检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Dan, Jun Liu, Weiming Xie, Chunfeng Yu, Hua Dong, Shunjie Tan, Yanchao Zhejiang University China Queen Mary University of London United Kingdom Dalian University of Technology China Shanghai Jiao Tong University China Fuzhou University China Engineering Research Center of Big Data Intelligence Ministry of Education China Fujian Key Laboratory of Network Computing and Intelligent Information Processing China

Semi-supervised graph domain adaptation, as a branch of graph transfer learning, aims to annotate unlabeled target graph nodes by utilizing transferable knowledge learned from a label-scarce source graph. However, most existing studies primarily concentrate on aligning feature distributions directly to extract domain-invariant features, while ignoring the utilization of the intrinsic structure information in graphs. Inspired by the significance of data structure information in enhancing models' generalization performance, this paper aims to investigate how to leverage the structure information to assist graph transfer learning. To this end, we propose an innovative framework called TFGDA. Specially, TFGDA employs a structure alignment strategy named STSA to encode graphs' topological structure information into the latent space, greatly facilitating the learning of transferable features. To achieve a stable alignment of feature distributions, we also introduce a SDA strategy to mitigate domain discrepancy on the sphere. Moreover, to address the overfitting issue caused by label scarcity, a simple but effective RNC strategy is devised to guide the discriminative clustering of unlabeled nodes. Experiments on various benchmarks demonstrate the superiority of TFGDA over SOTA methods. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Demand Response Scheme: Achieving Sustainability in Distributed data Processing 9

Demand Response Scheme: Achieving Sustainability in Distribu...

引用

9th IEEE International Conference on data Science in Cyberspace, DSC 2024

作者： Zhai, Xueying Peng, Yunfeng Guo, Xiuping Zhang, Liang Zhang, Wei University of Science and Technology Beijing School of Computer and Communication Engineering Beijing China Beijing University of Posts and Telecommunications School of Economics and Management Beijing China Guizhou Institute of Technology Guizhou Key Laboratory of Electric Power Big Data Guizhou China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Jinan China

ISBN: (纸本)9798350391367

The rapid development of Internet of Things (IoT) technology has driven the intelligent transformation of various industries, including manufacturing, agriculture, and healthcare, etc., significantly enhancing their management capabilities and decision-making efficiency. data analysis is crucial, serving as both the core technology of this transformation and a major driving force for advancing industry intelligence. However, the increasing volume of data has led to high energy consumption during data analysis, posing significant challenges to environmental and economic sustainability. Integrating renewable energy sources (RESs) is an effective way to reduce greenhouse gas emissions due to their low-carbon and renewable nature. Additionally, the spatiotemporal variability and complementarity of RES generation and grid electricity prices provide favorable conditions for distributed data processing. Therefore, a two-stage demand response scheme is proposed to reduce carbon emissions and electricity costs by prioritizing data processing in data centers (DCs) where RES is abundant or electricity prices are low, based on RES generation and electricity price signals. Simulation results show that the proposed scheme reduces 36.37% carbon emissions and 20.49% electricity costs compared to the benchmark algorithm, indicating its potential for both environmental and economic optimization. © 2024 IEEE.

关键词： Low emission

来源：评论

学校读者我要写书评

暂无评论

Siamese network Visual Tracking Algorithm Based on GCT Attention and Dual-Template Update 5

Siamese Network Visual Tracking Algorithm Based on GCT Atten...

引用

5th International Conference on Natural Language Processing, ICNLP 2023

作者： Ma, Sugang Sun, Siwei Pu, Lei Yang, Xiaobao Xi'an University of Posts and Telecommunications School of Computer Science and Technology Xi'an China Rocket Force Engineering University School of Operational Support Xi'an China Xi'an University of Posts and Telecommunications Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an China

