检索结果-内蒙古大学图书馆

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Learning

学校读者我要写书评

暂无评论

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Lea...

IEEE International Conference on Industrial Informatics (INDIN)

作者： Weipeng Cao Xuyang Yao Zhiwu Xu Yinghui Pan Yixuan Sun Dachuan Li Bohua Qiu Muheng Wei Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen) Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Stony Brook University New York United States Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China ZhenDui Industry Artificial Intelligence Co. Ltd Shenzhen China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output by the final layer while disregarding potential performance enhancements from other layers. Indeed, numerous researchers have visually depicted variations in the features learned across different layers of neural networks. Motivated by this observation, we propose a Vision Transformer (ViT)-based GZSL method named Depth-Aware Multi-Modal ViT (DAM2ViT), which exploits multi-level features of ViT. DAM2ViT incorporates a multi-modal interaction block to align semantic information of categories across multiple layers, thereby augmenting the model's capacity to learn associations between visual and semantic spaces. Extensive experiments conducted on three benchmark datasets (i.e., CUB, SUN, AWA2) have showcased that DAM2ViT achieves competitive results compared to state-of-the-art methods.

关键词： Visualization Adaptation models Semantics Zero shot learning Neural networks Termination of employment Transformers Market research Sun Optimization

Inverse learning of black-box aggregator for robust Nash equilibrium

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Guanpu Xu, Gehui He, Fengxiang Tao, Dacheng Parisini, Thomas Johansson, Karl Henrik Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm100 44 Sweden Digital Futures Stockholm100 44 Sweden Artificial Intelligence and its Applications Institute School of Informatics University of Edinburgh EdinburghEH8 9AB United Kingdom College of Computing & Data Science Nanyang Technological University Singapore639798 Singapore Department of Electrical and Electronic Engineering Imperial College London LondonSW7 2AZ United Kingdom Department of Engineering and Architecture University of Trieste Trieste34127 Italy

In this note, we investigate the robustness of Nash equilibria (NE) in multi-player aggregative games with coupling constraints. There are many algorithms for computing an NE of an aggregative game given a known aggregator. When the coupling parameters are affected by uncertainty, robust NE need to be computed. We consider a scenario where players' weight in the aggregator is unknown, making the aggregator kind of "a black box". We pursue a suitable learning approach to estimate the unknown aggregator by proposing an inverse variational inequality-based relationship. We then utilize the counterpart to reconstruct the game and obtain first-order conditions for robust NE in the worst case. Furthermore, we characterize the generalization property of the learning methodology via an upper bound on the violation probability. Simulation experiments show the effectiveness of the proposed inverse learning approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Inverse problems

Towards Communication-efficient Federated Learning via Sparse and Aligned Adaptive Optimization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Deng, Xiumei Li, Jun Wei, Kang Shi, Long Xiong, Zeihui Ding, Ming Chen, Wen Jin, Shi Poor, H. Vincent School of Electronic and Optical Engineering Nanjing University of Science and Technology Nanjing210094 China The Department of Computing Hong Kong Polytechnic University 999077 Hong Kong The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore Data61 CSIRO SydneyNSW2015 Australia Department of Electronics Engineering Shanghai Jiao Tong University Shanghai200240 China The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China Department of Electrical and Computer Engineering Princeton University NJ08544 United States

