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

Mechanism design for Blockchain Order Books Against Selfish Miners

引用

IEEE Transactions on Network Science and engineering 2025年第3期12卷 2121-2134页

作者： Liu, Yunshu Duan, Lingjie Northwestern Polytechnical University School of Cybersecurity Xi'an710129 China Singapore University of Technology and Design Pillar of Engineering Systems and Design 487372 Singapore

In blockchain-based order book systems, buyers and sellers trade assets, while it is miners to match them and include their transactions in the blockchain. It is found that many miners behave selfishly and myopically, prioritizing transactions with high fees and ignoring many desirable matches that could enhance social welfare. Existing blockchain mechanisms fail to address this issue by overlooking miners' selfish behaviors. To our best knowledge, this work presents the first analytical study to quantify and understand buyer and seller transaction fee choices and selfish miners' transaction matching strategies, proving an infinitely large price of anarchy (PoA) for social welfare loss. To mitigate this, we propose an adjustable block size mechanism that is easy to implement without altering the existing decentralized protocols and still allows buyers and sellers to freely decide transaction fees and miners to selfishly match. The analysis is challenging, as pure strategy Nash equilibria do not always exist, requiring the analysis of many buyers' or sellers' interactive mixed-strategy distributions. Moreover, the system designer may even lack information about each buyer's or seller's bid/ask prices and trading quantities. Nevertheless, our mechanism achieves a well-bounded PoA, and under the homogeneous-quantity trading for non-fungible tokens (NFT), it attains a PoA of 1 with no social welfare loss. We implement our mechanism on a local instance of Ethereum to demonstrate the feasibility of our approach. Experiments based on the realistic dataset demonstrate that our mechanism achieves social optimum for homogeneous-quantity trading like NFT. It can enhance social welfare up to 3.7 times compared to the existing order book benchmarks for heterogeneous-quantity trading of Bitcoin tokens. It exhibits robustness against random variations in buyers and sellers. © 2013 IEEE.

关键词： Sales

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

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

To Analyze and Regulate Human-in-the-loop Learning for Congestion Games

arXiv

引用

arXiv 2025年

作者： Li, Hongbo Duan, Lingjie The Pillar of Engineering Systems and Design Singapore University of Technology and Design 487372 Singapore

In congestion games, selfish users behave myopically to crowd to the shortest paths, and the social planner designs mechanisms to regulate such selfish routing through information or payment incentives. However, such mechanism design requires the knowledge of time-varying traffic conditions and it is the users themselves to learn and report past road experiences to the social planner (e.g., Waze or Google Maps). When congestion games meet mobile crowdsourcing, it is critical to incentivize selfish users to explore non-shortest paths in the best exploitation-exploration trade-off. First, we consider a simple but fundamental parallel routing network with one deterministic path and multiple stochastic paths for users with an average arrival probability λ. We prove that the current myopic routing policy (widely used in Waze and Google Maps) misses both exploration (when strong hazard belief) and exploitation (when weak hazard belief) as compared to the social optimum. Due to the myopic policy's under-exploration, we prove that the caused price of anarchy (PoA) is larger than (Equation presented) which can be arbitrarily large as discount factor ρ → 1. To mitigate such huge efficiency loss, we propose a novel selective information disclosure (SID) mechanism: we only reveal the latest traffic information to users when they intend to over-explore stochastic paths upon arrival, while hiding such information when they want to under-explore. We prove that our mechanism successfully reduces PoA to be less than 2. Besides the parallel routing network, we further extend our mechanism and PoA results to any linear path graphs with multiple intermediate nodes. In addition to the worst-case performance evaluation, we conduct extensive simulations with both synthetic and real transportation datasets to demonstrate the close-to-optimal average-case performance of our SID mechanism. © 2025, CC BY.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Federated Learning-Assisted Predictive Beamforming for Extremely Large-Scale Antenna Array systems With Rate-Splitting Multiple Access

引用

IEEE Journal on Selected Topics in Signal Processing 2025年第2期19卷 461-476页

作者： Zhang, Shengyu Mao, Yijie Chen, Zihan Clerckx, Bruno Quek, Tony Q.S Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore ShanghaiTech University School of Information Science and Technology Shanghai201210 China Imperial College London Department of Electrical and Electronic Engineering LondonSW7 2AZ United Kingdom Singapore University of Technology and Design 487372 Singapore Kyung Hee University Department of Electronic Engineering Yongin17104 Korea Republic of

Achieving perfect Channel State Information at the Transmitter (CSIT) is often infeasible in Extremely Large-scale Antenna Array (ELAA) systems due to user mobility and feedback/processing delay. This results in severe multi-user interference. Therefore, how to effectively and efficiently manage interference with partial/historical CSIT is one of the most important challenges for implementing ELAA. In this paper, we propose a Federated Learning (FL)-assisted predictive beamforming framework for ELAA systems to address this challenge. Specifically, we introduce Rate-Splitting Multiple Access (RSMA) to relax the sensitivity to imperfect CSIT while still benefiting from the spatial resolution. Moreover, a predictive beamforming protocol is designed to optimize the precoder design under the imperfections in the channel estimate quality originating from user mobility and latency. To calculate the beamformers, we first propose a lightweight patch-mixing approach to split the historical CSIT data samples into smaller manageable segments. Then, we propose an FL-based training method that enables parallel processing of these CSI segments, thereby accelerating the training process. Simulation results show the effectiveness and efficacy of the proposed FL-assisted predictive beamforming framework, which paves the way for real-world implementation of ELAA. © 2007-2012 IEEE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

Reading Users’ Minds With Large Language Models: Mental Inference for Artificial Empathy in design

引用

Journal of Mechanical design 2025年第6期147卷 061401页

作者： Zhu, Qihao Chong, Leah Yang, Maria Luo, Jianxi Engineering Product Development Pillar Singapore University of Technology and Design 8 Somapah Road Singapore487372 Singapore Department of Mechanical Engineering Massachusetts Institute of Technology 77 Massachusetts Avenue CambridgeMA02139 United States Department of Systems Engineering City University of Hong Kong 83 Tat Chee Ave Kowloon Tong Hong Kong

In human-centered design, developing a comprehensive and in-depth understanding of user experiences—empathic understanding—is paramount for designing products that truly meet human needs. Nevertheless, accurately comprehending the real underlying mental states of a large human population remains a significant challenge today. This difficulty mainly arises from the tradeoff between depth and scale of user experience research: gaining in-depth insights from a small group of users does not easily scale to a larger population, and vice versa. This paper investigates the use of large language models (LLMs) for performing mental inference tasks, specifically inferring users’ underlying goals and fundamental psychological needs (FPNs). Baseline and benchmark datasets were collected from human users and designers to develop an empathic accuracy metric for measuring the mental inference performance of LLMs. The empathic accuracy of inferring goals and FPNs of different LLMs with varied zero-shot prompt engineering techniques are experimented against that of human designers. Experimental results suggest that LLMs can infer and understand the underlying goals and FPNs of users with performance comparable to that of human designers, suggesting a promising avenue for enhancing the scalability of empathic design approaches through the integration of advanced artificial intelligence technologies. This work has the potential to significantly augment the toolkit available to designers during human-centered design, enabling the development of both large-scale and in-depth understanding of users’ experiences. Copyright © 2025 by ASME.

关键词： User centered design

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：