Searcharxiv⌕ Search

arXiv subjects

Bin Guo

Publications and source records attributed to Bin Guo.

At least 163 records · Page 9Linked to original sources
arXiv2021

DeepExpress: Heterogeneous and Coupled Sequence Modeling for Express Delivery Prediction

The prediction of express delivery sequence, i.e., modeling and estimating the volumes of daily incoming and outgoing parcels for delivery, is critical for online business, logistics, and positive customer experience, and specifically for resource allocation optimization and promotional activity arrangement. A precise estimate of consumer delivery requests has to involve sequential factors such as shopping behaviors, weather conditions, events, business campaigns, and their couplings. Besides, conventional sequence prediction assumes a stable sequence evolution, failing to address complex nonlinear sequences and various feature effects in the above multi-source data. Although deep networks and attention mechanisms demonstrate the potential of complex sequence modeling, extant networks ignore the heterogeneous and coupling situation between features and sequences, resulting in weak prediction accuracy. To address these issues, we propose DeepExpress - a deep-learning based express delivery sequence prediction model, which extends the classic seq2seq framework to learning complex coupling between sequence and features. DeepExpress leverages an express delivery seq2seq learning, a carefully-designed heterogeneous feature representation, and a novel joint training attention mechanism to adaptively map heterogeneous data, and capture sequence-feature coupling for precise estimation. Experimental results on real-world data demonstrate that the proposed method outperforms both shallow and deep baseline models.

cs.LG↗
arXiv2021

Decentralized Multi-AGV Task Allocation based on Multi-Agent Reinforcement Learning with Information Potential Field Rewards

Automated Guided Vehicles (AGVs) have been widely used for material handling in flexible shop floors. Each product requires various raw materials to complete the assembly in production process. AGVs are used to realize the automatic handling of raw materials in different locations. Efficient AGVs task allocation strategy can reduce transportation costs and improve distribution efficiency. However, the traditional centralized approaches make high demands on the control center's computing power and real-time capability. In this paper, we present decentralized solutions to achieve flexible and self-organized AGVs task allocation. In particular, we propose two improved multi-agent reinforcement learning algorithms, MADDPG-IPF (Information Potential Field) and BiCNet-IPF, to realize the coordination among AGVs adapting to different scenarios. To address the reward-sparsity issue, we propose a reward shaping strategy based on information potential field, which provides stepwise rewards and implicitly guides the AGVs to different material targets. We conduct experiments under different settings (3 AGVs and 6 AGVs), and the experiment results indicate that, compared with baseline methods, our work obtains up to 47\% task response improvement and 22\% training iterations reduction.

cs.RO↗
arXiv2021

TL-SDD: A Transfer Learning-Based Method for Surface Defect Detection with Few Samples

Surface defect detection plays an increasingly important role in manufacturing industry to guarantee the product quality. Many deep learning methods have been widely used in surface defect detection tasks, and have been proven to perform well in defects classification and location. However, deep learning-based detection methods often require plenty of data for training, which fail to apply to the real industrial scenarios since the distribution of defect categories is often imbalanced. In other words, common defect classes have many samples but rare defect classes have extremely few samples, and it is difficult for these methods to well detect rare defect classes. To solve the imbalanced distribution problem, in this paper we propose TL-SDD: a novel Transfer Learning-based method for Surface Defect Detection. First, we adopt a two-phase training scheme to transfer the knowledge from common defect classes to rare defect classes. Second, we propose a novel Metric-based Surface Defect Detection (M-SDD) model. We design three modules for this model: (1) feature extraction module: containing feature fusion which combines high-level semantic information with low-level structural information. (2) feature reweighting module: transforming examples to a reweighting vector that indicates the importance of features. (3) distance metric module: learning a metric space in which defects are classified by computing distances to representations of each category. Finally, we validate the performance of our proposed method on a real dataset including surface defects of aluminum profiles. Compared to the baseline methods, the performance of our proposed method has improved by up to 11.98% for rare defect classes.

