arXiv subjects

Wang Chen

Publications and source records attributed to Wang Chen.

At least 55 records · Page 3Linked to original sources

arXiv2024

On the convergence of conditional gradient method for unbounded multiobjective optimization problems

This paper focuses on developing a conditional gradient algorithm for multiobjective optimization problems with an unbounded feasible region. We employ the concept of recession cone to establish the well-defined nature of the algorithm. The asymptotic convergence property and the iteration-complexity bound are established under mild assumptions. Numerical examples are provided to verify the algorithmic performance.

math.OC↗

arXiv2024

Parameter-efficient Prompt Learning for 3D Point Cloud Understanding

This paper presents a parameter-efficient prompt tuning method, named PPT, to adapt a large multi-modal model for 3D point cloud understanding. Existing strategies are quite expensive in computation and storage, and depend on time-consuming prompt engineering. We address the problems from three aspects. Firstly, a PromptLearner module is devised to replace hand-crafted prompts with learnable contexts to automate the prompt tuning process. Then, we lock the pre-trained backbone instead of adopting the full fine-tuning paradigm to substantially improve the parameter efficiency. Finally, a lightweight PointAdapter module is arranged near target tasks to enhance prompt tuning for 3D point cloud understanding. Comprehensive experiments are conducted to demonstrate the superior parameter and data efficiency of the proposed method.Meanwhile, we obtain new records on 4 public datasets and multiple 3D tasks, i.e., point cloud recognition, few-shot learning, and part segmentation. The implementation is available at https://github.com/auniquesun/PPT.

cs.CV↗

arXiv2024

Improvements to steepest descent method for multi-objective optimization

In this paper, we propose a simple yet efficient strategy for improving the multi-objective steepest descent method proposed by Fliege and Svaiter (Math Methods Oper Res, 2000, 3: 479--494). The core idea behind this strategy involves incorporating a positive modification parameter into the iterative formulation of the multi-objective steepest descent algorithm in a multiplicative manner. This modification parameter captures certain second-order information associated with the objective functions. We provide two distinct methods for calculating this modification parameter, leading to the development of two improved multi-objective steepest descent algorithms tailored for solving multi-objective optimization problems. Under reasonable assumptions, we demonstrate the convergence of sequences generated by the first algorithm toward a critical point. Moreover, for strongly convex multi-objective optimization problems, we establish the linear convergence to Pareto optimality of the sequence of generated points. The performance of the new algorithms is empirically evaluated through a computational comparison on a set of multi-objective test instances. The numerical results underscore that the proposed algorithms consistently outperform the original multi-objective steepest descent algorithm.

math.OC↗

arXiv2023

Quantifying traffic emission reductions and traffic congestion alleviation from high-capacity ride-sharing

Despite the promising benefits that ride-sharing offers, there has been a lack of research on the benefits of high-capacity ride-sharing services. Prior research has also overlooked the relationship between traffic volume and the degree of traffic congestion and emissions. To address these gaps, this study develops an open-source agent-based simulation platform and a heuristic algorithm to quantify the benefits of high-capacity ride-sharing with significantly lower computational costs. The simulation platform integrates a traffic emission model and a speed-density traffic flow model to characterize the interactions between traffic congestion levels and emissions. The experiment results demonstrate that ride-sharing with vehicle capacities of 2, 4, and 6 passengers can alleviate total traffic congestion by approximately 3%, 4%, and 5%, and reduce traffic emissions of a ride-sourcing system by approximately 30%, 45%, and 50%, respectively. This study can guide transportation network companies in designing and managing more efficient and environment-friendly mobility systems.

eess.SY↗

arXiv2023

Infrastructure Crack Segmentation: Boundary Guidance Method and Benchmark Dataset

Cracks provide an essential indicator of infrastructure performance degradation, and achieving high-precision pixel-level crack segmentation is an issue of concern. Unlike the common research paradigms that adopt novel artificial intelligence (AI) methods directly, this paper examines the inherent characteristics of cracks so as to introduce boundary features into crack identification and then builds a boundary guidance crack segmentation model (BGCrack) with targeted structures and modules, including a high frequency module, global information modeling module, joint optimization module, etc. Extensive experimental results verify the feasibility of the proposed designs and the effectiveness of the edge information in improving segmentation results. In addition, considering that notable open-source datasets mainly consist of asphalt pavement cracks because of ease of access, there is no standard and widely recognized dataset yet for steel structures, one of the primary structural forms in civil infrastructure. This paper provides a steel crack dataset that establishes a unified and fair benchmark for the identification of steel cracks.

