检索结果-内蒙古大学图书馆

Gray Learning from Non-IID data with Out-of-distribution Samples

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhao, Zhilin Cao, Longbing Wang, Chang-Dong The Data Science Lab School of Computing and DataX Research Centre Macquarie University SydneyNSW2109 Australia The School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Computational Science Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

The integrity of training data, even when annotated by experts, is far from guaranteed, especially for non-IID datasets comprising both in- and out-of-distribution samples. In an ideal scenario, the majority of samples would be in-distribution, while samples that deviate semantically would be identified as out-of-distribution and excluded during the annotation process. However, experts may erroneously classify these out-of-distribution samples as in-distribution, assigning them labels that are inherently unreliable. This mixture of unreliable labels and varied data types makes the task of learning robust neural networks notably challenging. We observe that both in- and out-of-distribution samples can almost invariably be ruled out from belonging to certain classes, aside from those corresponding to unreliable ground-truth labels. This opens the possibility of utilizing reliable complementary labels that indicate the classes to which a sample does not belong. Guided by this insight, we introduce a novel approach, termed Gray Learning (GL), which leverages both ground-truth and complementary labels. Crucially, GL adaptively adjusts the loss weights for these two label types based on prediction confidence levels. By grounding our approach in statistical learning theory, we derive bounds for the generalization error, demonstrating that GL achieves tight constraints even in non-IID settings. Extensive experimental evaluations reveal that our method significantly outperforms alternative approaches grounded in robust statistics. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

Hyperbolic Geometric Latent Diffusion Model for Graph Generation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Fu, Xingcheng Gao, Yisen Wei, Yuecen Sun, Qingyun Peng, Hao Li, Jianxin Li, Xianxian Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Institute of Artificial Intelligence Beihang University Beijing China School of Software Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing China

Diffusion models have made significant contributions to computer vision, sparking a growing interest in the community recently regarding the application of them to graph generation. Existing discrete graph diffusion models exhibit heightened computational complexity and diminished training efficiency. A preferable and natural way is to directly diffuse the graph within the latent space. However, due to the non-Euclidean structure of graphs is not isotropic in the latent space, the existing latent diffusion models effectively make it difficult to capture and preserve the topological information of graphs. To address the above challenges, we propose a novel geometrically latent diffusion framework HypDiff. Specifically, we first establish a geometrically latent space with interpretability measures based on hyperbolic geometry, to define anisotropic latent diffusion processes for graphs. Then, we propose a geometrically latent diffusion process that is constrained by both radial and angular geometric properties, thereby ensuring the preservation of the original topological properties in the generative graphs. Extensive experimental results demonstrate the superior effectiveness of HypDiff for graph generation with various topologies. Copyright © 2024, The Authors. All rights reserved.

关键词： Topology

knowledge graph enhanced neural collaborative recommendation

学校读者我要写书评

暂无评论

Expert Systems with Applications 2021年 164卷 113992-113992页

作者： Sang, Lei Xu, Min Qian, Shengsheng Wu, Xindong Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) Ministry of Education Hefei 230009 China Faculty of Engineering and Information Technology University of Technology Sydney Sydney 2007 Australia School of Computer Science and Information Engineering Hefei University of Technology Hefei 230009 China Institute of Automation Chinese Academy of Sciences Beijing 100190 China Mininglamp Academy of Sciences Mininglamp Technology Beijing 100084 China

Existing neural collaborative filtering (NCF) recommendation methods suffer from severe sparsity problem. knowledge Graph (KG), which commonly consists of fruitful connected facts about items, presents an unprecedented opportunity to alleviate the sparsity problem. However, pure NCF models can hardly model the high-order connectivity in KG, and ignores complex pairwise correlations between user/item embedding dimensions. To address these problems, we propose a novel knowledge graph enhanced Neural Collaborative Recommendation (K-NCR) framework, which effectively combines user–item interaction information and auxiliary knowledge information for recommendation task into three parts: (1) For items, the proposed propagating model learns the representation of item entity. It recursively aggregates information from its multi-hop neighbours in KG, and employs an attention mechanism to discriminate the importance of the relation type to mine users’ potential preferences. (2) For users, another heterogeneous attention weights are leveraged to strengthen the embedding learning of users. (3) The user and item embeddings are then fed into a newly designed two-dimensional interaction map with convolutional hidden layers to model the complex pairwise correlations between their embedding dimensions explicitly. Extensive experimental results on three benchmark datasets demonstrate the effectiveness of our K-NCR framework. © 2020

关键词： Attention mechanism Graph convolutional networks knowledge graph Neural collaborative filtering Recommendation system

