arXiv subjects

Xiao Huang

Publications and source records attributed to Xiao Huang.

At least 145 records · Page 8Linked to original sources

arXiv2021

A Bioinspired Approach-Sensitive Neural Network for Collision Detection in Cluttered and Dynamic Backgrounds

Rapid, accurate and robust detection of looming objects in cluttered moving backgrounds is a significant and challenging problem for robotic visual systems to perform collision detection and avoidance tasks. Inspired by the neural circuit of elementary motion vision in the mammalian retina, this paper proposes a bioinspired approach-sensitive neural network (ASNN) that contains three main contributions. Firstly, a direction-selective visual processing module is built based on the spatiotemporal energy framework, which can estimate motion direction accurately via only two mutually perpendicular spatiotemporal filtering channels. Secondly, a novel approach-sensitive neural network is modeled as a push-pull structure formed by ON and OFF pathways, which responds strongly to approaching motion while insensitivity to lateral motion. Finally, a method of directionally selective inhibition is introduced, which is able to suppress the translational backgrounds effectively. Extensive synthetic and real robotic experiments show that the proposed model is able to not only detect collision accurately and robustly in cluttered and dynamic backgrounds but also extract more collision information like position and direction, for guiding rapid decision making.

cs.RO↗

arXiv2021

Measuring Global Multi-Scale Place Connectivity using Geotagged Social Media Data

Shaped by human movement, place connectivity is quantified by the strength of spatial interactions among locations. For decades, spatial scientists have researched place connectivity, applications, and metrics. The growing popularity of social media provides a new data stream where spatial social interaction measures are largely devoid of privacy issues, easily assessable, and harmonized. In this study, we introduced a global multi-scale place connectivity index (PCI) based on spatial interactions among places revealed by geotagged tweets as a spatiotemporal-continuous and easy-to-implement measurement. The multi-scale PCI, demonstrated at the US county level, exhibits a strong positive association with SafeGraph population movement records (10 percent penetration in the US population) and Facebook's social connectedness index (SCI), a popular connectivity index based on social networks. We found that PCI has a strong boundary effect and that it generally follows the distance decay, although this force is weaker in more urbanized counties with a denser population. Our investigation further suggests that PCI has great potential in addressing real-world problems that require place connectivity knowledge, exemplified with two applications: 1) modeling the spatial spread of COVID-19 during the early stage of the pandemic and 2) modeling hurricane evacuation destination choice. The methodological and contextual knowledge of PCI, together with the launched visualization platform and open-sourced PCI datasets at various geographic levels, are expected to support research fields requiring knowledge in human spatial interactions.

cs.SI↗

arXiv2021

Dynamic Memory based Attention Network for Sequential Recommendation

Sequential recommendation has become increasingly essential in various online services. It aims to model the dynamic preferences of users from their historical interactions and predict their next items. The accumulated user behavior records on real systems could be very long. This rich data brings opportunities to track actual interests of users. Prior efforts mainly focus on making recommendations based on relatively recent behaviors. However, the overall sequential data may not be effectively utilized, as early interactions might affect users' current choices. Also, it has become intolerable to scan the entire behavior sequence when performing inference for each user, since real-world system requires short response time. To bridge the gap, we propose a novel long sequential recommendation model, called Dynamic Memory-based Attention Network (DMAN). It segments the overall long behavior sequence into a series of sub-sequences, then trains the model and maintains a set of memory blocks to preserve long-term interests of users. To improve memory fidelity, DMAN dynamically abstracts each user's long-term interest into its own memory blocks by minimizing an auxiliary reconstruction loss. Based on the dynamic memory, the user's short-term and long-term interests can be explicitly extracted and combined for efficient joint recommendation. Empirical results over four benchmark datasets demonstrate the superiority of our model in capturing long-term dependency over various state-of-the-art sequential models.

cs.IR↗

arXiv2021

On developing piecewise rational mapping with fine regulation capability for WENO schemes

