检索结果-内蒙古大学图书馆

Open-book neural algorithmic reasoning 24

学校读者我要写书评

暂无评论

Open-book neural algorithmic reasoning

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Hefei Li Chao Peng Chenyang Xu Zhengfeng Yang Shanghai Key Laboratory of Trustworthy Computing Software Engineering Institute East China Normal University Shanghai China

ISBN: (纸本)9798331314385

Neural algorithmic reasoning is an emerging area of machine learning that focuses on building neural networks capable of solving complex algorithmic tasks. Recent advancements predominantly follow the standard supervised learning paradigm - feeding an individual problem instance into the network each time and training it to approximate the execution steps of a classical algorithm. We challenge this mode and propose a novel open-book learning framework. In this framework, whether during training or testing, the network can access and utilize all instances in the training dataset when reasoning for a given *** evaluation is conducted on the challenging CLRS Algorithmic Reasoning Benchmark, which consists of 30 diverse algorithmic tasks. Our open-book learning framework exhibits a significant enhancement in neural reasoning capabilities. Further, we notice that there is recent literature suggesting that multi-task training on CLRS can improve the reasoning accuracy of certain tasks, implying intrinsic connections between different algorithmic tasks. We delve into this direction via the open-book framework. When the network reasons for a specific task, we enable it to aggregate information from training instances of other tasks in an attention-based manner. We show that this open-book attention mechanism offers insights into the inherent relationships among various tasks in the benchmark and provides a robust tool for interpretable multi-task training.

关键词：

Green Federated Learning over Cloud-RAN with Limited Fronthaul and Quantized Neural Networks 3

学校读者我要写书评

暂无评论

Green Federated Learning over Cloud-RAN with Limited Frontha...

3rd IEEE International Mediterranean Conference on Communications and Networking, MeditCom 2023

作者： Wang, Jiali Mao, Yijie Wang, Ting Shi, Yuanming Shanghai Key Lab. of Trustworthy Computing East China Normal University MoE Engineering Research Center of Software/Hardware Co-Design Technology and Application China China

ISBN: (纸本)9798350333732

In this paper, we investigate a green federated learning (FL) framework over cloud radio access network (Cloud-RAN) system that comprises a server, multiple devices and remote radio heads (RRHs). Each device utilizes quantized neural networks (QNNs) and sends quantized model parameters to the server to save energy consumption via RRHs. The server aggregates all the signals to update the global model parameters and broadcasts the updated parameters to the selected devices. In this context, we propose an energy consumption model for the QNN training and communication model over Cloud-RAN. We develop an energy minimization problem based on the proposed energy model. We jointly design fronthaul rate allocation, device transmit power, and precision level of QNNs while ensuring target accuracy, transmit power budget and limited fronthaul capacity. Guided by the convergence analysis, we adopt alternative optimization method to solve the energy minimization problem. The simulation outcomes demonstrate that the FL framework suggested can considerably diminish energy usage in comparison to other traditional methods. This has immense potential in realizing a sustainable and eco-friendly FL over Cloud-RAN. © 2023 IEEE.

关键词： Radio access networks

Fuzzy Information Entropy and Region Biased Matrix Factorization for Web Service QoS Prediction

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Tang, Guoxing Du, Yugen Chen, Xia Luo, Yingwei Ma, Benchi Shanghai Key Laboratory of Trustworthy Computing Software Engineering Institute East China Normal University Shanghai200062 China

Nowadays, there are many similar services available on the internet, making Quality of Service (QoS) a key concern for users. Since collecting QoS values for all services through user invocations is impractical, predicting QoS values is a more feasible approach. Matrix factorization is considered an effective prediction method. However, most existing matrix factorization algorithms focus on capturing global similarities between users and services, overlooking the local similarities between users and their similar neighbors, as well as the non-interactive effects between users and services. This paper proposes a matrix factorization approach based on user information entropy and region bias, which utilizes a similarity measurement method based on fuzzy information entropy to identify similar neighbors of users. Simultaneously, it integrates the region bias between each user and service linearly into matrix factorization to capture the non-interactive features between users and services. This method demonstrates improved predictive performance in more realistic and complex network environments. Additionally, numerous experiments are conducted on real-world QoS datasets. The experimental results show that the proposed method outperforms some of the state-of-the-art methods in the field at matrix densities ranging from 5% to 20%. Copyright © 2025, The Authors. All rights reserved.