Adaptive moment estimation (Adam), as a Stochastic Gradient Descent (SGD) variant, has gained widespread popularity in federated learning (FL) due to its fast convergence. However, federated Adam (FedAdam) algorithms suffer from a threefold increase in uplink communication overhead compared to federated SGD (FedSGD) algorithms, which arises from the necessity to transmit both local model updates and first and second moment estimates from distributed devices to the centralized server for aggregation. Driven by this issue, we propose a novel sparse FedAdam algorithm called FedAdam-SSM, wherein distributed devices sparsify the updates of local model parameters and moment estimates and subsequently upload the sparse representations to the centralized server. To further reduce the communication overhead, the updates of local model parameters and moment estimates incorporate a shared sparse mask (SSM) into the sparsification process, eliminating the need for three separate sparse masks. Theoretically, we develop an upper bound on the divergence between the local model trained by FedAdam-SSM and the desired model trained by centralized Adam, which is related to sparsification error and imbalanced data distribution. By minimizing the divergence bound between the model trained by FedAdam-SSM and centralized Adam, we optimize the SSM to mitigate the learning performance degradation caused by sparsification error. Additionally, we provide convergence bounds for FedAdam-SSM in both convex and non-convex objective function settings, and investigate the impact of local epoch, learning rate and sparsification ratio on the convergence rate of FedAdam-SSM. Experimental results show that FedAdam-SSM outperforms baselines in terms of convergence rate (over 1.1× faster than the sparse FedAdam baselines) and test accuracy (over 14.5% ahead of the quantized FedAdam baselines). Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

Machine-Learning Methods for Detecting Tuberculosis in Ziehl-Neelsen Stained Slides: A Systematic Literature Review

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Tamura, Gabriel Llano, Gonzalo Aristizábal, Andrés Valencia, Juan Sua, Luz Fernanda Fernandez, Liliana Department of Computing and Intelligent Systems Universidad Icesi Valle del Cauca Cali Colombia Center of Artificial Intelligence and Data Science Universidad Icesi Valle del Cauca Cali Colombia Universidad Icesi Valle del Cauca Cali Colombia Faculty of Health Sciences Universidad Icesi Valle del Cauca Cali Colombia Department of Pathology and Laboratory Medicine Fundación Valle del Lili Valle del Cauca Cali Colombia Department of Internal Medicine Pulmonology Service Fundación Valle del Lili Valle del Cauca Cali Colombia

In recent years, different Machine Learning (ML) methods applied to medical image analysis have been increasingly used for the detection of Mycobacterium Tuberculosis (MT) in Ziehl-Neelsen stained human samples, since manual detection and counting of bacteria is a tedious, costly, error-prone and slow task. This paper presents the results of a Systematic Literature Review (SLR) that comprehensively surveyed and analyzed the current stateof-the-art ML methods and approaches that have been used for TB detection in the period of 2017-2022, as well as their achieved metrics and the characteristics of the datasets on which they were applied. The primary goal of this⋆ This work was supported by Tecnoquímicas Corp. in partnertship with Fundación Valle del Lili and Universidad Icesi with the aim to strenghten the research and development of technology in health in the Valle del Cauca region. © 2023, The Authors. All rights reserved.

关键词： Computer vision

Generative AI for Space-Air-Ground Integrated Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Ruichen Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui Jamalipour, Abbas Zhang, Ping Kim, Dong In The College of Computing and Data Science Nanyang Technological University Singapore The Department of Electrical and Electronic Engineering University of Hong Kong Pok Fu Lam Hong Kong The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore The University of Sydney SydneyNSW2006 Australia The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Recently, generative AI technologies have emerged as a significant advancement in artificial intelligence field, renowned for their language and image generation capabilities. Meantime, space-air-ground integrated network (SAGIN) is an integral part of future B5G/6G for achieving ubiquitous connectivity. Inspired by this, this article explores an integration of generative AI in SAGIN, focusing on potential applications and case study. We first provide a comprehensive review of SAGIN and generative AI models, highlighting their capabilities and opportunities of their integration. Benefiting from generative AI’s ability to generate useful data and facilitate advanced decision-making processes, it can be applied to various scenarios of SAGIN. Accordingly, we present a brief survey on their integration, including channel modeling and channel state information (CSI) estimation, joint air-space-ground resource allocation, intelligent network deployment, semantic communications, image extraction and processing, security and privacy enhancement. Next, we propose a framework that utilizes a generative diffusion model (GDM) to construct channel information map to enhance quality of service for SAGIN. Simulation results demonstrate the effectiveness of the proposed framework. Finally, we discuss potential research directions for generative AI-enabled SAGIN. © 2023, CC BY.