On the idea of mapped WENO-JS scheme, properties of mapping methods are analyzed, uncertainties in mapping development are investigated, and new rational mappings are proposed. Based on our former understandings, i.e. mapping at endpoints {0, 1} tending to identity mapping, an integrated Cm,n condition is summarized for function development. Uncertainties, i.e., whether the mapping at endpoints would make mapped scheme behave like WENO or ENO, whether piecewise implementation would entail numerical instability, and whether WENO3-JS could preserve the third-order at first-order critical points by mapping, are analyzed and clarified. A new piecewise rational mapping with sufficient regulation capability is developed afterwards, where the flatness of mapping around the linear weights and its endpoint convergence toward identity mapping can be coordinated explicitly and simultaneously. Hence, the increase of resolution and preservation of stability can be balanced. Especially, concrete mappings are determined for WENO3,5,7-JS. Numerical cases are tested for the new mapped WENO-JS, which regards numerical stability including that in long time computation, resolution and robustness. In purpose of comparison, some recent mappings such as IM by [App. Math. Comput. 232, 2014:453-468], RM by [J. Sci. Comput. 67, 2016:540-580] and AIM by [J. Comput. Phys. 381, 2019:162-188] are chosen; in addition, some recent WENO-Z type scheme are selected also. Proposed new schemes can preserve optimal orders at corresponding critical points, achieve numerical stability and indicate overall comparative advantages regarding accuracy, resolution and robustness.

math.NA↗

arXiv2021

Covariate Balancing Based on Kernel Density Estimates for Controlled Experiments

Controlled experiments are widely used in many applications to investigate the causal relationship between input factors and experimental outcomes. A completely randomized design is usually used to randomly assign treatment levels to experimental units. When covariates of the experimental units are available, the experimental design should achieve covariate balancing among the treatment groups, such that the statistical inference of the treatment effects is not confounded with any possible effects of covariates. However, covariate imbalance often exists, because the experiment is carried out based on a single realization of the complete randomization. It is more likely to occur and worsen when the size of the experimental units is small or moderate. In this paper, we introduce a new covariate balancing criterion, which measures the differences between kernel density estimates of the covariates of treatment groups. To achieve covariate balance before the treatments are randomly assigned, we partition the experimental units by minimizing the criterion, then randomly assign the treatment levels to the partitioned groups. Through numerical examples, we show that the proposed partition approach can improve the accuracy of the difference-in-mean estimator and outperforms the complete randomization and rerandomization approaches.

stat.ME↗

arXiv2020

ODT Flow Explorer: Extract, Query, and Visualize Human Mobility

Understanding human mobility dynamics among places provides fundamental knowledge regarding their interactive gravity, benefiting a wide range of applications in need of prior knowledge in human spatial interactions. The ongoing COVID-19 pandemic uniquely highlights the need for monitoring and measuring fine-scale human spatial interactions. In response to the soaring needs of human mobility data under the pandemic, we developed an interactive geospatial web portal by extracting worldwide daily population flows from billions of geotagged tweets and United States (U.S.) population flows from SafeGraph mobility data. The web portal is named ODT (Origin-Destination-Time) Flow Explorer. At the core of the explorer is an ODT data cube coupled with a big data computing cluster to efficiently manage, query, and aggregate billions of OD flows at different spatial and temporal scales. Although the explorer is still in its early developing stage, the rapidly generated mobility flow data can benefit a wide range of domains that need timely access to the fine-grained human mobility records. The ODT Flow Explorer can be accessed via http://gis.cas.sc.edu/GeoAnalytics/od.html.

cs.SI↗

arXiv2020

Teaching Machine Comprehension with Compositional Explanations

Advances in machine reading comprehension (MRC) rely heavily on the collection of large scale human-annotated examples in the form of (question, paragraph, answer) triples. In contrast, humans are typically able to generalize with only a few examples, relying on deeper underlying world knowledge, linguistic sophistication, and/or simply superior deductive powers. In this paper, we focus on "teaching" machines reading comprehension, using a small number of semi-structured explanations that explicitly inform machines why answer spans are correct. We extract structured variables and rules from explanations and compose neural module teachers that annotate instances for training downstream MRC models. We use learnable neural modules and soft logic to handle linguistic variation and overcome sparse coverage; the modules are jointly optimized with the MRC model to improve final performance. On the SQuAD dataset, our proposed method achieves 70.14% F1 score with supervision from 26 explanations, comparable to plain supervised learning using 1,100 labeled instances, yielding a 12x speed up.

