Edge closeness and betweenness centralities are widely used path-based metrics for characterizing the importance of edges in *** general graphs,edge closeness centrality indicates the importance of edges by the shorte...
详细信息
Edge closeness and betweenness centralities are widely used path-based metrics for characterizing the importance of edges in *** general graphs,edge closeness centrality indicates the importance of edges by the shortest distances from the edge to all the other *** betweenness centrality ranks which edges are significant based on the fraction of all-pairs shortest paths that pass through the ***,extensive research efforts go into centrality computation over general graphs that omit time ***,numerous real-world networks are modeled as temporal graphs,where the nodes are related to each other at different time *** temporal property is important and should not be neglected because it guides the flow of information in the *** state of affairs motivates the paper’s study of edge centrality computation methods on temporal *** introduce the concepts of the label,and label dominance relation,and then propose multi-thread parallel labeling-based methods on OpenMP to efficiently compute edge closeness and betweenness centralities *** types of optimal temporal *** edge closeness centrality computation,a time segmentation strategy and two observations are presented to aggregate some related temporal edges for uniform *** edge betweenness centrality computation,to improve efficiency,temporal edge dependency formulas,a labeling-based forward-backward scanning strategy,and a compression-based optimization method are further proposed to iteratively accumulate centrality *** experiments using 13 real temporal graphs are conducted to provide detailed insights into the efficiency and effectiveness of the proposed *** with state-ofthe-art methods,labeling-based methods are capable of up to two orders of magnitude speedup.
Matrix minimization techniques that employ the nuclear norm have gained recognition for their applicability in tasks like image inpainting, clustering, classification, and reconstruction. However, they come with inher...
详细信息
Matrix minimization techniques that employ the nuclear norm have gained recognition for their applicability in tasks like image inpainting, clustering, classification, and reconstruction. However, they come with inherent biases and computational burdens, especially when used to relax the rank function, making them less effective and efficient in real-world scenarios. To address these challenges, our research focuses on generalized nonconvex rank regularization problems in robust matrix completion, low-rank representation, and robust matrix regression. We introduce innovative approaches for effective and efficient low-rank matrix learning, grounded in generalized nonconvex rank relaxations inspired by various substitutes for the ?0-norm relaxed functions. These relaxations allow us to more accurately capture low-rank structures. Our optimization strategy employs a nonconvex and multi-variable alternating direction method of multipliers, backed by rigorous theoretical analysis for complexity and *** algorithm iteratively updates blocks of variables, ensuring efficient convergence. Additionally, we incorporate the randomized singular value decomposition technique and/or other acceleration strategies to enhance the computational efficiency of our approach, particularly for large-scale constrained minimization problems. In conclusion, our experimental results across a variety of image vision-related application tasks unequivocally demonstrate the superiority of our proposed methodologies in terms of both efficacy and efficiency when compared to most other related learning methods.
Anomaly detection(AD) has been extensively studied and applied across various scenarios in recent years. However, gaps remain between the current performance and the desired recognition accuracy required for practical...
详细信息
Anomaly detection(AD) has been extensively studied and applied across various scenarios in recent years. However, gaps remain between the current performance and the desired recognition accuracy required for practical *** paper analyzes two fundamental failure cases in the baseline AD model and identifies key reasons that limit the recognition accuracy of existing approaches. Specifically, by Case-1, we found that the main reason detrimental to current AD methods is that the inputs to the recovery model contain a large number of detailed features to be recovered, which leads to the normal/abnormal area has not/has been recovered into its original state. By Case-2, we surprisingly found that the abnormal area that cannot be recognized in image-level representations can be easily recognized in the feature-level representation. Based on the above observations, we propose a novel recover-then-discriminate(ReDi) framework for *** takes a self-generated feature map(e.g., histogram of oriented gradients) and a selected prompted image as explicit input information to address the identified in Case-1. Additionally, a feature-level discriminative network is introduced to amplify abnormal differences between the recovered and input representations. Extensive experiments on two widely used yet challenging AD datasets demonstrate that ReDi achieves state-of-the-art recognition accuracy.
Preserving formal style in neural machine translation (NMT) is essential, yet often overlooked as an optimization objective of the training processes. This oversight can lead to translations that, though accurate, lac...
详细信息
Preserving formal style in neural machine translation (NMT) is essential, yet often overlooked as an optimization objective of the training processes. This oversight can lead to translations that, though accurate, lack formality. In this paper, we propose how to improve NMT formality with large language models (LLMs), which combines the style transfer and evaluation capabilities of an LLM and the high-quality translation generation ability of NMT models to improve NMT formality. The proposed method (namely INMTF) encompasses two approaches. The first involves a revision approach using an LLM to revise the NMT-generated translation, ensuring a formal translation style. The second approach employs an LLM as a reward model for scoring translation formality, and then uses reinforcement learning algorithms to fine-tune the NMT model to maximize the reward score, thereby enhancing the formality of the generated translations. Considering the substantial parameter size of LLMs, we also explore methods to reduce the computational cost of INMTF. Experimental results demonstrate that INMTF significantly outperforms baselines in terms of translation formality and translation quality, with an improvement of +9.19 style accuracy points in the German-to-English task and +2.16 COMET score in the Russian-to-English task. Furthermore, our work demonstrates the potential of integrating LLMs within NMT frameworks to bridge the gap between NMT outputs and the formality required in various real-world translation scenarios.
