检索结果-内蒙古大学图书馆

Digital Twin-Assisted data-Driven Optimization for Reliable Edge Caching in Wireless Networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Zifan Liu, Yuchen Peng, Zhiyuan Chen, Mingzhe Xu, Dongkuan Cui, Shuguang Department of Computer Science North Carolina State University RaleighNC27695 United States Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States School of Science and Engineering The Chinese University of Hong Kong Shenzhen China

Optimizing edge caching is crucial for the advancement of next-generation (nextG) wireless networks, ensuring high-speed and low-latency services for mobile users. Existing data-driven optimization approaches often lack awareness of the distribution of random data variables and focus solely on optimizing cache hit rates, neglecting potential reliability concerns, such as base station overload and unbalanced cache issues. This oversight can result in system crashes and degraded user experience. To bridge this gap, we introduce a novel digital twinassisted optimization framework, called D-REC, which integrates reinforcement learning (RL) with diverse intervention modules to ensure reliable caching in nextG wireless networks. We first develop a joint vertical and horizontal twinning approach to efficiently create network digital twins, which are then employed by D-REC as RL optimizers and safeguards, providing ample datasets for training and predictive evaluation of our cache replacement policy. By incorporating reliability modules into a constrained Markov decision process, D-REC can adaptively adjust actions, rewards, and states to comply with advantageous constraints, minimizing the risk of network failures. Theoretical analysis demonstrates comparable convergence rates between DREC and vanilla data-driven methods without compromising caching performance. Extensive experiments validate that D-REC outperforms conventional approaches in cache hit rate and load balancing while effectively enforcing predetermined reliability intervention modules. Copyright © 2024, The Authors. All rights reserved.

关键词： Wireless networks

Monge-Ampere Regularization for Learning Arbitrary Shapes from Point Clouds

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Chuanxiang Zhou, Yuanfeng Wei, Guangshun Ma, Long Hou, Junhui Liu, Yuan Wang, Wenping The School of Software Shandong University Jinan250100 China The Department of Computer Science City University of Hong Kong Hong Kong The College of Computing and Data Science Nanyang Technological University Singapore The Department of Computer Science and Engineering Texas A&M University College StationTX77843 United States

As commonly used implicit geometry representations, the signed distance function (SDF) is limited to modeling watertight shapes, while the unsigned distance function (UDF) is capable of representing various surfaces. However, its inherent theoretical shortcoming, i.e., the non-differentiability at the zero level set, would result in sub-optimal reconstruction quality. In this paper, we propose the scaled-squared distance function (S2DF), a novel implicit surface representation for modeling arbitrary surface types. S2DF does not distinguish between inside and outside regions while effectively addressing the non-differentiability issue of UDF at the zero level set. We demonstrate that S2DF satisfies a second-order partial differential equation of Monge-Ampere-type, allowing us to develop a learning pipeline that leverages a novel Monge-Ampere regularization to directly learn S2DF from raw unoriented point clouds without supervision from ground-truth S2DF values. Extensive experiments across multiple datasets show that our method significantly outperforms state-of-the-art supervised approaches that require ground-truth surface information as supervision for training. The code will be publicly available at https://***/chuanxiang-yang/S2DF. Copyright © 2024, The Authors. All rights reserved.

关键词： Supervised learning

TRAIN SMALL, INFER LARGE: MEMORY-EFFICIENT LORA TRAINING FOR LARGE LANGUAGE MODELS

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Jun Wang, Jue Li, Huan Shou, Lidan Chen, Ke You, Yang Xie, Guiming Gong, Xuejian Zhou, Kunlong The State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China College of Computer Science and Technology Zhejiang University China Department of Computer Science National University of Singapore Singapore AI Center Guangdong OPPO Mobile Telecommunications Corp. Ltd. China

Large Language Models (LLMs) have significantly advanced natural language processing with exceptional task generalization capabilities. Low-Rank Adaption (LoRA) offers a cost-effective fine-tuning solution, freezing the original model parameters and training only lightweight, low-rank adapter matrices. However, the memory footprint of LoRA is largely dominated by the original model parameters. To mitigate this, we propose LORAM, a memory-efficient LoRA training scheme founded on the intuition that many neurons in over-parameterized LLMs have low training utility but are essential for inference. LORAM presents a unique twist: it trains on a pruned (small) model to obtain pruned low-rank matrices, which are then recovered and utilized with the original (large) model for inference. Additionally, minimal-cost continual pre-training, performed by the model publishers in advance, aligns the knowledge discrepancy between pruned and original models. Our extensive experiments demonstrate the efficacy of LORAM across various pruning strategies and downstream tasks. For a model with 70 billion parameters, LORAM enables training on a GPU with only 20G HBM, replacing an A100-80G GPU for LoRA training and 15 GPUs for full fine-tuning. Specifically, QLORAM implemented by structured pruning combined with 4-bit quantization, for LLaMA-3.1-70B (LLaMA-2-70B), reduces the parameter storage cost that dominates the memory usage in low-rank matrix training by 15.81× (16.95×), while achieving dominant performance gains over both the original LLaMA-3.170B (LLaMA-2-70B) and LoRA-trained LLaMA-3.1-8B (LLaMA-2-13B). Code is available at https://***/junzhang-zj/LoRAM. © 2025, CC BY.