cs.CV↗
arXiv2021

MetaDetector: Meta Event Knowledge Transfer for Fake News Detection

The blooming of fake news on social networks has devastating impacts on society, economy, and public security. Although numerous studies are conducted for the automatic detection of fake news, the majority tend to utilize deep neural networks to learn event-specific features for superior detection performance on specific datasets. However, the trained models heavily rely on the training datasets and are infeasible to apply to upcoming events due to the discrepancy between event distributions. Inspired by domain adaptation theories, we propose an end-to-end adversarial adaptation network, dubbed as MetaDetector, to transfer meta knowledge (event-shared features) between different events. Specifically, MetaDetector pushes the feature extractor and event discriminator to eliminate event-specific features and preserve required event-shared features by adversarial training. Furthermore, the pseudo-event discriminator is utilized to evaluate the importance of historical event posts to obtain partial shared features that are discriminative for detecting fake news. Under the coordinated optimization among the four submodules, MetaDetector accurately transfers the meta-knowledge of historical events to the upcoming event for fact checking. We conduct extensive experiments on two large-scale datasets collected from Weibo and Twitter. The experimental results demonstrate that MetaDetector outperforms the state-of-the-art methods, especially when the distribution shift between events is significant. Furthermore, we find that MetaDetector is able to learn the event-shared features, and alleviate the negative transfer caused by the large distribution shift between events.

cs.SI↗
arXiv2021

Stability estimates for the complex Monge-Ampère and Hessian equations

A new proof for stability estimates for the complex Monge-Ampère and Hessian equations is given, which does not require pluripotential theory. A major advantage is that the resulting stability estimates are then uniform under general degenerations of the background metric in the case of the Monge-Ampère equation, and under degenerations to a big class in the case of Hessian equations.

math.DG↗
arXiv2021

On $L^\infty$ estimates for complex Monge-Ampère equations

A PDE proof is provided for the sharp $L^\infty$ estimates for the complex Monge-Ampère equation which had required pluripotential theory before. The proof covers both cases of fixed background as well as degenerating background metrics. It extends to more general fully non-linear equations satisfying a structural condition, and it also gives estimates of Trudinger type.

math.DG↗
arXiv2021

RLTIR: Activity-based Interactive Person Identification based on Reinforcement Learning Tree

Identity recognition plays an important role in ensuring security in our daily life. Biometric-based (especially activity-based) approaches are favored due to their fidelity, universality, and resilience. However, most existing machine learning-based approaches rely on a traditional workflow where models are usually trained once for all, with limited involvement from end-users in the process and neglecting the dynamic nature of the learning process. This makes the models static and can not be updated in time, which usually leads to high false positive or false negative. Thus, in practice, an expert is desired to assist with providing high-quality observations and interpretation of model outputs. It is expedient to combine both advantages of human experts and the computational capability of computers to create a tight-coupling incremental learning process for better performance. In this study, we develop RLTIR, an interactive identity recognition approach based on reinforcement learning, to adjust the identification model by human guidance. We first build a base tree-structured identity recognition model. And an expert is introduced in the model for giving feedback upon model outputs. Then, the model is updated according to strategies that are automatically learned under a designated reinforcement learning framework. To the best of our knowledge, it is the very first attempt to combine human expert knowledge with model learning in the area of identity recognition. The experimental results show that the reinforced interactive identity recognition framework outperforms baseline methods with regard to recognition accuracy and robustness.

cs.HC↗
arXiv2021

AdaSpring: Context-adaptive and Runtime-evolutionary Deep Model Compression for Mobile Applications

