检索结果-内蒙古大学图书馆

Hyperbolic Neural Network Based Preselection for Expensive Multi-Objective Optimization

学校读者我要写书评

暂无评论

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Li, Bingdong Yang, Yanting Hong, Wenjing Yang, Peng Zhou, Aimin Shanghai Institute of AI for Education the School of Computer Science and Technology and the Shanghai Frontiers Science Center of Molecule Intelligent Syntheses East China Normal University Shanghai China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computer Science and Engineering Guangdong Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology Shenzhen China

A series of surrogate-assisted evolutionary algorithms (SAEAs) have been proposed for expensive multi-objective optimization problems (EMOPs), building cheap surrogate models to replace the expensive real function evaluations. However, the search efficiency of these SAEAs is not yet satisfactory. More efforts are needed to further exploit useful information from the real function evaluations in order to better guide the search process. Facing this challenge, this paper proposes a Hyperbolic Neural Network (HNN) based preselection operator to accelerate the optimization process based on limited evaluated solutions. First, the preselection task is modeled as a multi-label classification problem where solutions are classified into different layers (ordinal categories) through -relaxed objective aggregation. Second, in order to resemble the hierarchical structure of candidate solutions, a hyperbolic neural network is applied to tackle the multi-label classification problem. The reason for using HNN is that hyperbolic spaces more closely resemble hierarchical structures than Euclidean spaces. Moreover, to alleviate the data deficiency issue, a data augmentation strategy is employed for training the HNN. In order to evaluate its performance, the proposed HNN-based preselection operator is embedded into two surrogate-assisted evolutionary algorithms. Experimental results on two benchmark test suites and three real-world problems with up to 11 objectives and 150 decision variables involving seven state-of-the-art algorithms demonstrate the effectiveness of the proposed method. IEEE

关键词： Multiobjective optimization

FedMoS: Taming Client Drift in Federated Learning with Double Momentum and Adaptive Selection

学校读者我要写书评

暂无评论

FedMoS: Taming Client Drift in Federated Learning with Doubl...

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Xiong Wang Yuxin Chen Yuqing Li Xiaofei Liao Hai Jin Bo Li National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Cyber Science and Engineering Wuhan University Wuhan China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

Federated learning (FL) enables massive clients to collaboratively train a global model by aggregating their local updates without disclosing raw data. Communication has become one of the main bottlenecks that prolongs the training process, especially under large model variances due to skewed data distributions. Existing efforts mainly focus on either single momentum-based gradient descent, or random client selection for potential variance reduction, yet both often lead to poor model accuracy and system efficiency. In this paper, we propose FedMoS, a communication-efficient FL framework with coupled double momentum-based update and adaptive client selection, to jointly mitigate the intrinsic variance. Specifically, FedMoS maintains customized momentum buffers on both server and client sides, which track global and local update directions to alleviate the model discrepancy. Taking momentum results as input, we design an adaptive selection scheme to provide a proper client representation during FL aggregation. By optimally calibrating clients’ selection probabilities, we can effectively reduce the sampling variance, while ensuring unbiased aggregation. Through a rigid analysis, we show that FedMoS can attain the theoretically optimal ${{\mathcal{O}}}\left({{T^{ - 2/3}}}\right)$ convergence rate. Extensive experiments using real-world datasets further validate the superiority of FedMoS, with 58%-87% communication reduction for achieving the same target performance compared to state-of-the-art techniques.

关键词：

Game Solving with Online Fine-Tuning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wu, Ti-Rong Guei, Hung Wei, Ting Han Shih, Chung-Chin Chin, Jui-Te Wu, I-Chen Institute of Information Science Academia Sinica Taiwan Department of Computing Science University of Alberta Canada Department of Computer Science National Yang Ming Chiao Tung University Taiwan Research Center for Information Technology Innovation Academia Sinica Taiwan

Game solving is a similar, yet more difficult task than mastering a game. Solving a game typically means to find the game-theoretic value (outcome given optimal play), and optionally a full strategy to follow in order to achieve that outcome. The AlphaZero algorithm has demonstrated super-human level play, and its powerful policy and value predictions have also served as heuristics in game solving. However, to solve a game and obtain a full strategy, a winning response must be found for all possible moves by the losing player. This includes very poor lines of play from the losing side, for which the AlphaZero self-play process will not encounter. AlphaZero-based heuristics can be highly inaccurate when evaluating these out-of-distribution positions, which occur throughout the entire search. To address this issue, this paper investigates applying online fine-tuning while searching and proposes two methods to learn tailor-designed heuristics for game solving. Our experiments show that using online fine-tuning can solve a series of challenging 7x7 Killall-Go problems, using only 23.54% of computation time compared to the baseline without online fine-tuning. Results suggest that the savings scale with problem size. Our method can further be extended to any tree search algorithm for problem solving. Our code is available at https://***/papers/neurips2023-online-fine-tuning-solver. Copyright © 2023, The Authors. All rights reserved.