关键词： Graphics processing unit

MEAT: MEDIAN-ENSEMBLE ADVERSARIAL TRAINING FOR IMPROVING ROBUSTNESS AND GENERALIZATION

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hu, Zhaozhe Yin, Jia-Li Chen, Bin Lin, Luojun Chen, Bo-Hao Liu, Ximeng Fujian Province Key Laboratory of Information Security and Network Systems Fuzhou350108 China College of Computer Science and Big Data Fuzhou University Fuzhou350108 China Department of Computer Science and Engineering Yuan Ze University Taiwan

Self-ensemble adversarial training methods improve model robustness by ensembling models at different training epochs, such as model weight averaging (WA). However, previous research has shown that self-ensemble defense methods in adversarial training (AT) still suffer from robust overfitting, which severely affects the generalization performance. Empirically, in the late phases of training, the AT becomes more overfitting to the extent that the individuals for weight averaging also suffer from overfitting and produce anomalous weight values, which causes the self-ensemble model to continue to undergo robust overfitting due to the failure in removing the weight anomalies. To solve this problem, we aim to tackle the influence of outliers in the weight space in this work and propose an easy-to-operate and effective Median-Ensemble Adversarial Training (MEAT) method to solve the robust overfitting phenomenon existing in self-ensemble defense from the source by searching for the median of the historical model weights. Experimental results show that MEAT achieves the best robustness against the powerful AutoAttack and can effectively allievate the robust overfitting. We further demonstrate that most defense methods can improve robust generalization and robustness by combining with MEAT. Copyright © 2024, The Authors. All rights reserved.

关键词： Network security

Multi-Agent Systems for Autonomous IoT Network Management Using Distributed Reinforcement Learning

学校读者我要写书评

暂无评论

Multi-Agent Systems for Autonomous IoT Network Management Us...

International Symposium on Advanced Computing and Communication (ISACC)

作者： Neelamegam G Rajaram Venkatesan Ramya SR R.S. Ramya Akshya. J M. Sundarrajan Mani Deepak Choudhry Department of Computer Science and Engineering VSB College of Engineering and Technology Coimbatore Tamil Nadu India Department of Artificial Intelligence and Data Science Builders Engineering College Tirupur Tamil Nadu India Department of Computer Science and Engineering Dr NGP Institute of Technology Coimbatore Tamil Nadu India Department of Computer Science and Engineering Sri Ramakrishna Engineering College Coimbatore Tamil Nadu India Department of Computational Intelligence SRM Institute of Science and Technology Chennai Tamil Nadu India Department of Networking and Communications SRM Institute of Science and Technology Chennai Tamil Nadu India Department of Computing Technologies SRM Institute of Science and Technology Chennai Tamil Nadu India

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

The ever-growing complexity of IoT networks ignited by their wide scale adoption in applications such as smart cities, the industrial automation, and health care, compelled to develop sophisticated yet resource efficient and scalable network management solution. Centralized systems are traditional in architecture, which leads to higher latency and bottlenecks, while decentralized systems can distribute workloads however the lack of adaptability to real time, along with the difficulty of extracting maximum resource usage, are limitations. In recent years, reinforcement learning (RL) based approaches have taken shape as a promising alternative to facilitate the automated learning and optimisation of task management. However, there are two challenges for existing RL based methods: slow convergence, inefficient priority assignment of tasks, and poor coordination amongst agents in the case of dynamic, large scale IoT environment. To solve these challenges, in this research we propose a distributed reinforcement learning based multi agent framework for managing IoT network. The framework also integrates a task prioritization mechanism to dynamically choose an optimal task allocation solution. Further validation was performed in a simulated IoT environment where real world inspired datasets were used. The proposed framework demonstrated 30% more task throughput than centralized, 25% less latency than decentralized, and 40% more energy efficiency than current RL based systems. The system was further validated using advanced visualizations such as anomaly detection maps and resource allocation efficiency graphs, demonstrating its capacity to manage dynamic load of tasks and resource allocation. The proposed framework addresses the critical limitations of current methods, through scalable, adaptive, and energy efficient framework for managing IoT network, and accordingly helps advancing the intelligent and autonomous IoT systems.

关键词： Smart cities Reinforcement learning Medical services Throughput Dynamic scheduling Energy efficiency Real-time systems Resource management Optimization Multi-agent systems

Comprehensive Analysis of Autism Spectrum Disorder Detection Using Deep Learning

学校读者我要写书评

暂无评论

Comprehensive Analysis of Autism Spectrum Disorder Detection...