cs.CL↗

arXiv2020

Simulating multi-exit evacuation using deep reinforcement learning

Conventional simulations on multi-exit indoor evacuation focus primarily on how to determine a reasonable exit based on numerous factors in a changing environment. Results commonly include some congested and other under-utilized exits, especially with massive pedestrians. We propose a multi-exit evacuation simulation based on Deep Reinforcement Learning (DRL), referred to as the MultiExit-DRL, which involves in a Deep Neural Network (DNN) framework to facilitate state-to-action mapping. The DNN framework applies Rainbow Deep Q-Network (DQN), a DRL algorithm that integrates several advanced DQN methods, to improve data utilization and algorithm stability, and further divides the action space into eight isometric directions for possible pedestrian choices. We compare MultiExit-DRL with two conventional multi-exit evacuation simulation models in three separate scenarios: 1) varying pedestrian distribution ratios, 2) varying exit width ratios, and 3) varying open schedules for an exit. The results show that MultiExit-DRL presents great learning efficiency while reducing the total number of evacuation frames in all designed experiments. In addition, the integration of DRL allows pedestrians to explore other potential exits and helps determine optimal directions, leading to the high efficiency of exit utilization.

cs.LG↗

arXiv2020

TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition

Training neural models for named entity recognition (NER) in a new domain often requires additional human annotations (e.g., tens of thousands of labeled instances) that are usually expensive and time-consuming to collect. Thus, a crucial research question is how to obtain supervision in a cost-effective way. In this paper, we introduce "entity triggers," an effective proxy of human explanations for facilitating label-efficient learning of NER models. An entity trigger is defined as a group of words in a sentence that helps to explain why humans would recognize an entity in the sentence. We crowd-sourced 14k entity triggers for two well-studied NER datasets. Our proposed model, Trigger Matching Network, jointly learns trigger representations and soft matching module with self-attention such that can generalize to unseen sentences easily for tagging. Our framework is significantly more cost-effective than the traditional neural NER frameworks. Experiments show that using only 20% of the trigger-annotated sentences results in a comparable performance as using 70% of conventional annotated sentences.

cs.CL↗

arXiv2020

A GRU-based Mixture Density Network for Data-Driven Dynamic Stochastic Programming

The conventional deep learning approaches for solving time-series problem such as long-short term memory (LSTM) and gated recurrent unit (GRU) both consider the time-series data sequence as the input with one single unit as the output (predicted time-series result). Those deep learning approaches have made tremendous success in many time-series related problems, however, this cannot be applied in data-driven stochastic programming problems since the output of either LSTM or GRU is a scalar rather than probability distribution which is required by stochastic programming model. To fill the gap, in this work, we propose an innovative data-driven dynamic stochastic programming (DD-DSP) framework for time-series decision-making problem, which involves three components: GRU, Gaussian Mixture Model (GMM) and SP. Specifically, we devise the deep neural network that integrates GRU and GMM which is called GRU-based Mixture Density Network (MDN), where GRU is used to predict the time-series outcomes based on the recent historical data, and GMM is used to extract the corresponding probability distribution of predicted outcomes, then the results will be input as the parameters for SP. To validate our approach, we apply the framework on the car-sharing relocation problem. The experiment validations show that our framework is superior to data-driven optimization based on LSTM with the vehicle average moving lower than LSTM.

