检索结果-内蒙古大学图书馆

UAV-enabled Collaborative Beamforming via Multi-Agent Deep Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Saichao Sun, Geng Li, Jiahui Liang, Shuang Wu, Qingqing Wang, Pengfei Niyato, Dusit The College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun130012 China The College of Computing and Data Science Nanyang Technological University 639798 Singapore The School of Information Science and Technology Northeast Normal University Changchun130117 China The Department of Electronic Engineering Shanghai Jiao Tong University Shanghai200240 China The School of Computer Science and Technology Dalian University of Technology Dalian116024 China

In this paper, we investigate an unmanned aerial vehicle (UAV)-assistant air-to-ground communication system, where multiple UAVs form a UAV-enabled virtual antenna array (UVAA) to communicate with remote base stations by utilizing collaborative beamforming. To improve the work efficiency of the UVAA, we formulate a UAV-enabled collaborative beamforming multi-objective optimization problem (UCBMOP) to simultaneously maximize the transmission rate of the UVAA and minimize the energy consumption of all UAVs by optimizing the positions and excitation current weights of all UAVs. This problem is challenging because these two optimization objectives conflict with each other, and they are non-concave to the optimization variables. Moreover, the system is dynamic, and the cooperation among UAVs is complex, making traditional methods take much time to compute the optimization solution for a single task. In addition, as the task changes, the previously obtained solution will become obsolete and invalid. To handle these issues, we leverage the multi-agent deep reinforcement learning (MADRL) to address the UCBMOP. Specifically, we use the heterogeneous-agent trust region policy optimization (HATRPO) as the basic framework, and then propose an improved HATRPO algorithm, namely HATRPO-UCB, where three techniques are introduced to enhance the performance. Simulation results demonstrate that the proposed algorithm can learn a better strategy compared with other methods. Moreover, extensive experiments also demonstrate the effectiveness of the proposed techniques. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

Asymmetric Cross-Scale Alignment for Text-Based Person Search

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ji, Zhong Hu, Junhua Liu, Deyin Wu, Lin Yuanbo Zhao, Ye The School of Electrical and Information Engineering Tianjin University Tianjin300072 China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230039 China Department of Computer Science Swansea University SA1 8EN United Kingdom The Key Laboratory of Knowledge Engineering with Big Data School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China

Text-based person search (TBPS) is of significant importance in intelligent surveillance, which aims to retrieve pedestrian images with high semantic relevance to a given text description. This retrieval task is characterized with both modal heterogeneity and fine-grained matching. To implement this task, one needs to extract multi-scale features from both image and text domains, and then perform the cross-modal alignment. However, most existing approaches only consider the alignment confined at their individual scales, e.g., an image-sentence or a region-phrase scale. Such a strategy adopts the presumable alignment in feature extraction, while overlooking the cross-scale alignment, e.g., image-phrase. In this paper, we present a transformer-based model to extract multi-scale representations, and perform Asymmetric Cross-Scale Alignment (ACSA) to precisely align the two modalities. Specifically, ACSA consists of a global-level alignment module and an asymmetric cross-attention module, where the former aligns an image and texts on a global scale, and the latter applies the cross-attention mechanism to dynamically align the cross-modal entities in region/image-phrase scales. Extensive experiments on two benchmark datasets CUHK-PEDES and RSTPReid demonstrate the effectiveness of our approach. Codes are available at https://***/mulhjh/ACSA. Copyright © 2022, The Authors. All rights reserved.

关键词： Alignment

Hypergraph-driven soft semantics flexible learning for visible–infrared person re-identification

学校读者我要写书评

暂无评论

engineering Applications of Artificial Intelligence 2025年 158卷

作者： Zhu, Jiacheng Ge, Hongwei Liu, Yuxuan Wu, Chunguo Fan, Jiulin School of Computer Science and Technology Dalian University of Technology No. 2 Linggong Road Dalian Liaoning 116024 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University No. 2699 Qianjin Street Changchun Jilin 130012 China Huadian Coal Industry Group Co Ltd. No. 2 Xuanwumennei Street Beijing 100031 China

