检索结果-内蒙古大学图书馆

Dist-PU: Positive-Unlabeled Learning from a Label Distribution Perspective

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhao, Yunrui Xu, Qianqian Jiang, Yangbangyan Wen, Peisong Huang, Qingming School of Computer Science and Technology University of Chinese Academy of Sciences China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS China State Key Laboratory of Information Security Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences China

Positive-Unlabeled (PU) learning tries to learn binary classifiers from a few labeled positive examples with many unlabeled ones. Compared with ordinary semi-supervised learning, this task is much more challenging due to the absence of any known negative labels. While existing cost-sensitive-based methods have achieved state-of-the-art performances, they explicitly minimize the risk of classifying unlabeled data as negative samples, which might result in a negative-prediction preference of the classifier. To alleviate this issue, we resort to a label distribution perspective for PU learning in this paper. Noticing that the label distribution of unlabeled data is fixed when the class prior is known, it can be naturally used as learning supervision for the model. Motivated by this, we propose to pursue the label distribution consistency between predicted and ground-truth label distributions, which is formulated by aligning their expectations. Moreover, we further adopt the entropy minimization and Mixup regularization to avoid the trivial solution of the label distribution consistency on unlabeled data and mitigate the consequent confirmation bias. Experiments on three benchmark datasets validate the effectiveness of the proposed method. Code available at: https://***/Ray-rui/Dist-PU-Positive-UnlabeledLearning-from-a-Label-Distribution-Perspective. Copyright © 2022, The Authors. All rights reserved.

关键词： Entropy

Order-preserving pattern mining with forgetting mechanism

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Yan Ma, Chenyu Gao, Rong Wu, Youxi Li, Jinyan Wang, Wenjian Wu, Xindong School of Economics and Management Hebei University of Technology Tianjin300400 China School of Artificial Intelligence Hebei University of Technology Tianjin300400 China School of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen518055 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China School of Computer and Information Technology Shanxi University Taiyuan237016 China Key Laboratory of Knowledge Engineering with Big Data The Ministry of Education of China Hefei University of Technology Hefei230009 China

Order-preserving pattern (OPP) mining is a type of sequential pattern mining method in which a group of ranks of time series is used to represent an OPP. This approach can discover frequent trends in time series. Existing OPP mining algorithms consider data points at different time to be equally important;however, newer data usually have a more significant impact, while older data have a weaker impact. We therefore introduce the forgetting mechanism into OPP mining to reduce the importance of older data. This paper explores the mining of OPPs with forgetting mechanism (OPF) and proposes an algorithm called OPF-Miner that can discover frequent OPFs. OPF-Miner performs two tasks, candidate pattern generation and support calculation. In candidate pattern generation, OPF-Miner employs a maximal support priority strategy and a group pattern fusion strategy to avoid redundant pattern fusions. For support calculation, we propose an algorithm called support calculation with forgetting mechanism, which uses prefix and suffix pattern pruning strategies to avoid redundant support calculations. The experiments are conducted on nine datasets and 12 alternative algorithms. The results verify that OPF-Miner is superior to other competitive algorithms. More importantly, OPF-Miner yields good clustering performance for time series, since the forgetting mechanism is employed. Copyright © 2024, The Authors. All rights reserved.

关键词： Miners

Asymmetric Cross-Scale Alignment for Text-Based Person Search

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ji, Zhong Hu, Junhua Liu, Deyin Wu, Lin Yuanbo Zhao, Ye The School of Electrical and Information Engineering Tianjin University Tianjin300072 China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230039 China Department of Computer Science Swansea University SA1 8EN United Kingdom The Key Laboratory of Knowledge Engineering with Big Data School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China

Text-based person search (TBPS) is of significant importance in intelligent surveillance, which aims to retrieve pedestrian images with high semantic relevance to a given text description. This retrieval task is characterized with both modal heterogeneity and fine-grained matching. To implement this task, one needs to extract multi-scale features from both image and text domains, and then perform the cross-modal alignment. However, most existing approaches only consider the alignment confined at their individual scales, e.g., an image-sentence or a region-phrase scale. Such a strategy adopts the presumable alignment in feature extraction, while overlooking the cross-scale alignment, e.g., image-phrase. In this paper, we present a transformer-based model to extract multi-scale representations, and perform Asymmetric Cross-Scale Alignment (ACSA) to precisely align the two modalities. Specifically, ACSA consists of a global-level alignment module and an asymmetric cross-attention module, where the former aligns an image and texts on a global scale, and the latter applies the cross-attention mechanism to dynamically align the cross-modal entities in region/image-phrase scales. Extensive experiments on two benchmark datasets CUHK-PEDES and RSTPReid demonstrate the effectiveness of our approach. Codes are available at https://***/mulhjh/ACSA. Copyright © 2022, The Authors. All rights reserved.