ISBN: (纸本)9798350302219

To address the problem of insufficient representational capability and lack of online update of the Fully-convolutional Siamese network (SiamFC) tracker in complex scenes, this paper proposes a siamese network visual tracking algorithm based on GCT attention and dual-template update mechanism. First, the feature extraction network is constructed by replacing AlexNet with the VGG16 network and SoftPool is used to replace the maximum pooling layer. Secondly, the attention module is added after the backbone network to enhance the network's ability to extract object features. Finally, a dual-template update mechanism is designed for response map fusion. Average Peak-to-Correlation Energy (APCE) is used to determine whether to update the dynamic templates, effectively improving the tracking robustness. The proposed algorithm is trained on the Got-10k dataset and tested on the OTB2015 and VOT2018 datasets. The experimental results show that, compared with SiamFC, the success rate and accuracy reach 0.663 and 0.891 on the OTB2015, which improve respectively 7.6% and 11.9%;On the VOT2018 dataset, the tracking accuracy, robustness and EAO are improved respectively by 2.9%, 29% and 14%. The proposed algorithm achieves high tracking accuracy in complex scenes and the tracking speed reaches 52.6 Fps, which meets the real-time tracking requirements. © 2023 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Sequence-to-Sequence Knowledge Graph Completion Based on Gated Attention Unit 29

Sequence-to-Sequence Knowledge Graph Completion Based on Gat...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Yi, Fengge Wei, Xiumei Liu, Xiaojing Jiang, Xuesong Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China State Key Laboratory of High-end Server & Storage Technology Jinan China

ISBN: (纸本)9798350330717

We present GauKGT5, a sequence-to-sequence model proposed for knowledge graph completion (KGC). Our research extends the KGT5 model, a recent sequence-to-sequence link prediction (LP) model. GauKGT5 takes advantage of textual characteristics inherent in the knowledge graph, exhibiting a small model size. However, KGT5's proficiency in link prediction necessitates the ensemble with a knowledge graph embedding model, which itself poses challenges due to its substantial size and expense. By integrating the Gated Attention Unit into the KGT5 model and directly applying it to the encoder-decoder structure, we achieve improved contextual dependency capturing within the sequence, resulting in enhanced prediction accuracy, accelerated training speed, and enhanced computational efficiency. At the same time, we introduce parallel computing as a means to enhance the efficiency of model training and inference within the XPU distributed computing environment. © 2023 IEEE.

关键词： gated attention unit knowledge graph completion sequence-to-sequence model

来源：评论

学校读者我要写书评

暂无评论

Federated Collaborative Filtering Recommendation Based on Semi-Homomorphic Encryption

Federated Collaborative Filtering Recommendation Based on Se...

引用

IEEE International Conference on Cloud Computing and Big data Analysis (ICCCBDA)

作者： Xiaohan Niu Xing Zhang Zhiguang Chu Xiang Li School of Electronics and Information Engineering Key Laboratory of Security for Network and Data in Industrial Internet of Liaoning Province Liaoning University of Technology Jinzhou China Faculty of Information Technology Key Laboratory of Security for Network and Data in Industrial Internet of Liaoning Province Beijing University of Technology Jinzhou China

Federated collaborative filtering trains models by uploading gradients to achieve privacy protection. Recent studies have shown that gradients have the risk of compromising user privacy. To address this problem, this paper proposes a general federal framework based on Paillier semi-homomorphic encryption for implicit feedback recommendation with privacy protection. First, a non-sampling matrix decomposition model based on the federation framework is designed, and alternating least squares (ALS) and stochastic gradient descent (SGD) are used to optimize the user factor and item factor, respectively, to achieve improved recommendation accuracy and recommendation efficiency while ensuring certain privacy protection. Then, the privacy protection is further enhanced by encrypting the gradients using Paillier semi-homomorphic encryption and transmitting the encrypted gradients via TLS/SSL secure channel. Since the encryption process does not need to obfuscate the data, the method is lossless and ensures the accuracy of recommendations. Finally, experimental analysis is performed on the publicly available MovieLens dataset. The experimental results show that the method is able to enhance privacy protection as well as improve recommendation performance with higher recommendation efficiency and lower time overhead.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PPA: Preference Profiling Attack Against Federated Learning 30

PPA: Preference Profiling Attack Against Federated Learning

引用

30th Annual network and Distributed System Security Symposium, NDSS 2023

作者： Zhou, Chunyi Gao, Yansong Fu, Anmin Chen, Kai Dai, Zhiyang Zhang, Zhi Xue, Minhui Zhang, Yuqing School of Computer Science and Engineering Nanjing University of Science and Technology China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Science China Data61 CSIRO Syndey Australia National Computer Network Intrusion Protection Center University of Chinese Academy of Science China