cs.CV↗

arXiv2023

Scaling Laws of Dynamic High-Capacity Ride-Sharing

Dynamic ride-sharing services, including ride-pooling offered by ride-hailing platforms and demand-responsive buses, have become an essential part of urban mobility systems. These services cater to personalized and on-demand mobility requirements while simultaneously improving efficiency and sustainability by accommodating several trip requests within a single ride. However, quantifying the advantages and disadvantages of dynamic ride-sharing, particularly high-capacity ride-sharing, remains a challenge due to the complex dynamics that depend on several factors, including matching algorithms, vehicle capacity, transportation network topology, and spatiotemporal demand and supply distribution. In this study, we conduct extensive experiments on an agent-based simulation platform calibrated by real-world mobility data from Chengdu, Hong Kong, and Manhattan. Our findings reveal a few scaling laws that can effectively measure how key performance metrics such as passenger service rate and vehicle occupancy rate change with a dimensionless system loading factor that reflects the relative magnitude of demand versus supply. Moreover, our results indicate that these scaling laws are universal for different network topologies and supply-demand situations. As a result, these scaling laws offer a means for urban planners, city managers, and ride-hailing platforms to quantify the potential benefits and drawbacks of dynamic ride-sharing under different circumstances and to design better operational and regulatory strategies.

eess.SY↗

arXiv2023

MLOps Spanning Whole Machine Learning Life Cycle: A Survey

Google AlphaGos win has significantly motivated and sped up machine learning (ML) research and development, which led to tremendous ML technical advances and wider adoptions in various domains (e.g., Finance, Health, Defense, and Education). These advances have resulted in numerous new concepts and technologies, which are too many for people to catch up to and even make them confused, especially for newcomers to the ML area. This paper is aimed to present a clear picture of the state-of-the-art of the existing ML technologies with a comprehensive survey. We lay out this survey by viewing ML as a MLOps (ML Operations) process, where the key concepts and activities are collected and elaborated with representative works and surveys. We hope that this paper can serve as a quick reference manual (a survey of surveys) for newcomers (e.g., researchers, practitioners) of ML to get an overview of the MLOps process, as well as a good understanding of the key technologies used in each step of the ML process, and know where to find more details.

cs.LG↗

arXiv2022

SR-DCSK Cooperative Communication System with Code Index Modulation: A New Design for 6G New Radios

This paper proposes a high-throughput short reference differential chaos shift keying cooperative communication system with the aid of code index modulation, referred to as CIM-SR-DCSK-CC system. In the proposed CIM-SR-DCSK-CC system, the source transmits information bits to both the relay and destination in the first time slot, while the relay not only forwards the source information bits but also sends new information bits to the destination in the second time slot. To be specific, the relay employs an $N$-order Walsh code to carry additional ${{\log }_{2}}N$ information bits, which are superimposed onto the SR-DCSK signal carrying the decoded source information bits. Subsequently, the superimposed signal carrying both the source and relay information bits is transmitted to the destination. Moreover, the theoretical bit error rate (BER) expressions of the proposed CIM-SR-DCSK-CC system are derived over additive white Gaussian noise (AWGN) and multipath Rayleigh fading channels. Compared with the conventional DCSK-CC system and SR-DCSK-CC system, the proposed CIM-SR-DCSK-CC system can significantly improve the throughput without deteriorating any BER performance. As a consequence, the proposed system is very promising for the applications of the 6G-enabled low-power and high-rate communication.

cs.IT↗

arXiv2022

Global Mixup: Eliminating Ambiguity with Clustering

Data augmentation with \textbf{Mixup} has been proven an effective method to regularize the current deep neural networks. Mixup generates virtual samples and corresponding labels at once through linear interpolation. However, this one-stage generation paradigm and the use of linear interpolation have the following two defects: (1) The label of the generated sample is directly combined from the labels of the original sample pairs without reasonable judgment, which makes the labels likely to be ambiguous. (2) linear combination significantly limits the sampling space for generating samples. To tackle these problems, we propose a novel and effective augmentation method based on global clustering relationships named \textbf{Global Mixup}. Specifically, we transform the previous one-stage augmentation process into two-stage, decoupling the process of generating virtual samples from the labeling. And for the labels of the generated samples, relabeling is performed based on clustering by calculating the global relationships of the generated samples. In addition, we are no longer limited to linear relationships but generate more reliable virtual samples in a larger sampling space. Extensive experiments for \textbf{CNN}, \textbf{LSTM}, and \textbf{BERT} on five tasks show that Global Mixup significantly outperforms previous state-of-the-art baselines. Further experiments also demonstrate the advantage of Global Mixup in low-resource scenarios.

cs.LG↗

arXiv2022

Memory gradient method for multiobjective optimization

In this paper, we propose a new descent method, termed as multiobjective memory gradient method, for finding Pareto critical points of a multiobjective optimization problem. The main thought in this method is to select a combination of the current descent direction and past multi-step iterative information as a new search direction and to obtain a stepsize by virtue of two types of strategies. It is proved that the developed direction with suitable parameters always satisfies the sufficient descent condition at each iteration. Based on mild assumptions, we obtain the global convergence and the rates of convergence for our method. Computational experiments are given to demonstrate the effectiveness of the proposed method.

