检索结果-内蒙古大学图书馆

Geometry Interaction knowledge Graph Embeddings

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Cao, Zongsheng Xu, Qianqian Yang, Zhiyong Cao, Xiaochun Huang, Qingming State Key Laboratory of Information Security Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China Peng Cheng Laboratory Shenzhen China

knowledge graph (KG) embeddings have shown great power in learning representations of entities and relations for link prediction tasks. Previous work usually embeds KGs into a single geometric space such as Euclidean space (zero curved), hyperbolic space (negatively curved) or hyperspherical space (positively curved) to maintain their specific geometric structures (e.g., chain, hierarchy and ring structures). However, the topological structure of KGs appears to be complicated, since it may contain multiple types of geometric structures simultaneously. Therefore, embedding KGs in a single space, no matter the Euclidean space, hyperbolic space or hyperspheric space, cannot capture the complex structures of KGs accurately. To overcome this challenge, we propose Geometry Interaction knowledge graph Embeddings (GIE), which learns spatial structures interactively between the Euclidean, hyperbolic and hyperspherical spaces. Theoretically, our proposed GIE can capture a richer set of relational information, model key inference patterns, and enable expressive semantic matching across entities. Experimental results on three well-established knowledge graph completion benchmarks show that our GIE achieves the state-of-the-art performance with fewer parameters. © 2022, CC BY.

关键词： knowledge graph

Improve Cross-domain Mixed Sampling with Guidance Training for Adaptive Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhou, Wenlve Zhou, Zhiheng Wang, Tianlei Zeng, Delu School of Electronic and Information Engineering South China University of Technology Guangdong Guangzhou510641 China Key Laboratory of Big Data and Intelligent Robot Ministry of Education South China University of Technology Guangzhou510641 China The Department of Intelligent Manufacturing Wuyi University Jiangmen529020 China

Unsupervised Domain Adaptation (UDA) endeavors to adjust models trained on a source domain to perform well on a target domain without requiring additional annotations. In the context of domain adaptive semantic segmentation, which tackles UDA for dense prediction, the goal is to circumvent the need for costly pixel-level annotations. Typically, various prevailing methods baseline rely on constructing intermediate domains via cross-domain mixed sampling techniques to mitigate the performance decline caused by domain gaps. However, such approaches generate synthetic data that diverge from real-world distributions, potentially leading the model astray from the true target distribution. To address this challenge, we propose a novel auxiliary task called Guidance Training. This task facilitates the effective utilization of cross-domain mixed sampling techniques while mitigating distribution shifts from the real world. Specifically, Guidance Training guides the model to extract and reconstruct the target-domain feature distribution from mixed data, followed by decoding the reconstructed target-domain features to make pseudo-label predictions. Importantly, integrating Guidance Training incurs minimal training overhead and imposes no additional inference burden. We demonstrate the efficacy of our approach by integrating it with existing methods, consistently improving performance. The implementation will be available at https://***/Wenlve-Zhou/Guidance-Training. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

Open-Vocabulary X-ray Prohibited Item Detection via Fine-tuning CLIP

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lin, Shuyang Jia, Tong Wang, Hao Ma, Bowen Li, Mingyuan Chen, Dongyue The College of Information Science and Engineering Northeastern University Liaoning Shenyang110819 China The Key Laboratory of Data Analytics and Optimization for Smart Industry Ministry of Education Northeastern University Liaoning Shenyang110819 China The Foshan Graduate School of Innovation Northeastern University Guangdong Foshan528311 China

X-ray prohibited item detection is an essential component of security check and categories of prohibited item are continuously increasing in accordance with the latest laws. Previous works all focus on close-set scenarios, which can only recognize known categories used for training and often require time-consuming as well as labor-intensive annotations when learning novel categories, resulting in limited real-world applications. Although the success of vision-language models (e.g. CLIP) provides a new perspectives for open-set X-ray prohibited item detection, directly applying CLIP to X-ray domain leads to a sharp performance drop due to domain shift between X-ray data and general data used for pre-training CLIP. To address aforementioned challenges, in this paper, we introduce distillation-based open-vocabulary object detection (OVOD) task into X-ray security inspection domain by extending CLIP to learn visual representations in our specific X-ray domain, aiming to detect novel prohibited item categories beyond base categories on which the detector is trained. Specifically, we propose X-ray feature adapter and apply it to CLIP within OVOD framework to develop OVXD model. X-ray feature adapter containing three adapter submodules of bottleneck architecture, which is simple but can efficiently integrate new knowledge of X-ray domain with original knowledge, further bridge domain gap and promote alignment between X-ray images and textual concepts. Extensive experiments conducted on PIXray and PIDray datasets demonstrate that proposed method performs favorably against other baseline OVOD methods in detecting novel categories in X-ray scenario. It outperforms previous best result by 15.2 AP50 and 1.5 AP50 on PIXray and PIDray with achieving 21.0 AP50 and 27.8 AP50 respectively. Furthermore, our model can be directly transferred to different X-ray datasets without fine-tuning, verifying its generalization ability. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