关键词： Generative adversarial networks

Accelerated Sparse Recovery via Gradient Descent with Nonlinear Conjugate Gradient Momentum

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hu, Mengqi Lou, Yifei Wang, Bao Yan, Ming Yang, Xiu Ye, Qiang Department of Industrial and Systems Engineering Lehigh University 200 West Packer Avenue BethlehemPA18015 United States Department of Mathematical Sciences The University of Texas at Dallas 800 W. Campbell Rd RichardsonTX75080 United States Department of Mathematics and Scientific Computing Imaging Institute The University of Utah 72 Central Campus Dr Salt Lake CityUT84102 United States School of Data Science The Chinese University of Hong Kong Shenzhen 2001 Longxiang Blvd Guangdong Shenzhen China Department of Computational Mathematics Science and Engineering Department of Mathematics Michigan State University 428 South Shaw Lane East LansingMI48824 United States Department of Mathematics University of Kentucky LexingtonKY40513 United States

This paper applies an idea of adaptive momentum for the nonlinear conjugate gradient to accelerate optimization problems in sparse recovery. Specifically, we consider two types of minimization problems: a (single) differentiable function and the sum of a non-smooth function and a differentiable function. In the first case, we adopt a fixed step size to avoid the traditional line search and establish the convergence analysis of the proposed algorithm for a quadratic problem. This acceleration is further incorporated with an operator splitting technique to deal with the non-smooth function in the second case. We use the convex 1 and the nonconvex 1 − 2 functionals as two case studies to demonstrate the efficiency of the proposed approaches over traditional methods. © 2022, CC BY-SA.

关键词： Momentum

Low-Loss Zero-Index Waveguides and Devices

学校读者我要写书评

暂无评论

Low-Loss Zero-Index Waveguides and Devices

Conference on Lasers and Electro-Optics (CLEO)

作者： Tian Dong Tianxiang Dai Ye Chen Yueyang Liu Hancheng Liu Yiting Wang Anqi Ma Haifeng Hu Lihua Xu Le Zhao Weiguo Chu Chao Peng Jianwei Wang Yang Li Department of Precision Instrument State Key Laboratory of Precision Measurement Technology and Instrument Tsinghua University Beijing China State Key Laboratory for Mesoscopic Physics School of Physics Peking University Beijing China Department of Electronics and Frontiers Science Center for Nano-optoelectronics State Key Laboratory of Advanced Optical Communication Systems and Networks Peking University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Nanofabrication Laboratory National Center for Nanoscience and Technology Beijing China

We report flexible zero-index waveguides and devices whose loss is two orders of magnitude lower than the state of the art, enabling phase-error-free high-dense photonic integrated circuits for classical and quantum i... 详细信息

ISBN: (纸本)9798350369311

关键词： Optical losses Quantum computing Photonic integrated circuits Waveguide lasers Information processing Lasers and electrooptics Electro-optical waveguides

Machine Learning and Physics-Driven Modelling and Simulation of Multiphase systems

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Basha, Nausheen Arcucci, Rossella Angeli, Panagiota Anastasiou, Charitos Abadie, Thomas Casas, César Quilodrán Chen, Jianhua Cheng, Sibo Chagot, Loïc Galvanin, Federico Heaney, Claire E. Hossein, Fria Hu, Jinwei Kovalchuk, Nina Kalli, Maria Kahouadji, Lyes Kerhouant, Morgan Lavino, Alessio Liang, Fuyue Nathanael, Konstantia Magri, Luca Lettieri, Paola Materazzi, Massimiliano Erigo, Matteo Pico, Paula Pain, Christopher C. Shams, Mosayeb Simmons, Mark Traverso, Tullio Valdes, Juan Pablo Wolffs, Zef Zhu, Kewei Zhuang, Yilin Matar, Omar K. Department of Chemical Engineering Imperial College London United Kingdom Department of Earth Science & Engineering Imperial College London United Kingdom Department of Chemical Engineering University College London United Kingdom School of Chemical Engineering University of Birmingham United Kingdom Data Science Institute Department of Computing Imperial College London United Kingdom State Key Laboratory of Multiphase Complex Systems Institute of Process Engineering Chinese Academy of Sciences Beijing China Centre for AI-Physics Modelling Imperial-X White City Campus Imperial College London United Kingdom The Alan Turing Institute British Library 96 Euston Road LondonNW1 2DB United Kingdom Department of Aeronautics Imperial College London United Kingdom Institute of Physics University of Amsterdam Science Park Amsterdam904 Netherlands Nikhef Science Park Amsterdam105 Netherlands Department of Computer Science University of York United Kingdom