There are many deep learning (e.g., DNN) powered mobile and wearable applications today continuously and unobtrusively sensing the ambient surroundings to enhance all aspects of human lives. To enable robust and private mobile sensing, DNN tends to be deployed locally on the resource-constrained mobile devices via model compression. The current practice either hand-crafted DNN compression techniques, i.e., for optimizing DNN-relative performance (e.g., parameter size), or on-demand DNN compression methods, i.e., for optimizing hardware-dependent metrics (e.g., latency), cannot be locally online because they require offline retraining to ensure accuracy. Also, none of them have correlated their efforts with runtime adaptive compression to consider the dynamic nature of the deployment context of mobile applications. To address those challenges, we present AdaSpring, a context-adaptive and self-evolutionary DNN compression framework. It enables the runtime adaptive DNN compression locally online. Specifically, it presents the ensemble training of a retraining-free and self-evolutionary network to integrate multiple alternative DNN compression configurations (i.e., compressed architectures and weights). It then introduces the runtime search strategy to quickly search for the most suitable compression configurations and evolve the corresponding weights. With evaluation on five tasks across three platforms and a real-world case study, experiment outcomes show that AdaSpring obtains up to 3.1x latency reduction, 4.2 x energy efficiency improvement in DNNs, compared to hand-crafted compression techniques, while only incurring <= 6.2ms runtime-evolution latency.

cs.LG↗
arXiv2021

Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities

The vast proliferation of sensor devices and Internet of Things enables the applications of sensor-based activity recognition. However, there exist substantial challenges that could influence the performance of the recognition system in practical scenarios. Recently, as deep learning has demonstrated its effectiveness in many areas, plenty of deep methods have been investigated to address the challenges in activity recognition. In this study, we present a survey of the state-of-the-art deep learning methods for sensor-based human activity recognition. We first introduce the multi-modality of the sensory data and provide information for public datasets that can be used for evaluation in different challenge tasks. We then propose a new taxonomy to structure the deep methods by challenges. Challenges and challenge-related deep methods are summarized and analyzed to form an overview of the current research progress. At the end of this work, we discuss the open issues and provide some insights for future directions.

cs.HC↗
arXiv2020

Conditional Text Generation for Harmonious Human-Machine Interaction

In recent years, with the development of deep learning, text generation technology has undergone great changes and provided many kinds of services for human beings, such as restaurant reservation and daily communication. The automatically generated text is becoming more and more fluent so researchers begin to consider more anthropomorphic text generation technology, that is the conditional text generation, including emotional text generation, personalized text generation, and so on. Conditional Text Generation (CTG) has thus become a research hotspot. As a promising research field, we find that many efforts have been paid to exploring it. Therefore, we aim to give a comprehensive review of the new research trends of CTG. We first summary several key techniques and illustrate the technical evolution route in the field of neural text generation, based on the concept model of CTG. We further make an investigation of existing CTG fields and propose several general learning models for CTG. Finally, we discuss the open issues and promising research directions of CTG.

cs.CL↗
arXiv2020

Energy decay rates of solutions to a viscoelastic wave equation with variable exponents and weak damping

The goal of the present paper is to study the asymptotic behavior of solutions for the viscoelastic wave equation with variable exponents \[ u_{tt}-Δu+\int_0^tg(t-s)Δu(s)ds+a|u_t|^{m(x)-2}u_t=b|u|^{p(x)-2}u\] under initial-boundary condition, where the exponents $p(x)$ and $m(x)$ are given functions, and $a,~b>0$ are constants. More precisely, under the condition $g'(t)\le -ξ(t)g(t)$, here $ξ(t):\mathbb{R}^+\to\mathbb{R}^+$ is a non-increasing differential function with $ξ(0)>0,~\int_0^\inftyξ(s)ds=+\infty$, general decay results are derived. In addition, when $g$ decays polynomially, the exponential and polynomial decay rates are obtained as well, respectively. This work generalizes and improves earlier results in the literature.