math.OC↗

arXiv2022

Conditional gradient method for vector optimization

In this paper, we propose a conditional gradient method for solving constrained vector optimization problems with respect to a partial order induced by a closed, convex and pointed cone with nonempty interior. When the partial order under consideration is the one induced by the non-negative orthant, we regain the method for multiobjective optimization recently proposed by Assunção et al. (Comput Optim Appl 78(3):741--768, 2021). In our method, the construction of auxiliary subproblem is based on the well-known oriented distance function. Three different types of step size strategies (Armijio, adaptative and nonmonotone) are considered. Without any assumptions, we prove that stationarity of accumulation points of the sequences produced by the proposed method equipped with the Armijio or the nonmonotone step size rule. To obtain the convergence result of the method with the adaptative step size strategy, we introduce an useful cone convexity condition which allows to circumvent the intricate question of the Lipschitz continuity of Jocabian for the objective function. This condition helps us generalize the classical descent lemma to the vector optimization case. Under suitable convexity assumptions for the objective function, it is proved that all accumulation points of any generated sequences obtained by our method are weakly efficient solutions.

math.OC↗

arXiv2021

A novel multiobjective evolutionary algorithm based on decomposition and multi-reference points strategy

Many real-world optimization problems such as engineering design can be eventually modeled as the corresponding multiobjective optimization problems (MOPs) which must be solved to obtain approximate Pareto optimal fronts. Multiobjective evolutionary algorithm based on decomposition (MOEA/D) has been regarded as a significantly promising approach for solving MOPs. Recent studies have shown that MOEA/D with uniform weight vectors is well-suited to MOPs with regular Pareto optimal fronts, but its performance in terms of diversity usually deteriorates when solving MOPs with irregular Pareto optimal fronts. In this way, the solution set obtained by the algorithm can not provide more reasonable choices for decision makers. In order to efficiently overcome this drawback, we propose an improved MOEA/D algorithm by virtue of the well-known Pascoletti-Serafini scalarization method and a new strategy of multi-reference points. Specifically, this strategy consists of the setting and adaptation of reference points generated by the techniques of equidistant partition and projection. For performance assessment, the proposed algorithm is compared with existing four state-of-the-art multiobjective evolutionary algorithms on benchmark test problems with various types of Pareto optimal fronts. According to the experimental results, the proposed algorithm exhibits better diversity performance than that of the other compared algorithms. Finally, our algorithm is applied to two real-world MOPs in engineering optimization successfully.

cs.NE↗

arXiv2021

Anisotropic magneto-optical absorption and linear dichroism in two-dimensional semi-Dirac electron systems

We present a theoretical study on the Landau levels (LLs) and magneto-optical absorption of a two-dimensional semi-Dirac electron system under a perpendicular magnetic field. Based on an effective k.p Hamiltonian, we find that the LLs are proportional to the two-thirds power law of the magnetic field and level index, which can be understood as a hybridization of the LL of Schrodinger and Dirac electrons with new features. With the help of Kubo formula, we find the selection rule for interband (intraband) magneto-optical transition is anisotropic (isotropic). Specifically, the selection rules for interband magneto-optical transitions are $Δn$=0, $\pm2$ ($\pm2$, $\pm4$) for linearly polarized light along the linear (parabolic) dispersion direction, while the selection rules for the intraband transition are $Δn$=$\pm1$, $\pm3$ regardless of the polarization direction of the light. Further, the magneto-optical conductivity for interband (intraband) transition excited by linearly polarized light along the linear dispersion direction is two (one) orders of magnitude larger than that along the parabolic dispersion direction. This anisotropic magneto-optical absorption spectrum clearly reflects the structure of the LLs, and results in a strong linear dichroism. Importantly, a perfect linear dichroism with magnetic-field tunable wavelength can be achieved by using the interband transition between the two lowest LLs, i.e, from Ev0 to Ec0. Our results shed light on the magneto-optical property of the two dimensional semi-Dirac electron systems and pave the way to design magnetically controlled optical devices.

cond-mat.mes-hall↗

arXiv2021

Dialogue Summarization with Supporting Utterance Flow Modeling and Fact Regularization

Dialogue summarization aims to generate a summary that indicates the key points of a given dialogue. In this work, we propose an end-to-end neural model for dialogue summarization with two novel modules, namely, the \emph{supporting utterance flow modeling module} and the \emph{fact regularization module}. The supporting utterance flow modeling helps to generate a coherent summary by smoothly shifting the focus from the former utterances to the later ones. The fact regularization encourages the generated summary to be factually consistent with the ground-truth summary during model training, which helps to improve the factual correctness of the generated summary in inference time. Furthermore, we also introduce a new benchmark dataset for dialogue summarization. Extensive experiments on both existing and newly-introduced datasets demonstrate the effectiveness of our model.