关键词： Alignment

DGA-Net: Dynamic gaussian attention network for sentence semantic matching

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Kun Lv, Guangyi Wang, Meng Chen, Enhong Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology China School of Computer Science and Information Engineering Hefei University of Technology China School of Computer Science and Technology University of Science and Technology of China China

Sentence semantic matching requires an agent to determine the semantic relation between two sentences, where much recent progress has been made by advancement of representation learning techniques and inspiration of human behaviors. Among all these methods, attention mechanism plays an essential role by selecting important parts effectively. However, current attention methods either focus on all the important parts in a static way or only select one important part at one attention step dynamically, which leaves a large space for further improvement. To this end, in this paper, we design a novel Dynamic Gaussian Attention Network (DGA-Net) to combine the advantages of current static and dynamic attention methods. More specifically, we first leverage pre-trained language model to encode the input sentences and construct semantic representations from a global perspective. Then, we develop a Dynamic Gaussian Attention (DGA) to dynamically capture the important parts and corresponding local contexts from a detailed perspective. Finally, we combine the global information and detailed local information together to decide the semantic relation of sentences comprehensively and precisely. Extensive experiments on two popular sentence semantic matching tasks demonstrate that our proposed DGA-Net is effective in improving the ability of attention mechanism. © 2021, CC BY.

关键词： Gaussian distribution

Web Log Analysis in Genealogy System

学校读者我要写书评

暂无评论

Web Log Analysis in Genealogy System

IEEE International Conference on Big knowledge (ICBK)

作者： Xiaojian Liu Yi Zhu Shengwei Ji Ministry of Education Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) China

ISBN: (数字)9781728181561

ISBN: (纸本)9781728181578

A large amount of log data is generated every moment in many real-world applications. System logs, mobile application logs, web logs etc., all of which contain rich information and can be analyzed for valuable information. At the same time, genealogy attracts more and more attention in recent decades, especially for Chinese. People utilize the genealogy system to seek roots, find source of family, build a family tree and so on. Due to the complexity of genealogy data and specific features of genealogy system, how to extract and analyze the valued genealogy information effectively is a huge challenge. Motivated by this, we propose a novel analysis method using web logs in genealogy system for drawing user profile and providing personalized recommendations. More specifically, firstly, all web logs are extracted from genealogy system based on the enhanced logs which record the behaviors and data of user. Secondly, the extracted logs are formatted for analysis, and we analyze the logs to extract various user-related attributes for drawing user profile. Finally, personalized recommendations like interested people and family tree are provided for each user in system. The high availability and effectiveness of our proposed method is verified on genealogy system-Huapu system.

关键词： data mining databases data visualization Tools Big data Feature extraction knowledge engineering

An Abnormal data Analysis and Processing Method for Genealogy Graph databases

学校读者我要写书评

暂无评论

An Abnormal Data Analysis and Processing Method for Genealog...

IEEE International Conference on Big knowledge (ICBK)

作者： Jianxuan Shao Guliu Liu Shengwei Ji Ministry of Education Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) China

ISBN: (数字)9781728181561

ISBN: (纸本)9781728181578

Large amounts of data are generated continually in the real world. The objects in the data and the relationships between them have become increasingly complex. Graph is a powerful tool for representing these data and the complex relationships between them. To effectively describe the entities and connections in these data, the concept of a knowledge graph was proposed, and knowledge graph has become one of the bases for storing graph data, and the importance of it is self-evident. Genealogy data is a kind of graph data where nodes are used to represent the person in the genealogy data, and edges are used to represent the relationship between the person. Moreover, in a genealogy graph database, the "critical" relationship that is unique for an entity is defined. In contrast, the abnormal data derive from the existence of multiple "critical" relationships between entities. In a genealogy graph, abnormal data will cause the wrong relationships and redundant entities. To avoid such abnormal data in genealogy graph database, the abnormal data are categorized into four different types, and the corresponding processing methods are proposed for each type of abnormal data, respectively. The experiment results demonstrate that the processing method can effectively solve these abnormal data.