eess.SP↗

arXiv2020

Twitter, human mobility, and COVID-19

The outbreak of COVID-19 highlights the need for a more harmonized, less privacy-concerning, easily accessible approach to monitoring the human mobility that has been proved to be associated with the viral transmission. In this study, we analyzed 587 million tweets worldwide to see how global collaborative efforts in reducing human mobility are reflected from the user-generated information at the global, country, and the U.S. state scale. Considering the multifaceted nature of mobility, we propose two types of distance: the single-day distance and the cross-day distance. To quantify the responsiveness in certain geographical regions, we further propose a mobility-based responsive index (MRI) that captures the overall degree of mobility changes within a time window. The results suggest that mobility patterns obtained from Twitter data are amendable to quantitatively reflect the mobility dynamics. Globally, the proposed two distances had greatly deviated from their baselines after March 11, 2020, when WHO declared COVID-19 as a pandemic. The considerably less periodicity after the declaration suggests that the protection measures have obviously affected people's travel routines. The country scale comparisons reveal the discrepancies in responsiveness, evidenced by the contrasting mobility patterns in different epidemic phases. We find that the triggers of mobility changes correspond well with the national announcements of mitigation measures. In the U.S., the influence of the COVID-19 pandemic on mobility is distinct. However, the impacts varied substantially among states. The strong mobility recovering momentum is further fueled by the Black Lives Matter protests, potentially fostering the second wave of infections in the U.S.

cs.SI↗

arXiv2020

Towards Deeper Graph Neural Networks with Differentiable Group Normalization

Graph neural networks (GNNs), which learn the representation of a node by aggregating its neighbors, have become an effective computational tool in downstream applications. Over-smoothing is one of the key issues which limit the performance of GNNs as the number of layers increases. It is because the stacked aggregators would make node representations converge to indistinguishable vectors. Several attempts have been made to tackle the issue by bringing linked node pairs close and unlinked pairs distinct. However, they often ignore the intrinsic community structures and would result in sub-optimal performance. The representations of nodes within the same community/class need be similar to facilitate the classification, while different classes are expected to be separated in embedding space. To bridge the gap, we introduce two over-smoothing metrics and a novel technique, i.e., differentiable group normalization (DGN). It normalizes nodes within the same group independently to increase their smoothness, and separates node distributions among different groups to significantly alleviate the over-smoothing issue. Experiments on real-world datasets demonstrate that DGN makes GNN models more robust to over-smoothing and achieves better performance with deeper GNNs.

cs.LG↗

arXiv2020

Learning to Contextually Aggregate Multi-Source Supervision for Sequence Labeling

Sequence labeling is a fundamental framework for various natural language processing problems. Its performance is largely influenced by the annotation quality and quantity in supervised learning scenarios, and obtaining ground truth labels is often costly. In many cases, ground truth labels do not exist, but noisy annotations or annotations from different domains are accessible. In this paper, we propose a novel framework Consensus Network (ConNet) that can be trained on annotations from multiple sources (e.g., crowd annotation, cross-domain data...). It learns individual representation for every source and dynamically aggregates source-specific knowledge by a context-aware attention module. Finally, it leads to a model reflecting the agreement (consensus) among multiple sources. We evaluate the proposed framework in two practical settings of multi-source learning: learning with crowd annotations and unsupervised cross-domain model adaptation. Extensive experimental results show that our model achieves significant improvements over existing methods in both settings. We also demonstrate that the method can apply to various tasks and cope with different encoders.

cs.CL↗

arXiv2020

DDKSP: A Data-Driven Stochastic Programming Framework for Car-Sharing Relocation Problem

Car-sharing issue is a popular research field in sharing economy. In this paper, we investigate the car-sharing relocation problem (CSRP) under uncertain demands. Normally, the real customer demands follow complicating probability distribution which cannot be described by parametric approaches. In order to overcome the problem, an innovative framework called Data-Driven Kernel Stochastic Programming (DDKSP) that integrates a non-parametric approach - kernel density estimation (KDE) and a two-stage stochastic programming (SP) model is proposed. Specifically, the probability distributions are derived from historical data by KDE, which are used as the input uncertain parameters for SP. Additionally, the CSRP is formulated as a two-stage SP model. Meanwhile, a Monte Carlo method called sample average approximation (SAA) and Benders decomposition algorithm are introduced to solve the large-scale optimization model. Finally, the numerical experimental validations which are based on New York taxi trip data sets show that the proposed framework outperforms the pure parametric approaches including Gaussian, Laplace and Poisson distributions with 3.72% , 4.58% and 11% respectively in terms of overall profits.

