检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Hao, Shugang Duan, Lingjie Pillar of Engineering Systems and Design Singapore University of Technology and Design Singapore

ISBN: (纸本)9798350368741

Continual learning (CL) is a new online learning technique over sequentially generated streaming data from different tasks, aiming to maintain a small forgetting loss on previously-learned tasks. Existing work focuses on reducing the forgetting loss under a given task sequence. However, if similar tasks continuously appear to the end time, the forgetting loss is still huge on prior distinct tasks. In practical IoT networks, an autonomous vehicle to sample data and learn different tasks can route and alter the order of task pattern at increased travelling cost. To our best knowledge, we are the first to study how to opportunistically route the testing object and alter the task sequence in CL. We formulate a new optimization problem and prove it NP-hard. We propose a polynomial-time algorithm to achieve approximation ratios of 3/2 for underparameterized case and 2/3 +r1−T for overparameterized case, respectively. Simulation results verify our algorithm's close-to-optimum performance. © 2025 IEEE.

关键词： approximation algorithm design Continual learning IoT network task ordering

来源：评论

学校读者我要写书评

暂无评论

Online Learning from Strategic Human Feedback in LLM Fine-Tuning

Online Learning from Strategic Human Feedback in LLM Fine-Tu...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Hao, Shugang Duan, Lingjie Pillar of Engineering Systems and Design Singapore University of Technology and Design Singapore

ISBN: (纸本)9798350368741

Reinforcement learning from human feedback (RLHF) has become an essential step in fine-tuning large language models (LLMs) to align them with human preferences. However, human labelers are selfish and have diverse preferences. They may strategically misreport their online feedback to influence the system's aggregation towards their own preferences. Current practice simply averages labelers' feedback per time and fails to identify the most accurate human labeler, leading to linear regret O(T) for T time slots. To our best knowledge, we are the first to study online learning mechanisms against strategic human labelers in the LLM fine-tuning process. We formulate a new dynamic Bayesian game and dynamically adjust human labelers' weights in the preference aggregation, ensuring their truthful feedback and sublinear regret O(T1/2). Simulation results demonstrate our mechanism's great advantages over the existing benchmark schemes. © 2025 IEEE.

关键词： LLM fine-tuning online learning regret analysis strategic human feedback truthful mechanism design

来源：评论

学校读者我要写书评

暂无评论

To Save Crowdsourcing from Cheap-talk: Strategic Learning from Biased Users 21

To Save Crowdsourcing from Cheap-talk: Strategic Learning fr...

引用

21st International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks, WiOpt 2023

作者： Hao, Shugang Duan, Lingjie Pillar of Engineering Systems and Design Singapore University of Technology and Design Singapore

ISBN: (纸本)9783903176553

Today many users are invited by a crowdsourcing platform (e.g., TripAdvisor, and Waze) to provide their anonymous reviews about service experiences (e.g., in hotels, restaurants, and trips), yet many reviews are found biased to be extremely positive or negative. It is difficult to learn from biased users’ reviews to infer actual service state, as the service state can also be extreme and the platform cannot verify immediately. Further, due to the anonymity, reviewers can hide their bias types (positive or negative) from the platform and adaptively adjust their reviews against the platform’s inference. To our best knowledge, we are the first to study how to save crowdsourcing from cheap-talk and strategically learn the actual service state from biased users’ reviews. We formulate the problem as a dynamic Bayesian game, including the unknown users’ messaging and the platform’s follow-up inference. Through involved analysis, we provide closed-form expressions for the Perfect Bayesian Equilibrium (PBE). Our PBE shows that the platform’s strategic learning can successfully prevent biased users from cheap-talk in most cases, where a user even with extreme bias still honestly messages to convince the platform of listening to his review. We prove that the price of anarchy (PoA) is 2, telling that the social cost can at most be doubled in the worst-case. As the user number becomes large, our platform always learns the actual service state. Perhaps surprisingly, the platform’s expected cost may be worse off after adding one more user. © 2023 IFIP.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Physics-Informed Neural Networks for Privacy-Preserving Model Sharing in Power systems

Physics-Informed Neural Networks for Privacy-Preserving Mode...