关键词： databases Biology Task analysis Anomaly detection data models knowledge engineering Big data

Rule-enhanced Noisy knowledge Graph Embedding via Low-quality Error Detection

学校读者我要写书评

暂无评论

Rule-enhanced Noisy Knowledge Graph Embedding via Low-qualit...

IEEE International Conference on Big knowledge (ICBK)

作者： Yan Hong Chenyang Bu Tingting Jiang Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) Ministry of Education China

ISBN: (数字)9781728181561

ISBN: (纸本)9781728181578

knowledge graphs (KGs) have been widely applied in many fields such as recommendation systems and knowledge reasoning. Embedding KGs into a continuous vector space has quickly gained significant attention. However, most traditional KG embedding models assume that all the facts in the existing KGs are completely correct, ignoring that KG construction usually involves automatic mechanisms. These automatic construction processes inevitably generate a lot of noises and conflicts, including low-quality errors (e.g., entity type errors). Moreover, these low-quality noises could greatly influence the quality of rule extraction, which may reduce the efficiency of Rule-Guided Embedding model (RUGE). To address this problem, an efficient method to eliminate those entity type errors in triples is proposed and applied to RUGE. Experimental results demonstrate that the filtering of low-quality noises can greatly improve the accuracy of knowledge representation learning as well as the quality of rules, further illustrating the effectiveness of our method.

关键词： Noise measurement Semantics knowledge representation data mining Predictive models data models

Synthetic Instance Segmentation from Semantic Image Segmentation Masks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Shen, Yuchen Zhang, Dong Zhang, Zhao Fu, Liyong Ye, Qiaolin College of Information Science and Technology & Artificial Intelligence Nanjing Forestry University Jiangsu Nanjing210037 China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Hefei230009 China College of Information Science and Technology Nanjing Forestry University Jiangsu Nanjing210037 China Institute of Forest Resource Information Techniques Chinese Academy of Forestry Beijing100091 China

In recent years, instance segmentation has garnered significant attention across various applications. However, training a fully-supervised instance segmentation model requires costly both instance-level and pixel-level annotations. In contrast, weakly-supervised instance segmentation methods, such as those using image-level class labels or point labels, often struggle to satisfy the accuracy and recall requirements of practical scenarios. In this paper, we propose a novel paradigm called Synthetic Instance Segmentation (SISeg). SISeg achieves instance segmentation results by leveraging image masks generated by existing semantic segmentation models, and it is highly efficient as we do not require additional training for semantic segmentation or the use of instance-level image annotations. In other words, the proposed model does not need extra manpower or higher computational expenses. Specifically, we first obtain a semantic segmentation mask of the input image via an existent semantic segmentation model. Then, we calculate a displacement field vector for each pixel based on the segmentation mask, which can indicate representations belonging to the same class but different instances, i.e., obtaining the instance-level object information. Finally, the instance segmentation results are refined by a learnable category-agnostic object boundary branch. Extensive experimental results on two challenging datasets highlight the effectiveness of SISeg in achieving competitive results when compared to state-of-the-art methods, especially fully-supervised methods. The code will be released at: SISeg Copyright © 2023, The Authors. All rights reserved.

关键词： Semantic Segmentation

An integrated classification model for massive short texts with few words 19

学校读者我要写书评

暂无评论

An integrated classification model for massive short texts w...

2019 International Conference on Robotics Systems and Vehicle Technology, RSVT 2019

作者： Tang, Xuetao Zhu, Yi Hu, Xuegang Li, Peipei Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology China

ISBN: (纸本)9781450362429

The excellent performance of short texts classification has emerged in the past few years. However, massive short texts with few words like invoice data are different with traditional short texts like tweets in its no contextual and less semantic information, which hinders the application of conventional classification algorithms. To address these problems, we propose an integrated classification model for massive short texts with few words. More specifically, the word embedding model is introduced to train the word vectors of massive short texts with few words to form the feature space, and then the vector representation of each instance in texts is trained based on sentence embedding. With this integrated model, higher level representations are learned from massive short texts with few words. It can boost the performance of the base subsequent classifiers such as K-Nearest Neighbor. Extensive experiments conducted on dataset including 16 million real data demonstrate the superior classification performance of our proposed model compared with all competing state-of-the-art models. © 2019 Association for Computing Machinery.

关键词： Embeddings