math.AP↗
arXiv2020

Lifting at higher levels in the D1D5 CFT

The D1D5P system has a large set of BPS states at its orbifold point. Perturbing away from this 'free' point leads to some states joining up into long supermultiplets and lifting, while other states remain BPS. We consider the simplest orbifold which exhibits this lift: that with $N=2$ copies of the free $c=6$ CFT. We write down the number of lifted and unlifted states implied by the index at all levels upto $6$. We work to second order in the perturbation strength $λ$. For levels upto $4$, we find the wavefunctions of the lifted states, their supermultiplet structure and the value of the lift. All states that are allowed to lift by the index are in fact lifted at order $O(λ^2)$. We observe that the unlifted states in the untwisted sector have an antisymmetry between the copies in the right moving Ramond ground state sector, and extend this observation to find classes of states for arbitrary $N$ that will remain unlifted to $O(λ^2)$.

hep-th↗
arXiv2020

Classification of blow-up and global existence of solutions to an initial $\textrm{Neumann}$ problem

The aim of this paper is to apply the modified potential well method and some new differential inequalities to study the asymptotic behavior of solutions to the initial homogeneous $\hbox{Neumann}$ problem of a nonlinear diffusion equation driven by the $p(x)$-\hbox{Laplace} operator. Complete classification of global existence and blow-up in finite time of solutions is given when the initial data satisfies different conditions. Roughly speaking, we obtain a threshold result for the solution to exist globally or to blow up in finite time when the initial energy is subcritical and critical, respectively. Further, the decay rate of the $L^2$ norm is also obtained for global solutions. Sufficient conditions for the existence of global and blow-up solutions are also provided for supercritical initial energy. At last, we give two-sided estimates of asymptotic behavior when the diffusion term dominates the source. This is a continuation of our previous work \cite{GG}.

math.AP↗
arXiv2020

On the degeneration of asymptotically conical Calabi-Yau metrics

We study the degenerations of asymptotically conical Ricci-flat Kähler metrics as the Kähler class degenerates to a semi-positive class. We show that under appropriate assumptions, the Ricci-flat Kähler metrics converge to a incomplete smooth Ricci-flat Kähler metric away from a compact subvariety. As a consequence, we construct singular Calabi-Yau metrics with asymptotically conical behaviour at infinity on certain quasi-projective varieties and we show that the metric geometry of these singular metrics are homeomorphic to the topology of the singular variety. Finally, we will apply our results to study several classes of examples of geometric transitions between Calabi-Yau manifolds.

math.DG↗
arXiv2020

Towards information-rich, logical text generation with knowledge-enhanced neural models

Text generation system has made massive promising progress contributed by deep learning techniques and has been widely applied in our life. However, existing end-to-end neural models suffer from the problem of tending to generate uninformative and generic text because they cannot ground input context with background knowledge. In order to solve this problem, many researchers begin to consider combining external knowledge in text generation systems, namely knowledge-enhanced text generation. The challenges of knowledge enhanced text generation including how to select the appropriate knowledge from large-scale knowledge bases, how to read and understand extracted knowledge, and how to integrate knowledge into generation process. This survey gives a comprehensive review of knowledge-enhanced text generation systems, summarizes research progress to solving these challenges and proposes some open issues and research directions.

cs.AI↗
arXiv2020

On the Kahler-Ricci flow on Fano manifolds

A short proof of the convergence of the Kahler-Ricci flow on Fano manifolds admitting a Kahler-Einstein metric or a Kahler-Ricci soliton is given, using a variety of recent techniques

math.DG↗
arXiv2020

Kahler-Einstein Metrics and Eigenvalue Gaps

The existence of Kahler-Einstein metrics on a Fano manifold is characterized in terms of a uniform gap between 0 and the first positive eigenvalue of the Cauchy-Riemann operator on smooth vector fields. It is also characterized by a similar gap between 0 and the first positive eigenvalue for Hamiltonian vector fields. The underlying tool is a compactness criterion for suitably bounded subsets of the space of Kahler potentials which implies a positive gap.

math.DG↗