On the Stability and Generalization of Triplet Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Jun Chen, Hong Jiang, Xue Gu, Bin Li, Weifu Gong, Tieliang Zheng, Feng College of Informatics Huazhong Agricultural University Wuhan430070 China College of Science Huazhong Agricultural University Wuhan430070 China Engineering Research Center of Intelligent Technology for Agriculture Ministry of Education Wuhan430070 China Key Laboratory of Smart Farming for Agricultural Animals Wuhan430070 China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates School of Computer Science and Technology Xi'an Jiaotong University Xi’an710049 China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Ministry of Education Xi’an710049 China

Triplet learning, i.e. learning from triplet data, has attracted much attention in computer vision tasks with an extremely large number of categories, e.g., face recognition and person re-identification. Albeit with rapid progress in designing and applying triplet learning algorithms, there is a lacking study on the theoretical understanding of their generalization performance. To fill this gap, this paper investigates the generalization guarantees of triplet learning by leveraging the stability analysis. Specifically, we establish the first general high-probability generalization bound for the triplet learning algorithm satisfying the uniform stability, and then 1 obtain the excess risk bounds of the order (Equation presented). for both stochastic gradient descent (SGD) and regularized risk minimization (RRM), where 2n is approximately equal to the number of training samples. Moreover, an optimistic generalization bound in expectation as fast as O(n−1) is derived for RRM in a low noise case via the on-average stability analysis. Finally, our results are applied to triplet metric learning to characterize its theoretical underpinning. Copyright © 2023, The Authors. All rights reserved.

关键词： Learning algorithms

Adaptive structure-constrained robust latent low-rank coding for image recovery

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhang, Zhao Wang, Lei Li, Sheng Wang, Yang Zhang, Zheng Zha, Zhengjun Wang, Meng School of Computer Science and Technology Soochow University Suzhou215006 China Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology School of Computer Science and Information Engineering Hefei University of Technology Hefei China Department of Computer Science University of Georgia 549 Boyd GSRC AthensGA30602 Shenzhen China School of Information Science and Technology University of Science and Technology of China Hefei China

In this paper, we propose a robust representation learning model called Adaptive Structure-constrained Low-Rank Coding (AS-LRC) for the latent representation of data. To recover the underlying subspaces more accurately, AS-LRC seamlessly integrates an adaptive weighting based block-diagonal structure-constrained low-rank representation and the group sparse salient feature extraction into a unified framework. Specifically, AS-LRC performs the latent decomposition of given data into a low-rank reconstruction by a block-diagonal codes matrix, a group sparse locality-adaptive salient feature part and a sparse error part. To enforce the block-diagonal structures adaptive to different real datasets for the low-rank recovery, AS-LRC clearly computes an auto-weighting matrix based on the locality-adaptive features and multiplies by the low-rank coefficients for direct minimization at the same time. This encourages the codes to be block-diagonal and can avoid the tricky issue of choosing optimal neighborhood size or kernel width for the weight assignment, suffered in most local geometrical structures-preserving low-rank coding methods. In addition, our AS-LRC selects the L2,1-norm on the projection for extracting group sparse features rather than learning low-rank features by Nuclear-norm regularization, which can make learnt features robust to noise and outliers in samples, and can also make the feature coding process efficient. Extensive visualizations and numerical results demonstrate the effectiveness of our AS-LRC for image representation and recovery. Copyright © 2019, The Authors. All rights reserved.

关键词： Recovery

Refining BERT embeddings for document hashing via mutual information maximization

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ou, Zijing Su, Qinliang Yu, Jianxing Zhao, Ruihui Zheng, Yefeng Liu, Bang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China School of Artificial Intelligence Sun Yat-sen University Guangdong China Tencent Jarvis Lab Rali & Mila Université de Montréal Guangdong Key Lab. of Big Data Analysis and Processing Guangzhou China Key Lab. of Machine Intelligence and Advanced Computing Ministry of Education China

Existing unsupervised document hashing methods are mostly established on generative models. Due to the difficulties of capturing long dependency structures, these methods rarely model the raw documents directly, but instead to model the features extracted from them (e.g. bag-of-words (BOW), TFIDF). In this paper, we propose to learn hash codes from BERT embeddings after observing their tremendous successes on downstream tasks. As a first try, we modify existing generative hashing models to accommodate the BERT embeddings. However, little improvement is observed over the codes learned from the old BOW or TFIDF features. We attribute this to the reconstruction requirement in the generative hashing, which will enforce irrelevant information that is abundant in the BERT embeddings also compressed into the codes. To remedy this issue, a new unsupervised hashing paradigm is further proposed based on the mutual information (MI) maximization principle. Specifically, the method first constructs appropriate global and local codes from the documents and then seeks to maximize their mutual information. Experimental results on three benchmark datasets demonstrate that the proposed method is able to generate hash codes that outperform existing ones learned from BOW features by a substantial margin. Copyright © 2021, The Authors. All rights reserved.