引用

2024 IEEE PES Innovative Smart Grid Technologies Europe Conference, ISGT EUROPE 2024

作者： Canyakmaz, Ilayda Saner, Can Berk Varvitsiotis, Antonios Singapore University of Technology and Design Engineering Systems and Design Pillar Singapore National University of Singapore Electrical and Computer Engineering Department Singapore

ISBN: (纸本)9789531842976

Data privacy concerns in the power systems sector significantly complicate the sharing and integration of sensitive operational data among various independent entities. This challenge is particularly pronounced when developing system-wide mathematical models, as the reluctance to share sub-system models parametrized by sensitive data hinders effective system analysis and decision-making. To address this issue, this work introduces the application of Physics-Informed Neural Networks (PINNs) to develop surrogate models that accurately replicate power system dynamics without exposing sensitive data, enabling privacy-preserving model sharing. By embedding physical laws into the training process, PINNs utilize both available data and inherent system physics, making them particularly suitable for modeling complex dynamics. We propose a framework for model development, including dataset generation and integration of the physics knowledge during PINN training. As a proof-of-concept, we apply this framework to a simplified Single Machine Infinite Bus (SMIB) system. Case studies demonstrate that the trained PINN model closely follows ground-truth dynamics and consistently achieves higher accuracy compared to generic neural networks, highlighting the potential for accurate, privacy-preserving model sharing and system-wide dynamic simulations in power systems. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

OFDM-structure based waveform designs for integrated sensing and communication

引用

Science China(Information Sciences) 2025年第5期68卷 267-284页

作者： Jiaqi LIU Ping YANG Ke JIANG Jiarong ZHAO Wei XIANG Jianping WEI Ruixiang DUAN Saviour ZAMMIT Tony Q.S.QUEK National Key Laboratory of Wireless Communications University of Electronic Science and Technology of China School of Computing Engineering and Mathematical Sciences La Trobe University Meituan Academy of Robotics Department of Communications and Computer Engineering University of Malta Information Systems Technology and Design Pillar Singapore University of Technology and Design

The future sixth-generation(6G) paradigm aims to seamlessly integrate communication and environmental sensing capabilities into a single radio signal, promising improved efficiency and cost-effectiveness through simultaneous data communications and environmental perception. At the core of this evolution, orthogonal frequency division multiplexing(OFDM) and its advanced waveforms emerge as pivotal for integrated sensing and communications(ISAC). This study introduces a concise and unified ISAC waveform design framework based on orthogonal multicarriers. This framework supports versatile applications of OFDM and its derivative waveforms within a generalized ISAC system, marking a significant leap in integrating communication and sensing capabilities. A distinguishing feature of this framework is its adaptability,allowing users to intelligently select modulation strategies based on their specific environmental needs. This adaptability optimizes performance across diverse scenarios. Central to our innovations is the proposal of discrete Fourier transformspread OFDM with index modulation(DFT-S-OFDM-IM). This framework is paired with newly proposed signal processing methods for single-input single-output and multiple-input multiple-output(MIMO) systems. Extensive evaluations highlight DFT-S-OFDM-IM's superiority, including dramatically reduced peak-to-average power ratios(PAPRs), competitive communication performance, and exceptional sensing capabilities, striking an elegant balance between communication capacity and environmental sensing precision.

关键词： DFT-S-OFDM-IM index modulation integrated sensing and communication OFDM

来源：评论

学校读者我要写书评

暂无评论

Dynamic Matching with Impatient Agents: A Study for Ride-Sharing systems 4

Dynamic Matching with Impatient Agents: A Study for Ride-Sha...

引用

4th International Conference on Electrical, Computer, Communications and Mechatronics engineering, ICECCME 2024

作者： Gao, Shuqin Courcoubetis, Costas Duan, Lingjie School of Data Science The Chinese University of HongKong Shenzhen China Singapore University of Technology and Design Engineering Systems and Design Pillar Singapore

ISBN: (纸本)9798350391183

Ride-sharing systems have emerged as a popular and cost-effective urban transportation solution, allowing private car drivers to offer rides to passengers traveling in the same direction. This paper delves into the market design problem, where agents, i.e., drivers and riders, dynamically enter the system over time, each requiring transportation to specific destinations. To get an important insight, we focus on a fundamental case where all participants share a common origin but have distinct destinations that define their types. Given matching agents of the same type generates higher utility than matching different types, we explore how the matching of agents can enhance the overall utility generated by the market. Moreover, we assume agents exhibit impatience and will exit the system after waiting for a given time window. This introduces interesting incentive issues, whether an agent will accept a matching proposed by the platform. Initially, we tackle scenarios where agents are constrained to accept such a matching. We introduce a straightforward heuristic that matches a different-Type pair only when one agent is about to leave immediately and the other cannot wait beyond a threshold number of time periods. We establish a theoretical lower bound on the heuristic mechanism's performance and demonstrate its near-optimality. Subsequently, we shift focus to the incentive dynamics within the system, particularly when self-interested agents can be non-cooperative with the platform, i.e., reject low-value different-Type matchings hoping to get better ones in the future. We study the incentive compatibility of the heuristic mechanism regarding cooperation and propose a strategy to foster cooperation by compensating appropriately agents who agree to accept different-Type matching. © 2024 IEEE.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Enabling Visual Scene Recovery from Wi-Fi CSI for Occlusion-Free Surveillance

