Decentralized Online Learning(DOL)extends online learning to the domain of distributed ***,limitations of local data in decentralized settings lead to a decrease in the accuracy of decisions or models compared to cent...
详细信息
Decentralized Online Learning(DOL)extends online learning to the domain of distributed ***,limitations of local data in decentralized settings lead to a decrease in the accuracy of decisions or models compared to centralized *** the increasing requirement to achieve a high-precision model or decision with distributed data resources in a network,applying ensemble methods is attempted to achieve a superior model or decision with only transferring gradients or models.A new boosting method,namely Boosting for Distributed Online Convex Optimization(BD-OCO),is designed to realize the application of boosting in distributed ***-OCO achieves the regret upper bound O(M+N/MNT)where M measures the size of the distributed network and N is the number of Weak Learners(WLs)in each *** core idea of BD-OCO is to apply the local model to train a strong global ***-OCO is evaluated on the basis of eight different real-world *** results show that BD-OCO achieves excellent performance in accuracy and convergence,and is robust to the size of the distributed network.
Text classification is a challenging task in the field of Natural Language Processing (NLP), and significant progress has been made using deep learning methods. Traditional deep-learning approaches for text classifica...
详细信息
Dear Editor,This letter is concerned with the problem of time-varying formation tracking for heterogeneous multi-agent systems(MASs) under directed switching networks. For this purpose, our first step is to present so...
详细信息
Dear Editor,This letter is concerned with the problem of time-varying formation tracking for heterogeneous multi-agent systems(MASs) under directed switching networks. For this purpose, our first step is to present some sufficient conditions for the exponential stability of a particular category of switched systems.
Domain adaptation(DA) aims to find a subspace,where the discrepancies between the source and target domains are reduced. Based on this subspace, the classifier trained by the labeled source samples can classify unlabe...
详细信息
Domain adaptation(DA) aims to find a subspace,where the discrepancies between the source and target domains are reduced. Based on this subspace, the classifier trained by the labeled source samples can classify unlabeled target samples *** approaches leverage Graph Embedding Learning to explore such a subspace. Unfortunately, due to 1) the interaction of the consistency and specificity between samples, and 2) the joint impact of the degenerated features and incorrect labels in the samples, the existing approaches might assign unsuitable similarity, which restricts their performance. In this paper, we propose an approach called adaptive graph embedding with consistency and specificity(AGE-CS) to cope with these issues. AGE-CS consists of two methods, i.e., graph embedding with consistency and specificity(GECS), and adaptive graph embedding(AGE).GECS jointly learns the similarity of samples under the geometric distance and semantic similarity metrics, while AGE adaptively adjusts the relative importance between the geometric distance and semantic similarity during the iterations. By AGE-CS,the neighborhood samples with the same label are rewarded,while the neighborhood samples with different labels are punished. As a result, compact structures are preserved, and advanced performance is achieved. Extensive experiments on five benchmark datasets demonstrate that the proposed method performs better than other Graph Embedding methods.
Most existing domain adaptation(DA) methods aim to explore favorable performance under complicated environments by ***,there are three unsolved problems that limit their efficiencies:ⅰ) they adopt global sampling but...
详细信息
Most existing domain adaptation(DA) methods aim to explore favorable performance under complicated environments by ***,there are three unsolved problems that limit their efficiencies:ⅰ) they adopt global sampling but neglect to exploit global and local sampling simultaneously;ⅱ)they either transfer knowledge from a global perspective or a local perspective,while overlooking transmission of confident knowledge from both perspectives;and ⅲ) they apply repeated sampling during iteration,which takes a lot of *** address these problems,knowledge transfer learning via dual density sampling(KTL-DDS) is proposed in this study,which consists of three parts:ⅰ) Dual density sampling(DDS) that jointly leverages two sampling methods associated with different views,i.e.,global density sampling that extracts representative samples with the most common features and local density sampling that selects representative samples with critical boundary information;ⅱ)Consistent maximum mean discrepancy(CMMD) that reduces intra-and cross-domain risks and guarantees high consistency of knowledge by shortening the distances of every two subsets among the four subsets collected by DDS;and ⅲ) Knowledge dissemination(KD) that transmits confident and consistent knowledge from the representative target samples with global and local properties to the whole target domain by preserving the neighboring relationships of the target *** analyses show that DDS avoids repeated sampling during the *** the above three actions,confident knowledge with both global and local properties is transferred,and the memory and running time are greatly *** addition,a general framework named dual density sampling approximation(DDSA) is extended,which can be easily applied to other DA *** experiments on five datasets in clean,label corruption(LC),feature missing(FM),and LC&FM environments demonstrate the encouraging performance of KTL-DDS.
UAV reconnaissance has many advantages, such as high reliability, strong flexibility and wide coverage. When using unmanned aerial vehicles to scout targets, it is often necessary to quickly scout many fixed targets. ...
详细信息
This paper proposes a novel method for early action prediction based on 3D skeleton data. Our method combines the advantages of graph convolutional networks (GCNs) and adversarial learning to avoid the problems of ins...
详细信息
This paper proposes a novel method for early action prediction based on 3D skeleton data. Our method combines the advantages of graph convolutional networks (GCNs) and adversarial learning to avoid the problems of insufficient spatio-temporal feature extraction and difficulty in predicting actions in the early execution stage of actions. In our method, GCNs, which have outstanding performance in the field of action recognition, are used to extract the spatio-temporal features of the skeleton. The model learns how to optimize the feature distribution of partial videos from the features of full videos through adversarial learning. Experiments on two challenging action prediction datasets show that our method performs well on skeleton-based early action prediction. State-of-the-art performance is reported in some observation ratios.
The traditional telecommunications band performs poorly in harsh weather conditions due to atmospheric absorption. In recent years, researchers have begun to study optical communication through atmospheric windows, an...
详细信息
The traditional telecommunications band performs poorly in harsh weather conditions due to atmospheric absorption. In recent years, researchers have begun to study optical communication through atmospheric windows, and optical switches are an essential component of optical communication. A broadband atmospheric window optical switch was proposed based on Vanadium dioxide and magnetic polaritons(MP). It is formed by the stacking of two metal-dielectric-metal structures. The simulation results show that the modulation depth can reach 98.38%, and the extinction ratio is 17.93 dB. By calculating the magnetic field, we confirmed that the reason for the “off” mode is the coupling between the different MP modes, while the “on”mode is the excitation of MP. The optical switch we proposed may be applied to radiation cooling and optical satellite communication.
In the realm of RPGs, creating immersive, persona-driven dialogues remains a challenge, especially in intricate settings like Call of Cthulhu (CoC). Existing methodologies often falter in portraying character personas...
详细信息
Dear editor,Visual object tracking, which has attracted increasing attention in the field of general visual understanding, aims to track each temporally changing object in a video sequence, with the target specified o...
Dear editor,Visual object tracking, which has attracted increasing attention in the field of general visual understanding, aims to track each temporally changing object in a video sequence, with the target specified only in the first *** most tracking algorithms have facilitated significant advances in RGB video sequences, object tracking using only RGB information is unreliable under extreme lighting conditions(e.g., dark night, rain, and foggy).
暂无评论