Predicting response to patients with gastric cancer via a dynamic-aware model with longitudinal liquid biopsy data

学校读者我要写书评

暂无评论

Gastric cancer : official journal of the International Gastric Cancer Association and the Japanese Gastric Cancer Association 2025年 2025 Jun 17页

作者： Zifan Chen Jie Zhao Yanyan Li Xujiao Feng Yang Chen Yilin Li Xinyu Nan Huimin Liu Bin Dong Lin Shen Li Zhang Center for Data Science Peking University Haidian District Beijing 100080 China. National Engineering Laboratory for Big Data Analysis and Applications Peking University Beijing China. Peking University Changsha Institute for Computing and Digital Economy Changsha China. Department of Gastrointestinal Oncology Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education) Peking University Cancer Hospital and Institute Beijing China. Guangzhou Medical University Guangzhou China. Beijing International Center for Mathematical Research and the New Cornerstone Science Laboratory Peking University Beijing China. Center for Machine Learning Research Peking University Beijing China. Center for Data Science Peking University Haidian District Beijing 100080 China. zhangli_pku@***.

BACKGROUND:Gastric cancer (GC) presents challenges in predicting treatment responses due to its patient-specific heterogeneity. Recently, liquid biopsies have emerged as a valuable data modality, offering essential cellular and molecular insights while facilitating the capture of time-sensitive information. This study aimed to leverage artificial intelligence (AI) technology to analyze longitudinal liquid biopsy data. METHODS:We collected a dataset from longitudinal liquid biopsies of 91 patients at Peking Cancer Hospital, spanning from July 2019 to April 2022. This dataset included 1895 tumor-related cellular images and 1698 tumor marker indices. Subsequently, we introduced the Dynamic-Aware Model (DAM) to predict responses to GC treatment. DAM incorporates dynamic data through AI-engineered components, facilitating an in-depth longitudinal analysis. RESULTS:Utilizing threefold cross-validation, DAM exhibited superior performance compared to traditional cell-counting methods, achieving an AUC of 0.807 in predicting GC treatment responses. In the test set, DAM maintained stable efficacy with an AUC of 0.802. Besides, DAM showed the capability to accurately predict treatment responses based on early treatment data. Moreover, DAM's visual analysis of attention mechanisms identified six dynamic visual features related to focus areas, which were strongly associated with treatment-response. CONCLUSIONS:These findings represent a pioneering effort in applying AI technology to interpret longitudinal liquid biopsy data and employ visual analytics in GC. This approach provides a promising pathway toward precise response prediction and personalized treatment strategies for patients with GC.

关键词： Artificial intelligence Deep learning Gastric cancer Longitudinal liquid biopsy data Treatment response prediction

Hyper-IIoT: A Smart Contract-inspired Access Control Scheme for Resource-constrained Industrial Internet of Things

学校读者我要写书评

暂无评论

IEEE Transactions on Sustainable Computing

IEEE Transactions on Sustainable Computing 2025年

作者： Li, Dun Li, Hongzhi Crespi, Noel Minerva, Roberto Li, Ming Liang, Wei Li, Kuan-Ching Tsinghua University Department of Industrial Engineering China Institut Polytechnique de Paris Samovar Telecom SudParis Palaiseau91120 France Chizhou University College of Big Data and Artificial Intelligence Chizhou247100 China The Hong Kong Polytechnic University Research Institute for Advanced Manufacturing Hung Hom Hong Kong Hunan University of Science and Technology School of Computer Science and Engineering Hunan University of Science and Technology Sanya Research Institute Hunan Key Laboratory for Service Computing and Novel Software Technology China Providence University Dept. of Computer Science and Information Engineering Taiwan