引用

IEEE Internet of Things Journal 2025年第11期12卷 15040-15056页

作者： Chen, Cheng Ohta, Shoki Nishio, Takayuki Bennis, Mehdi Park, Jihong Wahib, Mohamed Tokyo Institute of Technology School of Engineering Meguro-ku Tokyo152-8550 Japan Kobe650-0047 Japan University of Oulu Centre of Wireless Communications Oulu90014 Finland Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore

We introduce CSI-Inpainter, a novel approach for obstacle removal using Wi-Fi channel state information (CSI). This method harnesses CSI data to reconstruct obscured visual elements, regardless of lighting conditions. Extensive empirical evaluation in both office and industrial settings demonstrates the effectiveness of CSI-Inpainter's exceptional ability to identify and reconstruct occluded segments, outperforming traditional baselines and our RSSI-based work, RF-Inpainter in terms of visual quality. Our findings emphasize the superiority of CSI data over RSSI for providing richer visual information and underscore the critical role of optimal sensor placement and data fusion from multiple CSI sensors in enhancing the performance. CSI-Inpainter represents a significant advancement in obstacle removal for various applications like surveillance, offering new insights into the integration of wireless sensing and visual scene recovery, expanding the potential applications of Computer Vision in real-world environments. © 2025 IEEE.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Online Learning from Strategic Human Feedback in LLM Fine-Tuning

Online Learning from Strategic Human Feedback in LLM Fine-Tu...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Shugang Hao Lingjie Duan Pillar of Engineering Systems and Design Singapore University of Technology and Design

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Reinforcement learning from human feedback (RLHF) has become an essential step in fine-tuning large language models (LLMs) to align them with human preferences. However, human labelers are selfish and have diverse preferences. They may strategically misreport their online feedback to influence the system’s aggregation towards their own preferences. Current practice simply averages labelers’ feedback per time and fails to identify the most accurate human labeler, leading to linear regret ${\mathcal{O}}(T)$ for T time slots. To our best knowledge, we are the first to study online learning mechanisms against strategic human labelers in the LLM fine-tuning process. We formulate a new dynamic Bayesian game and dynamically adjust human labelers’ weights in the preference aggregation, ensuring their truthful feedback and sublinear regret ${\mathcal{O}}\left({{T^{1/2}}}\right)$. Simulation results demonstrate our mechanism’s great advantages over the existing benchmark schemes.

关键词： Learning systems Simulation Large language models Reinforcement learning Games Benchmark testing Signal processing Acoustics Bayes methods Speech processing

来源：评论

学校读者我要写书评

暂无评论

Algorithm design for Continual Learning in IoT Networks

Algorithm Design for Continual Learning in IoT Networks

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Shugang Hao Lingjie Duan Pillar of Engineering Systems and Design Singapore University of Technology and Design

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Continual learning (CL) is a new online learning technique over sequentially generated streaming data from different tasks, aiming to maintain a small forgetting loss on previously-learned tasks. Existing work focuses on reducing the forgetting loss under a given task sequence. However, if similar tasks continuously appear to the end time, the forgetting loss is still huge on prior distinct tasks. In practical IoT networks, an autonomous vehicle to sample data and learn different tasks can route and alter the order of task pattern at increased travelling cost. To our best knowledge, we are the first to study how to opportunistically route the testing object and alter the task sequence in CL. We formulate a new optimization problem and prove it NP-hard. We propose a polynomial-time algorithm to achieve approximation ratios of $\frac{3}{2}$ for underparameterized case and $\frac{3}{2} + {r^{1 - T}}$ for overparameterized case, respectively. Simulation results verify our algorithm’s close-to-optimum performance.

关键词： Continuing education Costs Simulation Signal processing algorithms Signal processing Approximation algorithms Polynomials Speech processing Optimization Testing

来源：评论

学校读者我要写书评

暂无评论

Trustworthy DNN partition for blockchain-enabled digital twin in wireless IIoT networks

引用

Science China(Information Sciences) 2024年第11期67卷 373-374页

作者： Xiumei DENG Jun LI Long SHI Kang WEI Ming DING Yumeng SHAO Wen CHEN Shi JIN Pillar of Information Systems Technology and Design Singapore University of Technology and Design National Mobile Communications Research Laboratory Southeast University School of Electronic and Optical Engineering Nanjing University of Science and Technology Department of Computing Hong Kong Polytechnic University Data61 CSIRO Department of Electronics Engineering Shanghai Jiao Tong University

The integration of artificial intelligence(AI) and digital twin(DT) technology has revolutionized the industrial Internet of Things(IIoT), enabling advanced automation and intelligent manufacturing [1]. Through sophisticated interactions between physical entities and their virtual counterparts,AI-driven DTs facilitate performance monitoring, analysis,simulation, and optimization of physical assets, enabling predictive maintenance and informed decision-making [2].

关键词：

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：