关键词： Embeddings

DynaInsRemover: A Real-time Dynamic Instance-Aware Static 3D LiDAR Mapping Framework for Dynamic Environment

学校读者我要写书评

暂无评论

DynaInsRemover: A Real-time Dynamic Instance-Aware Static 3D...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Huanfeng Zhao Meibao Yao Xueming Xiao Bo Zheng Intelligent Robotics Lab (IRL) School of Artificial Intelligence Jilin University Changchun China Engineering Research Center of Knowledge-Driven Human-Machine Intelligence Ministry of Education China CVIR Lab Changchun University of Science and Technology Changchun China Key Lab of Opto-Electronic Measurement and Optical Information Transmission Technology Shanghai Aerospace Control Technology Institute Shanghai China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Dynamic objects diversify the distribution of point cloud in the map, degrading the performance of the robotic downstream tasks. To address this problem, we present a novel real-time dynamic instance-aware static mapping framework called DynaInsRemover, which exploits the geometric discrepancies between instances to efficiently remove dynamic objects and preserve more details of static map. It contains the Instance Occupancy Check module for initial dynamic instance proposal and the Instance Belief Update module for reverting false positives. We quantitatively evaluate our approach performance on the SemanticKITTI dataset and validate it in a real-world environment. Experimental evaluations show that our method achieves very promising results in dynamic environments. The implementation of our method is available as open source at: https://***/Zhaohuanfeng/***.

关键词： Point cloud compression Three-dimensional displays Laser radar Real-time systems Windows Proposals Object recognition

LPL-SLAM: LiDAR SLAM with Plane and Line Optimization for Structural Environment

学校读者我要写书评

暂无评论

LPL-SLAM: LiDAR SLAM with Plane and Line Optimization for St...

On-Line Conference (ONCON), Industrial Electronics Society Annual

作者： Huanfeng Zhao Meibao Yao Xueming Xiao Bo Zheng Tao Cao Tao Hu Intelligent Robotics Lab (IRL) School of Artificial Intelligence Jilin University Changchun China Engineering Research Center of Knowledge-Driven Human-Machine Intelligence Ministry of Education China CVIR Lab Changchun University of Science and Technology Changchun China Key Lab of Opto-Electronic Measurement and Optical Information Transmission Technology Shanghai Aerospace Control Technology Institute Shanghai China

In LiDAR SLAM, data association of sparse LiDAR scan and high computational complexity of point-to-model metrics limit real-time applications of joint optimization module like Bundle Adjustment in Visual SLAM, which leads to cumulative errors deteriorating performance. To address this drawback, in this paper, we propose LPL-SLAM with plane and line optimization for the structural environment. Since plane and line primitives are ubiquitous in man-made environments, we treat the primitives as landmarks to process scans. We introduce line and plane factors relying on line-to-line and plane-to-plane metrics to optimize keyframe poses, planes and lines. With the line and plane factors, our system avoids a large-scale optimization problem and yields accurate and consistent tracking poses. Experimental results demonstrate that LPL-SLAM outperforms the state-of-the-art algorithms and achieves real-time performance.

关键词：

Violence Detection In Videos via Motion-Guided Global and Local Views

学校读者我要写书评

暂无评论

Violence Detection In Videos via Motion-Guided Global and Lo...

IEEE International Conference on data Science in Cyberspace (DSC)

作者： Ning Su Lijuan Sun Yutong Gao Jingchen Wu Xu Wu Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education School of Cyberspace Security BUPT School of Economics and Management Beijing University of Posts and Telecommunications Beijing China Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China School of Computer Science (National Pilot Software Engineering School) BUPT

Video violence detection aims to locate the time window in which violent behavior occurs. Most methods focus on utilizing RGB features directly or only fusing RGB and audio features, ignoring the effective exploitation of motion information carried in optical flow. This lack of emphasis on motion information may impact the overall accuracy of violence detection. Moreover, we observe that videos contain strong local correlations, so it is insufficient to analyze only from a holistic perspective without capturing finer details. Therefore, in this paper, we design a novel Global-and-Local Cross-Modal Network (GL-CMN) for violence detection, which effectively integrates motion information and multi-granularity features from target videos. Specifically, we first propose a Motion-Guided Attention Module (MGAM) to obtain enhanced visual features by calibrating RGB features through optical flow features. Secondly, The enhanced features are simultaneously fed into two parallel branches of the network. The global branch fuses the visual and audio features into holistic representations. The local branch extracts multi-scale temporal dependencies through dilated convolutions. Experiments demonstrate that our method exhibits significant improvement compared to previous state-of-the-art methods on the XD-Violence dataset.

关键词：