In recent years, the refinements in industrial processes and the increasing complexity of managing privacy-sensitive data in Industrial Internet of Things (IIoT) devices have highlighted the need for secure, robust, and adaptive data management solutions. In this work, we propose a smart contract-assisted access control scheme for IIoT, which employs the Attribute-Based Access Control (ABAC) model to set access permissions for different industrial components. Besides, we defined a storage model and data format for private data by designing and deploying smart contracts to manage system operations and access policies. In addition, the bloom filter component is deployed to optimize the efficiency of contract management and system performance. Experimental results show that in real-world simulations, Hyper-IIoT demonstrates excellent contract execution time control, stable system throughput, and rapid consensus processes that are capable of handling high throughput and efficient consensus in distributed systems, even in large-scale request scenarios. © 2016 IEEE.

关键词： Smart contract

A Hybrid Blockchain Scheme for Tracing Manufacturing Processes and Trading Transactions

学校读者我要写书评

暂无评论

A Hybrid Blockchain Scheme for Tracing Manufacturing Process...

International Symposium on Parallel and Distributed Processing with Applications, ISPA

作者： Ye Yuan Mingxing Yang Ruoting Xiong Yani Sun Xianchao Zhang Wei Ren HuBei Land Resources Vocational College China Gemological Institute China University of Geosciences Wuhan China School of Computing Science University of East Anglia UK Yunnan Key Laboratory of Blockchain Application Technology Yunnan Innovation Institute of Beihang University Kunming China Key Laboratory of Medical Electronics and Digital Health of Zhejiang Province Jiaxing University Jiaxing China State Key Laboratory of Geo-Information Engineering and Key Laboratory of Surveying and Mapping Science and Geospatial Information Technology of MNR Beijing China Ministry of Education Key Laboratory of Data Protection and Intelligent Management (Sichuan University) China School of Computer Science China University of Geosciences Wuhan China

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

Blockchain can be envisioned as an enabling framework in terms of cryptography and distributed computing to construct trusted data records among un-trusted users. It can be applied in two typical scenarios - historical process provenance and transaction tracing, by immutably sequentialized blocks. In the former there exists no tokens; but in the latter token handover among accounts should be cryptographically guaranteed. In some situations, above two applications may be both required. E.g., in the manufacture of a jewel, processing flow by different operators should be recorded for quality guaranteeing, and in its trading stage, the ownership handover should be recorded for value confirmation. To tackle above two requirements, two chains are usually thus demanded. In this paper, we propose a single chain solution to avoid cross-chain burden, by a hybrid block structure. The process data can be imported from the legacy (non-anonymous) information processing system, and transaction data stems from anonymous payment demand for ownership handover. We formally describe and prove token handover model with cryptographical authenticity. We also propose several security enhancements in the design for shortening the length of the chain, and protecting the data confidentiality in the chain. Our design is general and not limited to single application. The experimental results and extensive analysis justified that the performance and security of our proposed scheme is efficient.

关键词： Distributed processing data privacy Manufacturing processes Information processing Handover Throughput data structures Blockchains Delays Periodic structures

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Xiaogeng Li, Minghui Wang, Haoyu Hu, Shengshan Ye, Dengpan Jin, Hai Wu, Libing Xiao, Chaowei School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab China School of Cyber Science and Engineering Wuhan University China Arizona State University United States

Deep neural networks are proven to be vulnerable to backdoor attacks. Detecting the trigger samples during the inference stage, i.e., the test-time trigger sample detection, can prevent the backdoor from being triggered. However, existing detection methods often require the defenders to have high accessibility to victim models, extra clean data, or knowledge about the appearance of backdoor triggers, limiting their practicality. In this paper, we propose the test-time corruption robustness consistency evaluation (TeCo)1, a novel test-time trigger sample detection method that only needs the hard-label outputs of the victim models without any extra information. Our journey begins with the intriguing observation that the backdoor-infected models have similar performance across different image corruptions for the clean images, but perform discrepantly for the trigger samples. Based on this phenomenon, we design TeCo to evaluate test-time robustness consistency by calculating the deviation of severity that leads to predictions' transition across different corruptions. Extensive experiments demonstrate that compared with state-of-the-art defenses, which even require either certain information about the trigger types or accessibility of clean data, TeCo outperforms them on different backdoor attacks, datasets, and model architectures, enjoying a higher AUROC by 10% and 5 times of stability. Copyright © 2023, The Authors. All rights reserved.

