.

cs.NE↗
arXiv2021

Learning to Ask Appropriate Questions in Conversational Recommendation

Conversational recommender systems (CRSs) have revolutionized the conventional recommendation paradigm by embracing dialogue agents to dynamically capture the fine-grained user preference. In a typical conversational recommendation scenario, a CRS firstly generates questions to let the user clarify her/his demands and then makes suitable recommendations. Hence, the ability to generate suitable clarifying questions is the key to timely tracing users' dynamic preferences and achieving successful recommendations. However, existing CRSs fall short in asking high-quality questions because: (1) system-generated responses heavily depends on the performance of the dialogue policy agent, which has to be trained with huge conversation corpus to cover all circumstances; and (2) current CRSs cannot fully utilize the learned latent user profiles for generating appropriate and personalized responses. To mitigate these issues, we propose the Knowledge-Based Question Generation System (KBQG), a novel framework for conversational recommendation. Distinct from previous conversational recommender systems, KBQG models a user's preference in a finer granularity by identifying the most relevant relations from a structured knowledge graph (KG). Conditioned on the varied importance of different relations, the generated clarifying questions could perform better in impelling users to provide more details on their preferences. Finially, accurate recommendations can be generated in fewer conversational turns. Furthermore, the proposed KBQG outperforms all baselines in our experiments on two real-world datasets.

cs.AI↗
arXiv2021

Speech2Slot: An End-to-End Knowledge-based Slot Filling from Speech

In contrast to conventional pipeline Spoken Language Understanding (SLU) which consists of automatic speech recognition (ASR) and natural language understanding (NLU), end-to-end SLU infers the semantic meaning directly from speech and overcomes the error propagation caused by ASR. End-to-end slot filling (SF) from speech is an essential component of end-to-end SLU, and is usually regarded as a sequence-to-sequence generation problem, heavily relied on the performance of language model of ASR. However, it is hard to generate a correct slot when the slot is out-of-vovabulary (OOV) in training data, especially when a slot is an anti-linguistic entity without grammatical rule. Inspired by object detection in computer vision that is to detect the object from an image, we consider SF as the task of slot detection from speech. In this paper, we formulate the SF task as a matching task and propose an end-to-end knowledge-based SF model, named Speech-to-Slot (Speech2Slot), to leverage knowledge to detect the boundary of a slot from the speech. We also release a large-scale dataset of Chinese speech for slot filling, containing more than 830,000 samples. The experiments show that our approach is markedly superior to the conventional pipeline SLU approach, and outperforms the state-of-the-art end-to-end SF approach with 12.51% accuracy improvement.

cs.CL↗
arXiv2021

Is there Anisotropy in Structural Bias?

Structural Bias (SB) is an important type of algorithmic deficiency within iterative optimisation heuristics. However, methods for detecting structural bias have not yet fully matured, and recent studies have uncovered many interesting questions. One of these is the question of how structural bias can be related to anisotropy. Intuitively, an algorithm that is not isotropic would be considered structurally biased. However, there have been cases where algorithms appear to only show SB in some dimensions. As such, we investigate whether these algorithms actually exhibit anisotropy, and how this impacts the detection of SB. We find that anisotropy is very rare, and even in cases where it is present, there are clear tests for SB which do not rely on any assumptions of isotropy, so we can safely expand the suite of SB tests to encompass these kinds of deficiencies not found by the original tests. We propose several additional testing procedures for SB detection and aim to motivate further research into the creation of a robust portfolio of tests. This is crucial since no single test will be able to work effectively with all types of SB we identify.

stat.ME↗
arXiv2021

Bayesian Neural Architecture Search using A Training-Free Performance Metric

Recurrent neural networks (RNNs) are a powerful approach for time series prediction. However, their performance is strongly affected by their architecture and hyperparameter settings. The architecture optimization of RNNs is a time-consuming task, where the search space is typically a mixture of real, integer and categorical values. To allow for shrinking and expanding the size of the network, the representation of architectures often has a variable length. In this paper, we propose to tackle the architecture optimization problem with a variant of the Bayesian Optimization (BO) algorithm. To reduce the evaluation time of candidate architectures the Mean Absolute Error Random Sampling (MRS), a training-free method to estimate the network performance, is adopted as the objective function for BO. Also, we propose three fixed-length encoding schemes to cope with the variable-length architecture representation. The result is a new perspective on accurate and efficient design of RNNs, that we validate on three problems. Our findings show that 1) the BO algorithm can explore different network architectures using the proposed encoding schemes and successfully designs well-performing architectures, and 2) the optimization time is significantly reduced by using MRS, without compromising the performance as compared to the architectures obtained from the actual training procedure.