This article proposes a distributed dynamic event-triggered data-driven iterative learning control(DET-DDILC)scheme under a predefined performance to tackle the bipartite tracking control problem for multiagent system...
详细信息
This article proposes a distributed dynamic event-triggered data-driven iterative learning control(DET-DDILC)scheme under a predefined performance to tackle the bipartite tracking control problem for multiagent systems(MASs). An improved dynamic linearization technique is utilized to convert the nonlinear MASs into an iterative linear data model. First,a peer-to-peer mapping function is introduced to map the constrained distributed system output homeomorphism to an unconstrained one. In addition, a DET mechanism based on a time-iteration-varying function is devised to conserve network communication resources. Based on the unconstrained transformation and the designed DET mechanism, the DET-DDILC algorithm is devised to ensure that the bipartite tracking performance of MASs can be within the preset range. Finally, the effectiveness and feasibility of the designed control scheme are demonstrated via a simulation case by a comparison.
作者:
Du, AnJia, JieChen, JianWang, XingweiHuang, MingNortheastern University
School of Computer Science and Engineering Engineering Research Center of Security Technology of Complex Network System Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Shenyang110819 China Northeastern University
School of Computer Science and Engineering Shenyang110819 China
Mobile edge computing (MEC) integrated with Network Functions Virtualization (NFV) helps run a wide range of services implemented by Virtual Network Functions (VNFs) deployed at MEC networks. This emerging paradigm of...
详细信息
Carbide dispersion reinforcing has been demonstrated to be an effective way of strengthening metal ma-trix ***,plagued by the nerve-wracking fact that the carbide particles tend to aggregate at the grain boundary of t...
详细信息
Carbide dispersion reinforcing has been demonstrated to be an effective way of strengthening metal ma-trix ***,plagued by the nerve-wracking fact that the carbide particles tend to aggregate at the grain boundary of the metal matrix,grow up,and form an incoherent interface with it,their im-provement in mechanical strength tends to be *** this study,spark plasma sintering(SPS)was used to prepare the bulk alloy Ni20Cr and its composites with different carbides including TiC,SiC,and *** leads to discharge and elevates temperature at the interface to melt the Ni20Cr alloy par-ticles *** cooled down,the alloy is heterogeneously solidified on the surface of the carbide and builds up a coherent interface with *** to the decomposition of Ti3SiC2 during sintering,it completely transformed into nanosized TiC particles,which are engulfed by the outer melted layer of Ni20Cr and well dispersed within the alloy *** comparison to the Ni20Cr alloy,the composite with merely 4 wt%Ti3SiC2 gains over three times enhancement in yield strength to 879 MPa,while keeping a moderate high elongation of 17.8%.Finite element analysis demonstrated that the combination of SPS and precursor MAX phase of Ti3SiC2,which results in the in-situ precipitation of coherent ultrafine TiC particles in alloy grains,plays the key role in getting a good balance between mechanical strength and ductility for the Ni20Cr matrix composites.
In the course of industrial electroslag remelting (ESR), large-size Ca–Al–Mg–O nonmetallic inclusions were prone to form in 4Cr13 die steels and will deteriorate mechanical properties and service life seriously. In...
详细信息
Constructing an effective common latent embedding by aligning the latent spaces of cross-modal variational autoencoders(VAEs) is a popular strategy for generalized zero-shot learning(GZSL). However, due to the lac...
详细信息
Constructing an effective common latent embedding by aligning the latent spaces of cross-modal variational autoencoders(VAEs) is a popular strategy for generalized zero-shot learning(GZSL). However, due to the lack of fine-grained instance-wise annotations, existing VAE methods can easily suffer from the posterior collapse problem. In this paper, we propose an innovative asymmetric VAE network by aligning enhanced feature representation(AEFR) for GZSL. Distinguished from general VAE structures, we designed two asymmetric encoders for visual and semantic observations and one decoder for visual reconstruction. Specifically, we propose a simple yet effective gated attention mechanism(GAM) in the visual encoder for enhancing the information interaction between observations and latent variables, alleviating the possible posterior collapse problem effectively. In addition, we propose a novel distributional decoupling-based contrastive learning(D2-CL) to guide learning classification-relevant information while aligning the representations at the taxonomy level in the latent representation space. Extensive experiments on publicly available datasets demonstrate the state-of-the-art performance of our method. The source code is available at https://***/seeyourmind/AEFR.
The novel Co-based superalloys are extensively used in gas-powered and jet engine turbines due to their excellent high-temperature performance, achieved by strengthening the L12-γ′ ordered phase. This review present...
详细信息
The novel Co-based superalloys are extensively used in gas-powered and jet engine turbines due to their excellent high-temperature performance, achieved by strengthening the L12-γ′ ordered phase. This review presents an overview of the research progress on oxidation behavior of Co-based superalloys, including oxidation kinetics, oxides morphology, the formation and spallation of oxide layers, and importantly, the synergistic effects of alloying elements on oxidation resistance—a critical area considering the complex interactions with multiple alloying elements. Additionally, this review compares the oxidation resistance of single crystal versus polycrystalline alloys. The effect of phase interface and dislocations on oxidation behavior is also discussed. While significant progress has been achieved, areas necessitating further investigation include optimizing alloy compositions for enhanced oxidation resistance and understanding the long-term stability of oxide layers. The future prospects for Co-based superalloys are promising as ongoing research aims to address the existing challenges and unlock new applications at even higher operating temperatures.
暂无评论