关键词： Crime

Solar-driven MEA/ChCl/2-MPZ/MXene-based nanofluid for efficient CO₂ adsorption–desorption

学校读者我要写书评

暂无评论

Separation and Purification Technology 2025年 376卷

作者： Wang, Jianjie Yu, Wei Zhu, Dahai Lyu, Qingyun Ye, Jiayi Wei, Xing Wu, Jiajia Xie, Huaqing Xing, Xing Li, Yifan School of Energy and Materials Shanghai Key Laboratory of Engineering Materials Application and Evaluation Shanghai Polytechnic University Shanghai 201209 China Shanghai Thermophysical Properties Big Data Professional Technical Service Platform Shanghai Engineering Research Center of Advanced Thermal Functional Materials Shanghai 201209 China China Faculty of Engineering McMaster University Hamilton L8S 4L8 Canada

The chemical adsorption method for CO2 capture exhibits exceptional selectivity and capture efficiency. However, conventional strategies still face challenges such as relatively high energy consumption and the inabili... 详细信息

The chemical adsorption method for CO₂ capture exhibits exceptional selectivity and capture efficiency. However, conventional strategies still face challenges such as relatively high energy consumption and the inability to self-regenerate captured CO₂. This study proposed a solar-driven CO₂ adsorption/desorption solution by incorporating MXene nanoparticles with the 2-methylpiperazine (2-MPZ) into a green absorbent eutectic solvent (MEA/ChCl). The prepared MEA/ChCl/2-MPZ/MXene (MC2M) nanofluids exhibit a remarkable enhancement in CO₂ adsorption capacity, which increases from the initial 0.286 g/g for MEA/ChCl to 0.530 g/g. Additionally, the incorporation of MXene plays a pivotal role in boosting the photothermal conversion efficiency, reaching an impressive 89 % under one-sun illumination. This improvement enables the nanofluids to achieve a peak temperature of 62.8℃. Density functional theory calculations reveal that the addition of 2-MPZ accelerates the CO₂ adsorbent adsorption rate, while the incorporation of MXene facilitates efficient desorption. MC2M nanofluid exhibits excellent recyclability, maintaining the adsorption capacity of 0.467 g/g after 10 adsorption–desorption cycles. The practical application highlights the great potential of the developed nanofluid in regulating the CO₂ concentration in a 150 m³ conference room. The nanofluid developed in this study demonstrates the potential to use CO₂ in closed environments, offering valuable insights for future research. © 2025 Elsevier B.V.

关键词： CO2 adsorption/desorption MC2M nanofluids Photothermal conversion Solar-driven

Unsupervised Community Discovery Algorithm via Reconstructed Graph Neural NEtwork

学校读者我要写书评

暂无评论

Unsupervised Community Discovery Algorithm via Reconstructed...

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Jinghong Wang Hui Wang Jiateng Yang Xizhao Wang College of Computer and Cyber Security Hebei Normal University Shijiazhuang China Hebei Key Laboratory of Network and Information Security Hebei Normal University Shijiazhuang China Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics & Data Security (Hebei Normal University) Shijiazhuang China College of Artificial Intelligence and Big Data Hebei Polytechnic Institute Shijiazhuang China College of Computer Science and Software Engineering ShenZhen University Shenzhen China

Community discovery can help discover potential community structures in the network, which is a fundamental and important issue in network science. Graph neural network-based algorithms are receiving increasing attention. However, there is relatively little work on community discovery directly using graph neural networks in reconstruction design. This paper presents an Unsupervised Community Discovery Algorithm based on reconstructed graph neural network (UCDA) to resolve the above issues. To be specific, this paper proposes a framework that learns the representation based on network structure and attribute information. By designing input network features, encoders, decoders, this algorithm uses an unsupervised loss function to train neural networks to extract communities in an integrated way. These designs integrate higher-order modularity information with network features and use variational graph auto-encoders to train data end-to-end under the graph neural network framework. Based on a series of experiments with a wide range of datasets and advanced algorithms, UCDA has achieved superior performance and shows strong competitiveness. Finally, the last section reports the results analysis, t-SNE visualization and hyperparameter analysis, which depicts stable performance and powerful network modularity ability.

关键词：