cs.LG↗
arXiv2021

Explorative Data Analysis of Time Series based AlgorithmFeatures of CMA-ES Variants

In this study, we analyze behaviours of the well-known CMA-ES by extracting the time-series features on its dynamic strategy parameters. An extensive experiment was conducted on twelve CMA-ES variants and 24 test problems taken from the BBOB (Black-Box Optimization Bench-marking) testbed, where we used two different cutoff times to stop those variants. We utilized the tsfresh package for extracting the features and performed the feature selection procedure using the Boruta algorithm, resulting in 32 features to distinguish either CMA-ES variants or the problems. After measuring the number of predefined targets reached by those variants, we contrive to predict those measured values on each test problem using the feature. From our analysis, we saw that the features can classify the CMA-ES variants, or the function groups decently, and show a potential for predicting the performance of those variants. We conducted a hierarchical clustering analysis on the test problems and noticed a drastic change in the clustering outcome when comparing the longer cutoff time to the shorter one, indicating a huge change in search behaviour of the algorithm. In general, we found that with longer time series, the predictive power of the time series features increase.

cs.NE↗
arXiv2021

Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning

With the ubiquitous graph-structured data in various applications, models that can learn compact but expressive vector representations of nodes have become highly desirable. Recently, bearing the message passing paradigm, graph neural networks (GNNs) have greatly advanced the performance of node representation learning on graphs. However, a majority class of GNNs are only designed for homogeneous graphs, leading to inferior adaptivity to the more informative heterogeneous graphs with various types of nodes and edges. Also, despite the necessity of inductively producing representations for completely new nodes (e.g., in streaming scenarios), few heterogeneous GNNs can bypass the transductive learning scheme where all nodes must be known during training. Furthermore, the training efficiency of most heterogeneous GNNs has been hindered by their sophisticated designs for extracting the semantics associated with each meta path or relation. In this paper, we propose WIde and DEep message passing Network (WIDEN) to cope with the aforementioned problems about heterogeneity, inductiveness, and efficiency that are rarely investigated together in graph representation learning. In WIDEN, we propose a novel inductive, meta path-free message passing scheme that packs up heterogeneous node features with their associated edges from both low- and high-order neighbor nodes. To further improve the training efficiency, we innovatively present an active downsampling strategy that drops unimportant neighbor nodes to facilitate faster information propagation. Experiments on three real-world heterogeneous graphs have further validated the efficacy of WIDEN on both transductive and inductive node representation learning, as well as the superior training efficiency against state-of-the-art baselines.

cs.SI↗
arXiv2021

An Iteratively Reweighted Method for Sparse Optimization on Nonconvex $\ell_{p}$ Ball

This paper is intended to solve the nonconvex $\ell_{p}$-ball constrained nonlinear optimization problems. An iteratively reweighted method is proposed, which solves a sequence of weighted $\ell_{1}$-ball projection subproblems. At each iteration, the next iterate is obtained by moving along the negative gradient with a stepsize and then projecting the resulted point onto the weighted $\ell_{1}$ ball to approximate the $\ell_{p}$ ball. Specifically, if the current iterate is in the interior of the feasible set, then the weighted $\ell_{1}$ ball is formed by linearizing the $\ell_{p}$ norm at the current iterate. If the current iterate is on the boundary of the feasible set, then the weighted $\ell_{1}$ ball is formed differently by keeping those zero components in the current iterate still zero. In our analysis, we prove that the generated iterates converge to a first-order stationary point. Numerical experiments demonstrate the effectiveness of the proposed method.

math.OC↗
arXiv2021

High-resolution light field prints by nanoscale 3D printing

A light field print (LFP) displays three-dimensional (3D) information to the naked-eye observer under ambient white light illumination. Changing perspectives of a 3D image are seen by the observer from varying angles. However, LFPs appear pixelated due to limited resolution and misalignment between their lenses and colour pixels. A promising solution to create high-resolution LFPs is through the use of advanced nanofabrication techniques. Here, we use two-photon polymerization lithography as a one-step nanoscale 3D printer to directly fabricate LFPs out of transparent resin. This approach produces simultaneously high spatial resolution (29 - 45 μm) and high angular resolution (~ 1.6 °) images with smooth motion parallax across 15 {\times} 15 views. Notably, the smallest colour pixel consists of only a single nanopillar (~ 300 nm diameter). Our LFP signifies a step towards hyper-realistic 3D images that can be applied in print media and security tags for high-value goods.