cs.CL↗

arXiv2021

A Training-free and Reference-free Summarization Evaluation Metric via Centrality-weighted Relevance and Self-referenced Redundancy

In recent years, reference-based and supervised summarization evaluation metrics have been widely explored. However, collecting human-annotated references and ratings are costly and time-consuming. To avoid these limitations, we propose a training-free and reference-free summarization evaluation metric. Our metric consists of a centrality-weighted relevance score and a self-referenced redundancy score. The relevance score is computed between the pseudo reference built from the source document and the given summary, where the pseudo reference content is weighted by the sentence centrality to provide importance guidance. Besides an $F_1$-based relevance score, we also design an $F_β$-based variant that pays more attention to the recall score. As for the redundancy score of the summary, we compute a self-masked similarity score with the summary itself to evaluate the redundant information in the summary. Finally, we combine the relevance and redundancy scores to produce the final evaluation score of the given summary. Extensive experiments show that our methods can significantly outperform existing methods on both multi-document and single-document summarization evaluation.

cs.CL↗

arXiv2021

Power law decay of local density of states oscillations near a line defect in a system with semi-Dirac points

We theoretically study the power-law decay behavior of the local density of states (LDOS) oscillations near a line defect in system with semi-Dirac points by using a low-energy k.p Hamiltonian. We find that the LDOS oscillations are strongly anisotropic and sensitively depend on the orientation of the line defect. We analytically obtain the decay indexes of the LDOS oscillations near a line defect running along different directions by using the stationary phase approximation. Specifically, when the line defect is perpendicular to the linear dispersion direction, the decay index is -5/4 whereas it becomes -1/4 if the system is gapped, both of which are different from the decay index -3/2 in isotropic Dirac systems. In contrast, when the line defect is perpendicular to the parabolic dispersion direction, the decay index is always -1/2 regardless of whether the system is gapped or not, which is the same as that in a conventional semimetal. In general, when the defect runs along an arbitrary direction, the decay index sensitively depends on the incident energy for a certain orientation of the line defect. It varies from -5/4 to -1/2 due to the absence of strict stationary phase point. Our results indicate that the decay index -5/4 provides a fingerprint to identify semi-Dirac points in 2D electron systems.

cond-mat.mes-hall↗

arXiv2021

A Unified Dual-view Model for Review Summarization and Sentiment Classification with Inconsistency Loss

Acquiring accurate summarization and sentiment from user reviews is an essential component of modern e-commerce platforms. Review summarization aims at generating a concise summary that describes the key opinions and sentiment of a review, while sentiment classification aims to predict a sentiment label indicating the sentiment attitude of a review. To effectively leverage the shared sentiment information in both review summarization and sentiment classification tasks, we propose a novel dual-view model that jointly improves the performance of these two tasks. In our model, an encoder first learns a context representation for the review, then a summary decoder generates a review summary word by word. After that, a source-view sentiment classifier uses the encoded context representation to predict a sentiment label for the review, while a summary-view sentiment classifier uses the decoder hidden states to predict a sentiment label for the generated summary. During training, we introduce an inconsistency loss to penalize the disagreement between these two classifiers. It helps the decoder to generate a summary to have a consistent sentiment tendency with the review and also helps the two sentiment classifiers learn from each other. Experiment results on four real-world datasets from different domains demonstrate the effectiveness of our model.

cs.CL↗

arXiv2020

Exclusive Hierarchical Decoding for Deep Keyphrase Generation

Keyphrase generation (KG) aims to summarize the main ideas of a document into a set of keyphrases. A new setting is recently introduced into this problem, in which, given a document, the model needs to predict a set of keyphrases and simultaneously determine the appropriate number of keyphrases to produce. Previous work in this setting employs a sequential decoding process to generate keyphrases. However, such a decoding method ignores the intrinsic hierarchical compositionality existing in the keyphrase set of a document. Moreover, previous work tends to generate duplicated keyphrases, which wastes time and computing resources. To overcome these limitations, we propose an exclusive hierarchical decoding framework that includes a hierarchical decoding process and either a soft or a hard exclusion mechanism. The hierarchical decoding process is to explicitly model the hierarchical compositionality of a keyphrase set. Both the soft and the hard exclusion mechanisms keep track of previously-predicted keyphrases within a window size to enhance the diversity of the generated keyphrases. Extensive experiments on multiple KG benchmark datasets demonstrate the effectiveness of our method to generate less duplicated and more accurate keyphrases.

cs.CL↗