关键词： Matrix factorization

SUNET: Framework, Security, and Privacy

学校读者我要写书评

暂无评论

SUNET: Framework, Security, and Privacy

2024 International Conference on Satellite Internet, SAT-NET 2024

作者： Xie, Zhan Wang, Liangmin Wu, Haiqin Zhang, Xiaoyu Wang, Liang Yang, Haotian Southeast University School of Cyber Science and Engineering Nanjing211189 China Southeast University Engineering Research Center of BASAM Ministry of Education Nanjing211189 China East China Normal University Software Engineering Institute Shanghai Key Laboratory of Trustworthy Computing Shanghai200062 China

ISBN: (纸本)9798350375176

SUNet (Satellite-assisted Unmanned-system Network) integrates satellite communication technology, unmanned equipment systems, and ground support facilities. Compared to traditional network system, SUNet has the advantages of flexible deployment and wide communication range. SUNet with cloud services (SUNET) breaks the limitation of satellites processing large-scale data, and integrates a large scope of computing and storage resources in a system. However, SUNET also poses more serious security risks than traditional networks for two reasons: i) the unique network framework, such as highly dynamic topology, unfixed network access points and decentralized control, of SUNET increases security risks, and ii) the rising probability of existing neighbor nodes with quantum computing. This paper firstly introduces the term SUNET from definition and compares SUNET with several related network frameworks. Then we anaylze the security risks, such as untrust between nodes, unauthorized access and quantum computing attack, faced by SUNET. Meanwhile, we illustrate the security requirements and the corresponding solutions, such as authentication, fine-grained authorization and quantum security, in SUNET. Finally, we discuss the security countermeasures and point out the potential future research directions. © 2024 IEEE.

关键词： Quantum computers

Open-Book Neural Algorithmic Reasoning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Hefei Peng, Chao Xu, Chenyang Yang, Zhengfeng Shanghai Key Laboratory of Trustworthy Computing Software Engineering Institute East China Normal University Shanghai China

Neural algorithmic reasoning is an emerging area of machine learning that focuses on building neural networks capable of solving complex algorithmic tasks. Recent advancements predominantly follow the standard supervised learning paradigm - feeding an individual problem instance into the network each time and training it to approximate the execution steps of a classical algorithm. We challenge this mode and propose a novel open-book learning framework. In this framework, whether during training or testing, the network can access and utilize all instances in the training dataset when reasoning for a given instance. Empirical evaluation is conducted on the challenging CLRS Algorithmic Reasoning Benchmark, which consists of 30 diverse algorithmic tasks. Our open-book learning framework exhibits a significant enhancement in neural reasoning capabilities. Further, we notice that there is recent literature suggesting that multi-task training on CLRS can improve the reasoning accuracy of certain tasks, implying intrinsic connections between different algorithmic tasks. We delve into this direction via the open-book framework. When the network reasons for a specific task, we enable it to aggregate information from training instances of other tasks in an attention-based manner. We show that this open-book attention mechanism offers insights into the inherent relationships among various tasks in the benchmark and provides a robust tool for interpretable multi-task training. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

TrajTrace: Tracing Moving Objects over Social Media 28th

学校读者我要写书评

暂无评论

TrajTrace: Tracing Moving Objects over Social Media

28th International Conference on Database Systems for Advanced Applications, DASFAA 2023

作者： Yang, Zhihao Zhang, Yunqi Li, Songda Chen, Qinhui Zhao, Hui Cai, Wei Lin, Xi Software Engineering Institute East China Normal University Shanghai China Shanghai Key Laboratory of Trustworthy Computing Shanghai China Electronics Technology Group Corporation The 51st Research Institue of China Beijing China

ISBN: (纸本)9783031306778

Online social media has lots of moving object information. Extracting movement information is a challenging work. It suffers from spatio-temporal information extraction, vague time, and vague location. Previous information extraction methods merely focus on the trajectory extraction. In this demonstration, we develop a web-based application, TrajTrace, to track moving objects. TrajTrace extracts triple from social media text employing our proposed span-level joint entity and relation extraction model, OMLer. OMLer casts joint extraction as a token pair multi-categories classification task. It predicts the triple list corresponding to the input sequence. We employ BERT to encode the input sentence word by word. The self-attention mechanism and BiLSTM are applied to learn sequence features. Then, an order-first time matching algorithm is designed to solve the lacking temporal information problem in the extracted triples. Utilizing the proposed TF-IDF based clustering algorithm, we make the vague time accurate. The vague geographic location is converted to accurate latitude and longitude using the Bezier geodetic coordinate conversion algorithm. Toward aircraft and ships, besides the keyword search and the trajectories visualization, TrajTrace provides the historical activity area search of a specific object and the spatio-temporal distribution of moving objects at a given time or location. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Trajectories