physics.optics↗
arXiv2021

Scene Text Retrieval via Joint Text Detection and Similarity Learning

Scene text retrieval aims to localize and search all text instances from an image gallery, which are the same or similar to a given query text. Such a task is usually realized by matching a query text to the recognized words, outputted by an end-to-end scene text spotter. In this paper, we address this problem by directly learning a cross-modal similarity between a query text and each text instance from natural images. Specifically, we establish an end-to-end trainable network, jointly optimizing the procedures of scene text detection and cross-modal similarity learning. In this way, scene text retrieval can be simply performed by ranking the detected text instances with the learned similarity. Experiments on three benchmark datasets demonstrate our method consistently outperforms the state-of-the-art scene text spotting/retrieval approaches. In particular, the proposed framework of joint detection and similarity learning achieves significantly better performance than separated methods. Code is available at: https://github.com/lanfeng4659/STR-TDSL.

cs.CV↗
arXiv2021

Generative Interventions for Causal Learning

We introduce a framework for learning robust visual representations that generalize to new viewpoints, backgrounds, and scene contexts. Discriminative models often learn naturally occurring spurious correlations, which cause them to fail on images outside of the training distribution. In this paper, we show that we can steer generative models to manufacture interventions on features caused by confounding factors. Experiments, visualizations, and theoretical results show this method learns robust representations more consistent with the underlying causal relationships. Our approach improves performance on multiple datasets demanding out-of-distribution generalization, and we demonstrate state-of-the-art performance generalizing from ImageNet to ObjectNet dataset.

cs.CV↗
arXiv2021

Any Part of Bayesian Network Structure Learning

We study an interesting and challenging problem, learning any part of a Bayesian network (BN) structure. In this challenge, it will be computationally inefficient using existing global BN structure learning algorithms to find an entire BN structure to achieve the part of a BN structure in which we are interested. And local BN structure learning algorithms encounter the false edge orientation problem when they are directly used to tackle this challenging problem. In this paper, we first present a new concept of Expand-Backtracking to explain why local BN structure learning methods have the false edge orientation problem, then propose APSL, an efficient and accurate Any Part of BN Structure Learning algorithm. Specifically, APSL divides the V-structures in a Markov blanket (MB) into two types: collider V-structure and non-collider V-structure, then it starts from a node of interest and recursively finds both collider V-structures and non-collider V-structures in the found MBs, until the part of a BN structure in which we are interested are oriented. To improve the efficiency of APSL, we further design the APSL-FS algorithm using Feature Selection, APSL-FS. Using six benchmark BNs, the extensive experiments have validated the efficiency and accuracy of our methods.

cs.LG↗
arXiv2021

Exploring Blockchain for The Coordination of Distributed Energy Resources

The fast growth of distributed energy resources (DERs), such as distributed renewables (e.g., rooftop PV panels), energy storage systems, electric vehicles, and controllable appliances, drives the power system toward a decentralized system with bidirectional power flow. The coordination of DERs through an aggregator, such as a utility, system operator, or a third-party coordinator, emerges as a promising paradigm. However, it is not well understood how to enable trust between the aggregator and DERs to integrate DERs efficiently. In this paper, we develop a trustable and distributed coordination system for DERs using blockchain technology. We model various DERs and formulate a cost minimization problem for DERs to optimize their energy trading, scheduling, and demand response. We use the alternating direction method of multipliers (ADMM) to solve the problem in a distributed fashion. To implement the distributed algorithm in a trustable way, we design a smart contract to update multipliers and communicate with DERs in a blockchain network. We validate our design by experiments using real-world data, and the simulation results demonstrate the effectiveness of our algorithm.

cs.DC↗
arXiv2021

Cooperative Energy Management of HVAC via Transactive Energy

Heating, Ventilation, and Air Conditioning (HVAC) energy consumption accounts for a significant part of the total energy consumption of buildings and households. The ubiquitous adoption of distributed renewable energy and smart meters helps to decarbonize the HVAC energy consumption and improve energy efficiency. However, how to scale up HVAC energy management for a group of users while persevering users' privacy remains a big challenge. In this work, we utilize the concept of transactive energy to build a cooperative energy management system for independent HVAC units in a distributed manner. Specifically, we develop a distributed energy trading algorithm that consists of two layers based on the alternating direction method of multipliers method. The distributed energy trading algorithm achieves optimal trading performance and also preserves users' privacy. Furthermore, we evaluate the performance of the distributed trading algorithm by extensive simulations with real-world data. Simulation results show that the energy trading algorithm converges fast and the cooperative energy platform reduces the user's individual cost by up to 50% and lowers the overall cost of all users by 23%.

eess.SY↗