Sustainable Expert Systems (ICSES), International Conference on

作者： E. Sujatha R.Suguna Devi D. Pavai K. Saranya Department of Computer Science and Engineering Saveetha Engineering College (Autonomous) Chennai India Department of Electronics and Communication Engineering Saveetha Engineering College (Autonomous) Chennai India Department of Artificial Intelligence and Data Science Saveetha Engineering College (Autonomous) Chennai India Department of Computer Science and Engineering (Cyber Security) Saveetha Engineering College (Autonomous) Chennai India

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540371

Autism Spectrum Disorder (ASD) is a complex neurological condition characterized by a wide range of symptoms. Early and accurate diagnosis is crucial for effective intervention and support. This research reviews the established diagnostic tools, including clinical assessments, behavioral observations, genetic testing, and neuroimaging techniques. Additionally, we explore the potential of emerging technologies like machine learning and AI-based approaches in enhancing ASD diagnosis. By analyzing the strengths and limitations of various detection methods, this research provides a comprehensive overview of the current state of the field. The findings highlight the importance of continued research and innovation in improving ASD diagnosis for the benefit of affected individuals and their families.

关键词： Neuroimaging Deep learning Autism Technological innovation Accuracy Reviews Genetics Expert systems Testing

Fair yet Asymptotically Equal Collaborative Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lin, Xiaoqiang Xu, Xinyi Ng, See-Kiong Foo, Chuan-Sheng Low, Bryan Kian Hsiang Department of Computer Science National University of Singapore Singapore Institute for Infocomm Research A*STAR Singapore Institute of Data Science National University of Singapore Singapore

In collaborative learning with streaming data, nodes (e.g., organizations) jointly and continuously learn a machine learning (ML) model by sharing the latest model updates computed from their latest streaming data. For the more resourceful nodes to be willing to share their model updates, they need to be fairly incentivized. This paper explores an incentive design that guarantees fairness so that nodes receive rewards commensurate to their contributions. Our approach leverages an explore-then-exploit formulation to estimate the nodes' contributions (i.e., exploration) for realizing our theoretically guaranteed fair incentives (i.e., exploitation). However, we observe a "rich get richer" phenomenon arising from the existing approaches to guarantee fairness and it discourages the participation of the less resourceful nodes. To remedy this, we additionally preserve asymptotic equality, i.e., less resourceful nodes achieve equal performance eventually to the more resourceful/"rich" nodes. We empirically demonstrate in two settings with real-world streaming data: federated online incremental learning and federated reinforcement learning, that our proposed approach outperforms existing baselines in fairness and learning performance while remaining competitive in preserving equality. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

Re-rank Search Engine Results via Machine Learning

学校读者我要写书评

暂无评论

Re-rank Search Engine Results via Machine Learning

International Conference on Web Research (ICWR)

作者： Amir Hussein Ataei Monfared Amir Hossein Avizheh Faculty of Mathematical Sciences and Computer Kharazmi University Tehran Iran Department of Data and Computer Science Shahid Beheshti University Tehran Iran

Research on search engines has demonstrated their significant impact on information search and user behavior and highlighted the need for continued investigation of their effectiveness, efficiency, and ethical implications. Moreover, search engine optimization (SEO) has emerged as a crucial aspect of online content creation and marketing, as it involves optimizing websites and online materials to improve their visibility and ranking on search engine results pages, thereby increasing their reach and impact. SEO metrics provide valuable insight into a website’s search engine performance. However, the relative importance of these metrics remains unclear as search engine algorithms and keyword competitiveness can vary widely. Therefore, ongoing research is needed to better understand the relationship between SEO metrics and search engine rankings. Given the challenge of determining the relative importance of SEO metrics using traditional statistical methods, interested in applying machine learning techniques. By training models with custom datasets of three search engine results (Google, Bing, and DuckDuckGo) and their associated SEO metrics, we hope to gain a better understanding of the complex relationships between these variables. The first two pages of each search engine return the most relevant results. In this article, we propose two types of methods to do this. First, classify the page index of web search results. Second, learning ranking methods to rank them. LambdaRank has the best NDCG compared to other methods for Google and DuckDuckGo which are 0.86 and 0.93 respectively. RankNet is the best learning-to-rank method for Bing with 0.85 as the NDCG value. Logistic regression has the highest accuracy compared to other methods in page index classification for Bing and Google, which are 61.29% and 64.71%, respectively. K-nearest neighbor performs best for DuckDuckGo with an accuracy of 66.67%.

关键词：

Instruction-Driven Game Engine: A Poker Case Study

学校读者我要写书评

暂无评论

Instruction-Driven Game Engine: A Poker Case Study

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Wu, Hongqiu Liu, Xingyuan Wang, Yan Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China Tencent China

ISBN: (纸本)9798891761674

The Instruction-Driven Game Engine (IDGE) project aims to democratize game development by enabling a large language model (LLM) to follow free-form game descriptions and generate game-play processes. The IDGE allows users to create games simply by natural language instructions, which significantly lowers the barrier for game development. We approach the learning process for IDGEs as a Next State Prediction task, wherein the model autoregressively predicts the game states given player actions. The computation of game states must be precise;otherwise, slight errors could corrupt the game-play experience. This is challenging because of the gap between stability and diversity. To address this, we train the IDGE in a curriculum manner that progressively increases its exposure to complex scenarios. Our initial progress lies in developing an IDGE for Poker, which not only supports a wide range of poker variants but also allows for highly individualized new poker games through natural language inputs. This work lays the groundwork for future advancements in transforming how games are created and played. © 2024 Association for Computational Linguistics.

关键词：