ISBN: (纸本)1891562835

—Federated learning (FL) trains a global model across a number of decentralized users, each with a local dataset. Compared to traditional centralized learning, FL does not require direct access to local datasets and thus aims to mitigate data privacy concerns. However, data privacy leakage in FL still exists due to inference attacks, including membership inference, property inference, and data inversion. In this work, we propose a new type of privacy inference attack, coined Preference Profiling A ttack (PPA), t hat accurately profiles t he p rivate p references o f a l ocal u ser, e .g., m ost liked (disliked) items from the client’s online shopping and most common expressions from the user’s selfies. I n g eneral, P PA can profile t op-k (i.e., k = 1, 2, 3 a nd k = 1 i n p articular) preferences contingent on the local client (user)’s characteristics. Our key insight is that the gradient variation of a local user’s model has a distinguishable sensitivity to the sample proportion of a given class, especially the majority (minority) class. By observing a user model’s gradient sensitivity to a class, PPA can profile the sample proportion of the class in the user’s local dataset, and thus the user’s preference of the class is exposed. The inherent statistical heterogeneity of FL further facilitates PPA. We have extensively evaluated the PPA’s effectiveness using four datasets (MNIST, CIFAR10, RAF-DB and Products-10K). Our results show that PPA achieves 90% and 98% top-1 attack accuracy to the MNIST and CIFAR10, respectively. More importantly, in real-world commercial scenarios of shopping (i.e., Products-10K) and social network (i.e., RAF-DB), PPA gains a top-1 attack accuracy of 78% in the former case to infer the most ordered items (i.e., as a commercial competitor), and 88% in the latter case to infer a victim user’s most often facial expressions, e.g., disgusted. The top-3 attack accuracy and top-2 accuracy is up to 88% and 100% for the Products-10K and RAF-DB, re

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modeling of unsupervised knowledge graph of events based on mutual information among neighbor domains and sparse representation

引用

Defence technology（防务技术） 2022年第12期18卷 2150-2159页

作者： Jing-Tao Sun Jing-Ming Li Qiu-Yu Zhang School of Computer Science and Technology Xi'an University of Posts and TelecommunicationsXi'anShaanxi710121China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and TelecommunicationsXi'anShaanxi710121China School of Management Science and Engineering Anhui University of Finance and EconomicsBengbuAnhui230030China School of Computer and Communication Lanzhou University of TechnologyLanzhouGansu730050China

Text event mining,as an indispensable method of text mining processing,has attracted the extensive attention of researchers.A modeling method for knowledge graph of events based on mutual information among neighbor domains and sparse representation is proposed in this paper,***,UKGE-MS can improve the existing text mining technology's ability of understanding and discovering high-dimensional unmarked information,and solves the problems of traditional unsupervised feature selection methods,which only focus on selecting features from a global perspective and ignoring the impact of local connection of ***,considering the influence of local information of samples in feature correlation evaluation,a feature clustering algorithm based on average neighborhood mutual information is proposed,and the feature clusters with certain event correlation are obtained;Secondly,an unsupervised feature selection method based on the high-order correlation of multi-dimensional statistical data is designed by combining the dimension reduction advantage of local linear embedding algorithm and the feature selection ability of sparse representation,so as to enhance the generalization ability of the selected feature ***,the events knowledge graph is constructed by means of sparse representation and l1 *** experiments are carried out on five real datasets and synthetic datasets,and the UKGE-MS are compared with five corresponding *** experimental results show that UKGE-MS is better than the traditional method in event clustering and feature selection,and has some advantages over other methods in text event recognition and discovery.

关键词： Text event mining Knowledge graph of events Mutual information among neighbor domains Sparse representation

来源：评论

学校读者我要写书评

暂无评论

Towards Event Extraction with Massive Types: LLM-based Collaborative Annotation and Partitioning Extraction

arXiv

引用

arXiv 2025年

作者： Liu, Wenxuan Li, Zixuan Bai, Long Zuo, Yuxin Xu, Daozhu Jin, Xiaolong Guo, Jiafeng Cheng, Xueqi School of Computer Science and Technology University of Chinese Academy of Sciences China Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China State Key Laboratory of Geo-Information Engineering Shaanxi Xi’an China