Sponsored Search Auction Design Beyond Single Utility Maximization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Changfeng Peng, Chao Xu, Chenyang Yang, Zhengfeng Shanghai Key Laboratory of Trustworthy Computing Software Engineering Institute East China Normal University China

Auction design for the modern advertising market has gained significant prominence in the field of game theory. With the recent rise of auto-bidding tools, an increasing number of advertisers in the market are utilizing these tools for auctions. The diverse array of auto-bidding tools has made auction design more challenging. Various types of bidders, such as quasi-linear utility maximizers and constrained value maximizers, coexist within this dynamic gaming environment. We study sponsored search auction design in such a mixed-bidder world and aim to design truthful mechanisms that maximize the total social welfare. To simultaneously capture the classical utility and the value-max utility, we introduce an allowance utility model. In this model, each bidder is endowed with an additional allowance parameter, signifying the threshold up to which the bidder can maintain a value-max strategy. The paper distinguishes two settings based on the accessibility of the allowance information. In the case where each bidder’s allowance is public, we demonstrate the existence of a truthful mechanism achieving an approximation ratio of (1+ϵ) for any ϵ > 0. In the more challenging private allowance setting, we establish that a truthful mechanism can achieve a constant approximation. Further, we consider uniform-price auction design in large markets and give a truthful mechanism that sets a uniform price in a random manner and admits bounded approximation in expectation. Copyright © 2024, The Authors. All rights reserved.

关键词： Commerce

HyLoReF: A Reputation Based QoS Prediction Framework using Hybrid Location Information

学校读者我要写书评

暂无评论

HyLoReF: A Reputation Based QoS Prediction Framework using H...

IEEE International Conference on Web Services (ICWS)

作者： Xia Chen Yugen Du Fan Chen Hanting Wang Yingwei Luo Benchi Ma Guoxing Tang Software Engineering Institute East China Normal University Shanghai China Shanghai Key Laboratory of Trustworthy Computing Shanghai China

ISBN: (数字)9798350368550

ISBN: (纸本)9798350368567

With the proliferation of Web services, users pay more attention to Quality of Service (QoS) information when choosing Web services with similar functionalities. Predicting QoS values effectively and accurately is a difficult challenge. In the real world, some users are strongly subjective in submitting QoS observations and some Web services suffer from instability caused by bugs. Therefore, this paper uses user reputation to measure the reliability of users and service reputation to measure the stability of Web services. We propose HyLoReF, a QoS prediction framework based on reputation and hybrid location information. HyLoReF uses Logit model to compute user reputation and service reputation, and combines them into Matrix Factorization (MF) model to improve the QoS prediction accuracy. Experimental results show that HyLoReF outperforms baseline methods and state-of-the-art models on the Web services standard dataset WS-DREAM [1] when the Matrix Density (MD) is in the interval of 5% to 30%.

关键词： Logistic regression Accuracy Web services Computational modeling Computer bugs Quality of service Predictive models Stability analysis Robustness Standards

RAHN: A Reputation Based Hourglass Network for Web Service QoS Prediction

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chen, Xia Du, Yugen Tang, Guoxing Luo, Yingwei Ma, Benchi Software Engineering Institute East China Normal University Shanghai200062 China Shanghai Key Laboratory of Trustworthy Computing Shanghai200062 China

As the homogenization of Web services becomes more and more common, the difficulty of service recommendation is gradually increasing. How to predict Quality of Service (QoS) more efficiently and accurately becomes an important challenge for service recommendation. Considering the excellent role of reputation and deep learning (DL) techniques in the field of QoS prediction, we propose a reputation and DL based QoS prediction network, RAHN, which contains the Reputation Calculation Module (RCM), the Latent Feature Extraction Module (LFEM), and the QoS Prediction Hourglass Network (QPHN). RCM obtains the user reputation and the service reputation by using a clustering algorithm and a Logit model. LFEM extracts latent features from known information to form an initial latent feature vector. QPHN aggregates latent feature vectors with different scales by using Attention Mechanism, and can be stacked multiple times to obtain the final latent feature vector for prediction. We evaluate RAHN on a real QoS dataset. The experimental results show that the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) of RAHN are smaller than the six baseline methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Web services