Visible–infrared person re-identification (VI-ReID) aims to match the images of the person across different modalities. The main challenge in the engineering application of VI-ReID lies in the considerable modality gap between visible and infrared images. Existing methods primarily focus on learning low-order hard semantics to reduce the modality gap, such as specific body parts (e.g., arms, legs, and hands), which are modality-specific and sensitive to cross-modality variations, leading to difficult modality alignment. However, high-order soft semantics contain more modality-invariant features that can be flexibly learned by the model to better align the cross-modality features and reduce the modality gap. To better learn soft semantics, we propose a novel, hypergraph-driven soft semantics flexible learning network (HSFLNet), which extracts hierarchical semantics and flexibly explores the relationships among the extracted soft semantics by using hypergraph neural networks (HGNNs). Specifically, first, we propose a soft semantics mining (SSM) module to capture and flexibly fuse hierarchical features, which integrates low- and high-level semantics across channel and spatial dimensions to align modalities. Second, a hypergraph-driven soft semantics flexible learning (HSFL) module is designed, which employs HGNNs to explore the relationships among soft semantics. These semantics are adaptively learned through gating mechanisms to capture modality-invariant features, thereby reducing the modality gap. We evaluate the performance of HSFLNet on SYSU-MM01, RegDB, and low-light cross-modality (LLCM) datasets, achieving a Rank-1/mean average precision of 75.09%/72.11%, 95.82%/92.42%, and 65.42%/68.55%, respectively. Experimental results demonstrate that HSFLNet outperforms state-of-the-art VI-ReID methods. Our code is available at https://***/Jiacheng813/HSFLNet. © 2025 Elsevier Ltd

关键词： Cross-modality retrieval Hypergraph neural networks Soft semantics Visible–infrared person re-identification

Multi-site MRI classification using Weighted federated learning based on Mixture of Experts domain adaptation

学校读者我要写书评

暂无评论

Multi-site MRI classification using Weighted federated learn...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Tian Bai Yingfang Zhang Yuzhao Wang Yanguo Qin Fa Zhang College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun China The Department of Orthopaedics The Second Hospital of Jilin University Changchun China School of Medical Technology Beijing Institute of Technology Beijing China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Deep learning often requires large amounts of data from different institutions. Federated learning, as a distributed training framework, enables multiple participants to collaboratively train models without collecting data together and hence protecting data privacy, but the datasets from different institutions usually bring the problem of domain shift, which affects the performance of the model. When addressing domain shift, previous works often use a single global model to share parameters. Therefore, we propose a novel method to train multiple public models with different structures under the federated framework to improve the reliability and robustness of the public models. And each participant keeps its own domain-tuned private model, the private model does not share parameters with other participants. We use Mixture of Experts (MoE) domain adaptation to dynamically combine different public models and private model, which utilizes the similarity between different datasets to update the parameters of the public models. We apply the proposed method to the multi-site Magnetic resonance imaging (MRI) end-to-end classification, and the experiments demonstrate its effectiveness.

关键词： Weight measurement Training Adaptation models Three-dimensional displays Federated learning Magnetic resonance imaging Biological system modeling

A Multi-Task-Based Deep Multi-Scale Information Fusion Method for Intelligent Diagnosis of Bearing Faults

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Xin, Ruihao Wang, Tiantian Miao, Fengbo Yu, Cuinan Feng, Xin College of Information and Control Engineering Jilin Institute of Chemical Technology Jilin Jilin132000 China College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Jilin Changchun130012 China School of Science Jilin Institute of Chemical Technology Jilin Jilin132000 China

The use of deep learning for fault diagnosis is already a commonly used method. However, complex operating conditions under different working conditions significantly impact bearing vibration signals. Integrating the discriminative information of fault type and size into the deep learning model to achieve rich multi-task fault feature diagnosis still deserves attention. This study proposes a deep multi-task-based multi-scale feature fusion network MEAT(multi-task-based deep multi-scale feature fusion network) model to address these issues. Solve the limitations and poor adaptability of traditional convolutional neural network models under complex work. This model considers two sub-tasks, fault scale discrimination, and fault type discrimination, in the fault diagnosis multi-classification task through multi-task mapping decomposition. First, multi-dimensional features are extracted by convolution at different scales to obtain multi-dimensional fault information at different levels. Then these features are weighted and fused using a multi-layer attention mechanism to get accurate diagnosis results of bearing faults. © 2022, The Authors. All rights reserved.

关键词： Failure analysis

A surrogate model based genetic algorithm for complex problem solving 6

学校读者我要写书评

暂无评论

A surrogate model based genetic algorithm for complex proble...

6th Annual International Conference on Network and Information Systems for Computers, ICNISC 2020

作者： Pei, Ying Gao, Hao Han, Xiaosong College of Information Engineering Changchun University of Finance and Economics Changchun130122 China Key Laboratory for Symbol Computation Knowledge Engineering of National Education Ministry College of Computer Science and Technology College of Software Jilin University Changchun130012 China

It is well known that when the fitness function is relatively complex, the optimization time cost of the genetic algorithm will be extremely huge. To address this issue, the surrogate model was employed to predict the fitness value of the optimization problem, to reduce the number of actual calculated fitness values. In this paper, BP neural network, the least square method and support vector machine were fused in the genetic algorithm to evaluate partial individuals' fitness. Sufficient benchmark numerical experiments were conducted, and the results proved that the strategy could reduce the calculating counts of fitness function on similar accuracy basis compared with simple genetic algorithm. © 2020 Journal of Physics: Conference Series.