关键词： Trees (mathematics)

On the Computational Complexity of Schrödinger Operators

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zheng, Yufan Leng, Jiaqi Liu, Yizhou Wu, Xiaodi Department of Computer Science University of Maryland United States Joint Center for Quantum Information and Computer Science University of Maryland United States Department of Mathematics University of Maryland United States Simons Institute for the Theory of Computing Department of Mathematics UC Berkeley United States Physics of Living Systems Department of Physics MIT United States Department of Mechanical Engineering MIT United States

We study computational problems related to the Schrödinger operator H = −∆ + V in the real space under the condition that (i) the potential function V is smooth and has its value and derivative bounded within some polynomial of n and (ii) V only consists of O(1)-body interactions. We prove that (i) simulating the dynamics generated by the Schrödinger operator implements universal quantum computation, i.e., it is BQP-hard, and (ii) estimating the ground energy of the Schrödinger operator is as hard as estimating that of local Hamiltonians with no sign problem (a.k.a. stoquastic Hamiltonians), i.e., it is StoqMA-complete. This result is particularly intriguing because the ground energy problem for general bosonic Hamiltonians is known to be QMA-hard and it is widely believed that StoqMA (Equation presented) QMA. Copyright © 2024, The Authors. All rights reserved.

关键词： Hamiltonians

LEARNING CAUSAL ALIGNMENT FOR RELIABLE DISEASE DIAGNOSIS

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Mingzhou Lee, Ching-Wen Sun, Xinwei Yu, Xueqing Yu, Qiao Wang, Yizhou School of Computer Science Peking University China School of Data Science Fudan University China Computer Science Department Shanghai Jiao Tong University China Center on Frontiers of Computing Studies Peking University China Institute for Artificial Intelligence Peking University China Nat’l Eng. Research Center of Visual Technology Peking University China State Key Lab. of General Artificial Intelligence Peking University China

Aligning the decision-making process of machine learning algorithms with that of experienced radiologists is crucial for reliable diagnosis. While existing methods have attempted to align their diagnosis behaviors to those of radiologists reflected in the training data, this alignment is primarily associational rather than causal, resulting in pseudo-correlations that may not transfer well. In this paper, we propose a causality-based alignment framework towards aligning the model’s decision process with that of experts. Specifically, we first employ counterfactual generation to identify the causal chain of model decisions. To align this causal chain with that of experts, we propose a causal alignment loss that enforces the model to focus on causal factors underlying each decision step in the whole causal chain. To optimize this loss that involves the counterfactual generator as an implicit function of the model’s parameters, we employ the implicit function theorem equipped with the conjugate gradient method for efficient estimation. We demonstrate the effectiveness of our method on two medical diagnosis applications, showcasing faithful alignment to radiologists. Code is publicly available at https://***/lmz123321/Causal_alignment. © 2023, CC BY.

关键词： Radiology

REFROM: Responsive, Energy-Efficient Frame Rendering for Mobile Devices

学校读者我要写书评

暂无评论

REFROM: Responsive, Energy-Efficient Frame Rendering for Mob...

International Symposium on Low Power Electronics and Design (ISLPED)

作者： Tsung-Yen Hsu Yi-Shen Chen Yun-Chih Chen Yuan-Hao Chang Tei-Wei Kuo Department of Computer Science and Information Engineering National Taiwan University Department of Electronic and Computer Engineering National Taiwan University of Science and Technology Institute of Information Science Academia Sinica Mohamed bin Zayed University of Artificial Intelligence High Performance and Scientific Computing Center National Taiwan University

The increasing demand for high-quality graphics on mobile devices necessitates a high frame rate for display refresh. However, current process scheduling and memory management policies fail to consider the computation demands of frame rendering because they are optimized for saving energy and resource utilization. This leads to unresponsive displays for mobile users due to rendering delays. Accurately estimating computation demands is challenging for the mobile operating system, particularly under memory pressure, without display-specific semantics from user space. Moreover, the complexity of frame rendering makes it infeasible to schedule them with real-time policies. To address these issues, we propose a new framework called REFROM that utilizes a history-based frame time estimator to analyze frame time samples from UI threads and predict the computation requirements of upcoming frames. Experimental results demonstrate that REFROM reduces the number of delayed frames by up to 40% and improves up to 4% energy efficiency compared to the existing approaches.

