Generative adversarial networks (GANs) has received wide attention in the machinelearning field because it can generate real-like data by estimating real data probability distribution. GANs has been successfully appl...
详细信息
Generative adversarial networks (GANs) has received wide attention in the machinelearning field because it can generate real-like data by estimating real data probability distribution. GANs has been successfully applied to many fields such as computer vision, pattern recognition, natural language processing and so on. By now many kinds of extended models of GANs have been proposed and investigated by different researchers from different viewpoints. Although there are a few review papers on the extended models of GANs in the literature, some remarkable extensions of GANs published in the recent years are not included in these surveys. This paper attempts to provide the potential readers with a recent advance on GANs by surveying its twelve representative variants. Furthermore, we also present the lineage of the extended models of GANs. This paper can provide researchers engaged in related works with very valuable help.
Knowledge reduction in decision table is important in both theory and application, and it outputs a minimal algorithm as a result. Set of the samples fitting the minimal algorithm is a concept over the set of all poss...
详细信息
Knowledge reduction in decision table is important in both theory and application, and it outputs a minimal algorithm as a result. Set of the samples fitting the minimal algorithm is a concept over the set of all possible instances. But in unfamiliar environment, decision table is obtained randomly. So the obtained concept is an approximation to a potential target concept. We discuss the model of this concept learning, sample complexity of its hypothesis space and PAC-learnability of its target concept class.
Patch-level features are essential for achieving good performance in computer vision tasks. Besides well-known pre-defined patch-level descriptors such as scaleinvariant feature transform (SIFT) and histogram of orien...
详细信息
Graph Neural Networks (GNNs) have achieved great success in various data mining tasks but they heavily rely on a large number of annotated nodes, requiring considerable human efforts. Despite the effectiveness of exis...
详细信息
Ordinal decision tree (ODT) can effectively deal with monotonic classification problems. However, it is difficult for the existing ordinal decision tree algorithms to learning ODT from large data sets. Based on the va...
详细信息
ISBN:
(纸本)9781479986989
Ordinal decision tree (ODT) can effectively deal with monotonic classification problems. However, it is difficult for the existing ordinal decision tree algorithms to learning ODT from large data sets. Based on the variable consistency dominance based rough set approach (VC-DRSA), an ordinal random forest algorithm is proposed in this paper. Combining with the computing framework of MapReduce, the proposed ordinal random forest algorithm is paralleled on the platform of Hadoop, which improves the efficiency of the proposed algorithm. The feasibility and effectiveness of the proposed algorithm is verified by the experimental results.
Multi-view clustering has attracted more attention recently since many real-world data are comprised of different representations or views. Recent multi-view clustering works mainly exploit the instance consistency to...
详细信息
Multi-view clustering has attracted more attention recently since many real-world data are comprised of different representations or views. Recent multi-view clustering works mainly exploit the instance consistency to obtain the shared representations across different views, and apply a single-view clustering method to perform data partitions. However, these existing methods often ignore the inconsistency of instance associations within the views, which may enlarge the intra-class diversity among the views and therefore degrade the clustering performance. To address this issue, this paper proposes an efficient mutual contrastive teacher-student leaning (MC-TSL) model to enhance the multi-view clustering, which is the first attempt to study the inconsistency distillation for consistency learning. First, the proposed MC-TSL approach exploits a view-specific encoder with two heads, an instance encoding head and a semantic distillation head, respectively, for capturing the consistent and discriminative feature representations. To be specific, the former head exploits a cross-view contrastive learning method to obtain a redundancy-free consistent representation at the instance level, while the latter head designs a mutual teacher-student learning module to capture the intra-view information at semantic level. By training these two heads in an end-to-end manner, the discriminative multi-view embeddings are efficiently obtained and refined by minimizing the weighted sum of the reconstruction loss, contrastive loss and contrast distillation loss. Extensive experiments verify the superiorities of the proposed MC-TSL framework and show its competitive clustering performances.
Graph Neural Networks (GNNs) have achieved great success in various data mining tasks but they heavily rely on a large number of annotated nodes, requiring considerable human efforts. Despite the effectiveness of exis...
详细信息
ISBN:
(数字)9798350317152
ISBN:
(纸本)9798350317169
Graph Neural Networks (GNNs) have achieved great success in various data mining tasks but they heavily rely on a large number of annotated nodes, requiring considerable human efforts. Despite the effectiveness of existing GNN-based Active learning (AL) methods, they assume that the annotated lab.ls are always correct, which is contradictory to the error-prone lab.ling process in a practical crowdsourcing environment. Besides, due to this impractical assumption, existing works only focus on optimizing the node selection in AL but neglect optimizing the lab.ling process. Therefore, we present NC-ALG, the first GNN-based AL framework that optimizes both the node selection and node lab.ling process under a noisy crowd. For node selection, NC-ALG introduces a new measurement to model influence reliability and an effective influence maximization objective to select nodes. For node lab.ling, NC-ALG significantly reduces the lab.ling cost by considering the model-predicted lab.ls and the lab.ls of mirror nodes. To the best of our knowledge, this is the first attempt to consider GNN-based AL under the practical noisy crowd. Empirical studies on public datasets demonstrate that NC-ALG significantly outperforms existing methods in terms lab.ling efficiency. Notably, it only takes NC-ALG one-third of the lab.ling budget that the competitive baseline GRAIN needs to achieve an accuracy of 70.7 % on PubMed.
The rapid advancements in artificial intelligence(AI)are catalyzing transformative changes in atomic modeling,simulation,and ***-driven potential energy models havedemonstrated the capability to conduct large-scale,lo...
详细信息
The rapid advancements in artificial intelligence(AI)are catalyzing transformative changes in atomic modeling,simulation,and ***-driven potential energy models havedemonstrated the capability to conduct large-scale,long-duration simulations with the accuracy of ab initio electronic structure ***,the model generation process remains a bottleneck for large-scale *** propose a shift towards a model-centric ecosystem,wherein a large atomic model(LAM),pretrained across multiple disciplines,can be efficiently fine-tuned and distilled for various downstream tasks,thereby establishing a new framework for molecular *** this study,we introduce the DPA-2 architecture as a prototype for ***-trained on a diverse array of chemical and materials systemsusing a multi-task approach,DPA-2demonstrates superior generalization capabilities across multiple downstream tasks compared to the traditional single-task pre-training and fine-tuning *** approach sets the stage for the development and broad application of LAMs in molecular and materials simulation research.
Artificial intelligence (AI) is transforming scientific research, including proteomics. Advances in mass spectrometry (MS)-based proteomics data quality, diversity, and scale, combined with groundbreaking AI technique...
详细信息
The rapid advancements in artificial intelligence (AI) are catalyzing transformative changes in atomic modeling, simulation, and design. AI-driven potential energy models have demonstrated the capability to conduct la...
详细信息
暂无评论