We highlight the work of a multi-university collaborative programme, PREMIERE (PREdictive Modelling with QuantIfication of UncERtainty for MultiphasE systems), which is at the intersection of multi-physics and machine learning, aiming to enhance predictive capabilities in complex multiphase flow systems across diverse length and time scales. Our contributions encompass a variety of approaches, including the Design of Experiments for nanoparticle synthesis optimisation, Generalised Latent Assimilation models for drop coalescence prediction, Bayesian regularised artificial neural networks, eXtreme Gradient Boosting for microdroplet formation prediction, and a sub-sampling based adversarial neural network for predicting slug flow behaviour in two-phase pipe flows. Additionally, we introduce a generalised latent assimilation technique, Long Short-Term Memory networks for sequence forecasting mixing performance in stirred and static mixers, active learning via Bayesian optimisation to recover coalescence model parameters for high current density electrolysers, Gaussian process regression for drop size distribution predictions for sprays, and acoustic emission signal inversion using gradient boosting machines to characterise particle size distribution in fluidised beds. We also offer perspectives on the development of a shape optimisation framework that leverages the use of a multi-fidelity multiphase emulator. The results presented have applications in chemical synthesis, microfluidics, product manufacturing, and green hydrogen generation. © 2024, The Authors. All rights reserved.

关键词： Forecasting

Prompt-based Code Completion via Multi-Retrieval Augmented Generation

学校读者我要写书评

暂无评论

ACM Transactions on Software Engineering and Methodology 1000年

作者： Hanzhuo Tan Qi Luo Ling Jiang Zizheng Zhan Jing Li Haotian Zhang Yuqun Zhang Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology China Department of Computer Science and Engineering Southern University of Science and Technology China Kuaishou Technology China Department of Computing and the Research Centre on Data Science and Artificial Intelligence (RCDSAI) the Hong Kong Polytechnic University China

Automated code completion, aiming at generating subsequent tokens from unfinished code, has significantly benefited from recent progress in pre-trained Large Language Models (LLMs). However, these models often suffer from coherence issues and hallucinations when dealing with complex code logic or extrapolating beyond their training data. Existing Retrieval Augmented Generation (RAG) techniques partially address these issues by retrieving relevant code with a separate encoding model where the retrieved snippet serves as contextual reference for code completion. However, their retrieval scope is subject to a singular perspective defined by the encoding model, which largely overlooks the complexity and diversity inherent in code semantics. To address this limitation, we propose ProCC, a code completion framework leveraging prompt engineering and the contextual multi-armed bandits algorithm to flexibly incorporate and adapt to multiple perspectives of code. ProCC first employs a prompt-based multi-retriever system which crafts prompt templates to elicit LLM knowledge to understand code semantics with multiple retrieval perspectives. Then, it adopts the adaptive retrieval selection algorithm to incorporate code similarity into the decision-making process to determine the most suitable retrieval perspective for the LLM to complete the code. Experimental results demonstrate that ProCC outperforms a widely-studied code completion technique RepoCoder by 7.92% on the public benchmark CCEval, 3.19% in HumanEval-Infilling, 2.80% on our collected open-source benchmark suite, and 4.48% on the private-domain benchmark suite collected from Kuaishou Technology in terms of Exact Match. ProCC also allows augmenting fine-tuned techniques in a plug-and-play manner, yielding an averaged 6.5% improvement over the fine-tuned model.

关键词： Code Completion Multi-Retriever Prompting