关键词： Genetic algorithms

An Empirical Study on Information Extraction using Large Language Models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Han, Ridong Yang, Chaohao Peng, Tao Tiwari, Prayag Wan, Xiang Liu, Lu Wang, Benyou College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China College of Software Jilin University China Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China School of Information Technology Halmstad University Sweden

Human-like large language models (LLMs), especially the most powerful and popular ones in OpenAI’s GPT family, have proven to be very helpful for many natural language processing (NLP) related tasks. Therefore, various attempts have been made to apply LLMs to information extraction (IE), which is a fundamental NLP task that involves extracting information from unstructured plain text. To demonstrate the latest representative progress in LLMs’ information extraction ability, we assess the information extraction ability of GPT-4 (the latest version of GPT at the time of writing this paper) from four perspectives: Performance, Evaluation Criteria, Robustness, and Error Types. Our results suggest a visible performance gap between GPT-4 and state-of-the-art (SOTA) IE methods. To alleviate this problem, considering the LLMs’ human-like characteristics, we propose and analyze the effects of a series of simple prompt-based methods, which can be generalized to other LLMs and NLP tasks. Rich experiments show our methods’ effectiveness and some of their remaining issues in improving GPT-4’s information extraction ability. Copyright © 2023, The Authors. All rights reserved.

关键词： Information retrieval

Sample efficient imitation learning via reward function trained in advance

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, LiHua Liu, Quan School of Computer Science and Technology Soochow University Soochow China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Soochow China Key Laboratory of Symbolic Computation Knowledge Engineering of Ministry of Education Jilin University Jilin China

Imitation learning (IL) is a framework that learns to imitate expert behavior from demonstrations. Recently, IL shows promising results on high dimensional and control tasks. However, IL typically suffers from sample inefficiency in terms of environment interaction, which severely limits their application to simulated domains. In industrial applications, learner usually have a high interaction cost, the more interactions with environment, the more damage it causes to the environment and the learner itself. In this article, we make an effort to improve sample efficiency by introducing a novel scheme of inverse reinforcement learning. Our method, which we call Model Reward Function Based Imitation Learning (MRFIL), uses an ensemble dynamic model as a reward function, what is trained with expert demonstrations. The key idea is to provide the agent with an incentive to match the demonstrations over a long horizon, by providing a positive reward upon encountering states in line with the expert demonstration distribution. In addition, we demonstrate the convergence guarantee for new objective function. Experimental results show that our algorithm reaches the competitive performance and significantly reducing the environment interactions compared to IL methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Demonstrations

Reinforced iterative knowledge distillation for cross-lingual named entity recognition

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liang, Shining Gong, Ming Pei, Jian Shou, Linjun Zuo, Wanli Zuo, Xianglin Jiang, Daxin College of Computer Science and Technology Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education STCA NLP Group Microsoft School of Computing Science Simon Fraser University

Named entity recognition (NER) is a fundamental component in many applications, such as Web Search and Voice Assistants. Although deep neural networks greatly improve the performance of NER, due to the requirement of large amounts of training data, deep neural networks can hardly scale out to many languages in an industry setting. To tackle this challenge, cross-lingual NER transfers knowledge from a rich-resource language to languages with low resources through pre-trained multilingual language models. Instead of using training data in target languages, cross-lingual NER has to rely on only training data in source languages, and optionally adds the translated training data derived from source languages. However, the existing cross-lingual NER methods do not make good use of rich unlabeled data in target languages, which is relatively easy to collect in industry applications. To address the opportunities and challenges, in this paper we describe our novel practice in Microsoft to leverage such large amounts of unlabeled data in target languages in real production settings. To effectively extract weak supervision signals from the unlabeled data, we develop a novel approach based on the ideas of semi-supervised learning and reinforcement learning. The empirical study on three benchmark data sets verifies that our approach establishes the new state-of-the-art performance with clear edges. Now, the NER techniques reported in this paper are on their way to become a fundamental component for Web ranking, Entity Pane, Answers Triggering, and Question Answering in the Microsoft Bing search engine. Moreover, our techniques will also serve as part of the Spoken Language Understanding module for a commercial voice assistant. We plan to open source the code of the prototype framework after deployment. © 2021, CC BY-NC-SA.

关键词： Deep neural networks