关键词：

QNN-QRL: Quantum Neural Network Integrated with Quantum Reinforcement Learning for Quantum Key Distribution

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Behera, Bikash K. Al-Kuwari, Saif Farouk, Ahmed Pvt. Ltd. WB Mohanpur741246 India Qatar Center for Quantum Computing College of Science and Engineering Hamad Bin Khalifa University Doha Qatar Department of Computer Science Faculty of Computers and Artificial Intelligence Hurghada University Hurghada Egypt

Quantum key distribution (QKD) has emerged as a critical component of secure communication in the quantum era, ensuring information-theoretic security. Despite its potential, there are issues in optimizing key generation rates, enhancing security, and incorporating QKD into practical implementations. This research introduces a unique framework for incorporating quantum machine learning (QML) algorithms, notably quantum reinforcement learning (QRL) and quantum neural networks (QNN), into QKD protocols to improve key generation performance. Here, we present two novel QRL-based algorithms, QRL-V.1 and QRL-V.2, and propose the standard BB84 and B92 protocols by integrating QNN algorithms to form QNN-BB84 and QNN-B92. Furthermore, we combine QNN with the above QRL-based algorithms to produce QNN-QRL-V.1 and QNN-QRL-V.2. These unique algorithms and established protocols are compared using evaluation metrics such as accuracy, precision, recall, F1 score, confusion matrices, and ROC curves. The results from the QNN-based proposed algorithms show considerable improvements in key generation quality. The existing and proposed models are investigated in the presence of different noisy channels to check their robustness. The proposed integration of QML algorithms into QKD protocols and their noisy analysis create a new paradigm for efficient key generation, which advances the practical implementation of QKD systems. © 2025, CC BY.

关键词： Quantum cryptography

Automatic Section Classification in Spanish Clinical Narratives Using Chunked Named Entity Recognition

学校读者我要写书评

暂无评论

Automatic Section Classification in Spanish Clinical Narrati...

2023 Iberian Languages Evaluation Forum, IberLEF 2023

作者： Carvallo, Andrés Rojas, Matías Muñoz-Castro, Carlos Aracena, Claudio Guerra, Rodrigo Pizarro, Benjamín Dunstan, Jocelyn National Center for Artificial Intelligence Santiago Chile Faculty of Physical and Mathematical Sciences Universidad de Chile Santiago Chile Department of Computer Science Pontificia Universidad Católica de Chile Santiago Chile Institute for Mathematical Computing Pontificia Universidad Católica de Chile Santiago Chile Center for Mathematical Modeling Santiago Chile Millenium Institute Foundational Research on Data Santiago Chile

The extraction and classification of important information from Spanish Electronic Clinical Narratives (ECNs) can be challenging due to the complexity of the clinical text and the limited availability of labeled data. In this paper, we introduce a chunked Named Entity Recognition model designed to parse and classify sections of ECNs into predefined categories. The model aims to improve section identification and classification accuracy within ECNs in the context of the IberLEF ClinAIS Task. Our system achieves a promising performance, obtaining a weighted B2 score of.6958, demonstrating its capability to accurately distinguish borders and boundaries between sections. The paper concludes with a comprehensive analysis of the results, discussing potential implications and suggesting directions for further improvements in clinical text analysis. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Classification (of information)

Removal of degradation from ancient stone inscription images using deep learning techniques

学校读者我要写书评

暂无评论

Removal of degradation from ancient stone inscription images...

3rd International Conference on Machine Learning and Data Engineering, ICMLDE 2024

作者： Nair, Bipin B.J. Veiyo, P.M. Gupta, Deepti Ravi, Vinayakumar Vijay, G. Sachin, A.S. Akhil, S. Department of Computer Science School of Computing Amrita Vishwa Vidyapeetham Mysore India Subhani Department of Computer Information Systems Texas A&M University-Central Texas KilleenTX76549 United States Center for Artificial Intelligence Prince Mohammad Bin Fahd University Khobar Saudi Arabia

Important knowledge, wisdom, and language are lost over time due to fading, erosion, and environmental variables that complicate ancient stone inscriptions. To help with protection efforts, the proposed study employs an image binarization model based on well-known deep neural networks algorithms. The methods durability is enhanced, and a more effective stone engraving preservation strategy is ensured by the application of multiple deep neural networks architectures. This research presents a model that has attained an incredible average 90.76% accuracy. This was made possible by extensive training with 437 images from temples in Karnataka. The deep neural networks technique is used to enhance the efficiency and accuracy of stone inscription preservation while reducing the challenges caused by environmental factors such as algae. © 2025 The Author(s).

关键词： Deep neural networks