Developing a general-purpose extraction system that can extract events with massive types is a long-standing target in Event Extraction (EE). In doing so, the challenge comes from two aspects: 1) The absence of an efficient and effective annotation method. 2) The absence of a powerful extraction method can handle massive types. For the first challenge, we propose a collaborative annotation method based on Large Language Models (LLMs). Through collaboration among multiple LLMs, it first refines annotations of trigger words from distant supervision and then carries out argument annotation. Next, a voting phase consolidates the annotation preferences across different LLMs. Finally, we create the EEMT dataset, the largest EE dataset to date, featuring over 200,000 samples, 3,465 event types, and 6,297 role types. For the second challenge, we propose an LLM-based Partitioning EE method called LLM-PEE. To overcome the limited context length of LLMs, LLM-PEE first recalls candidate event types and then splits them into multiple partitions for LLMs to extract events. The results in the supervised setting show that LLM-PEE outperforms the state-of-the-art methods by 5.4% in event detection and 6.1% in argument extraction. In the zero-shot setting, LLM-PEE achieves up to 12.9% improvement compared to mainstream LLMs, demonstrating its strong generalization capabilities. Copyright © 2025, The Authors. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Object Detection Algorithm Based on Bimodal Feature Alignment 7th

Object Detection Algorithm Based on Bimodal Feature Alignme...

引用

7th Asian Conference on Pattern Recognition, ACPR 2023

作者： Sun, Ying Hou, Zhiqiang Yang, Chen Ma, Sugang Fan, Jiulun School of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an710121 China Key Laboratory of Network Data Analysis and Intelligent Processing of Shaanxi Province Xi’an710121 China School of Communications and Information Engineering Xi’an University of Posts and Telecommunications Xi’an710121 China

ISBN: (纸本)9783031476334

A dual-modal feature alignment based object detection algorithm is proposed for the full fusion of visible and infrared image features. First, we propose a two stream detection model. The algorithm supports simultaneous input of visible and infrared image pairs. Secondly, a gated fusion network is designed, consisting of a dual-modal feature alignment module and a feature fusion module. Medium-term fusion is used, which will be used as the middle layer of the dual-stream backbone network. In particular, the dual-mode feature alignment module extracts detailed information of the dual-mode aligned features by computing a multi-scale dual-mode aligned feature vector. The feature fusion module recalibrates the bimodal fused features and then multiplies them with the bimodal aligned features to achieve cross-modal fusion with joint enhancement of the lower and higher level features. We validate the performance of the proposed algorithm using both the publicly available KAIST pedestrian dataset and a self-built GIR dataset. On the KAIST dataset, the algorithm achieves an accuracy of 77.1%, which is 17.3% and 5.6% better than the accuracy of the benchmark algorithm YOLOv5-s for detecting visible and infrared images alone;on the self-built GIR dataset, the detection accuracy is 91%, which is 1.2% and 14.2% better than the benchmark algorithm for detecting visible and infrared images alone respectively. And the speed meets the real time requirements. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Very-Short-Term Online PV Power Prediction Model Based on RAN With Secondary Dynamic Adjustment

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第5期4卷 1214-1224页

作者： Zhang, Tengfei Ma, Fumin Peng, Chen Yu, Yang Yue, Dong Dou, Chunxia O'Hare, Gregory M. P. Nanjing University of Posts and Telecommunications College of Automation College of Artificial Intelligence The Jiangsu Engineering Laboratory of Big Data Analysis and Control for Active Distribution Network Nanjing210023 China Nanjing University of Finance and Economics College of Information Engineering Nanjing210023 China Shanghai University School of Mechatronic Engineering and Automation Shanghai200072 China Nanjing University of Posts and Telecommunications Institute of Advanced Technology Nanjing210023 China Trinity College Dublin School of Computer Science and Statistics Dublin 2 Ireland

Photovoltaic (PV) power is progressively being subsumed into power grids. As a consequence, reliable PV power forecasting has become essential in order to ensure the optimal functioning of the power grid. Neural networks remain the dominant prediction model utilized. Conventional neural network forecasting models are wholly dependent upon offline data. Subsequent to offline training, no further structural adjustments can be made during the forecasting process, which therefore they fail to cater for PV power supply fluctuations that are fundamentally dynamic. To address this failing, this article proposes a very-short-term online prediction model based on a resource-allocating network (RAN) incorporating a secondary dynamic adjustment. The RAN is initially trained offline to obtain a basic forecasting model. Thereafter, in an online prediction process, those samples with large prediction errors that exceed a preset value are recorded in a specific buffer. When the set conditions are triggered, the secondary dynamic adjustment strategy is employed, which enables the online prediction model to effectively relearn previously unmodeled samples while shielding external interference. Experimental results obtained from actual testing demonstrate the validity of the secondary dynamic adjustment strategy for online learning while also providing higher accuracy levels from the prediction model. © 2020 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：