math.OC↗

arXiv2019

Translating multispectral imagery to nighttime imagery via conditional generative adversarial networks

Nighttime satellite imagery has been applied in a wide range of fields. However, our limited understanding of how observed light intensity is formed and whether it can be simulated greatly hinders its further application. This study explores the potential of conditional Generative Adversarial Networks (cGAN) in translating multispectral imagery to nighttime imagery. A popular cGAN framework, pix2pix, was adopted and modified to facilitate this translation using gridded training image pairs derived from Landsat 8 and Visible Infrared Imaging Radiometer Suite (VIIRS). The results of this study prove the possibility of multispectral-to-nighttime translation and further indicate that, with the additional social media data, the generated nighttime imagery can be very similar to the ground-truth imagery. This study fills the gap in understanding the composition of satellite observed nighttime light and provides new paradigms to solve the emerging problems in nighttime remote sensing fields, including nighttime series construction, light desaturation, and multi-sensor calibration.

cs.CV↗

arXiv2019

Multi-Channel Graph Convolutional Networks

Graph neural networks (GNN) has been demonstrated to be effective in classifying graph structures. To further improve the graph representation learning ability, hierarchical GNN has been explored. It leverages the differentiable pooling to cluster nodes into fixed groups, and generates a coarse-grained structure accompanied with the shrinking of the original graph. However, such clustering would discard some graph information and achieve the suboptimal results. It is because the node inherently has different characteristics or roles, and two non-isomorphic graphs may have the same coarse-grained structure that cannot be distinguished after pooling. To compensate the loss caused by coarse-grained clustering and further advance GNN, we propose a multi-channel graph convolutional networks (MuchGCN). It is motivated by the convolutional neural networks, at which a series of channels are encoded to preserve the comprehensive characteristics of the input image. Thus, we define the specific graph convolutions to learn a series of graph channels at each layer, and pool graphs iteratively to encode the hierarchical structures. Experiments have been carefully carried out to demonstrate the superiority of MuchGCN over the state-of-the-art graph classification algorithms.

cs.SI↗

arXiv2019

SpecAE: Spectral AutoEncoder for Anomaly Detection in Attributed Networks

Anomaly detection aims to distinguish observations that are rare and different from the majority. While most existing algorithms assume that instances are i.i.d., in many practical scenarios, links describing instance-to-instance dependencies and interactions are available. Such systems are called attributed networks. Anomaly detection in attributed networks has various applications such as monitoring suspicious accounts in social media and financial fraud in transaction networks. However, it remains a challenging task since the definition of anomaly becomes more complicated and topological structures are heterogeneous with nodal attributes. In this paper, we propose a spectral convolution and deconvolution based framework -- SpecAE, to project the attributed network into a tailored space to detect global and community anomalies. SpecAE leverages Laplacian sharpening to amplify the distances between representations of anomalies and the ones of the majority. The learned representations along with reconstruction errors are combined with a density estimation model to perform the detection. They are trained jointly as an end-to-end framework. Experiments on real-world datasets demonstrate the effectiveness of SpecAE.

cs.LG↗

arXiv2019

Learning A Unified Named Entity Tagger From Multiple Partially Annotated Corpora For Efficient Adaptation

Named entity recognition (NER) identifies typed entity mentions in raw text. While the task is well-established, there is no universally used tagset: often, datasets are annotated for use in downstream applications and accordingly only cover a small set of entity types relevant to a particular task. For instance, in the biomedical domain, one corpus might annotate genes, another chemicals, and another diseases---despite the texts in each corpus containing references to all three types of entities. In this paper, we propose a deep structured model to integrate these "partially annotated" datasets to jointly identify all entity types appearing in the training corpora. By leveraging multiple datasets, the model can learn robust input representations; by building a joint structured model, it avoids potential conflicts caused by combining several models' predictions at test time. Experiments show that the proposed model significantly outperforms strong multi-task learning baselines when training on multiple, partially annotated datasets and testing on datasets that contain tags from more than one of the training corpora.

cs.CL↗