检索结果-内蒙古大学图书馆

FedCL: Federated multi-Phase Curriculum Learning to Synchronously Correlate User Heterogeneity

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Mingjie Guo, Jianxiong Jia, Weijia The Guangdong Key Lab of AI and Multi-Modal Data Processing Department of Computer Science BNU-HKBU United International College Zhuhai519087 China The Advanced Institute of Natural Sciences Beijing Normal University Zhuhai519087 China The Guangdong Key Lab of AI and Multi-Modal Data Processing BNU-HKBU United International College Zhuhai519087 China

Federated Learning (FL) is a decentralized learning method used to train machine learning algorithms. In FL, a global model iteratively collects the parameters of local models without accessing their local data. However, a significant challenge in FL is handling the heterogeneity of local data distribution, which often results in a drifted global model that is difficult to converge. To address this issue, current methods employ different strategies such as knowledge distillation, weighted model aggregation, and multi-task learning. These approaches are referred to as asynchronous FL, as they align user models either locally or post-hoc, where model drift has already occurred or has been underestimated. In this paper, we propose an active and synchronous correlation approach to address the challenge of user heterogeneity in FL. Specifically, our approach aims to approximate FL as standard deep learning by actively and synchronously scheduling user learning pace in each round with a dynamic multi-phase curriculum. A global curriculum is formed by an auto-regressive auto-encoder that integrates all user curricula on the server. This global curriculum is then divided into multiple phases and broadcast to users to measure and align the domain-agnostic learning pace. Empirical studies demonstrate that our approach outperforms existing asynchronous approaches in terms of generalization performance, even in the presence of severe user heterogeneity. Copyright © 2022, The Authors. All rights reserved.

关键词： Curricula

A Fast Task Offloading Optimization Framework for IRS-Assisted multi-Access Edge Computing System

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wu, Jianqiu Yu, Zhongyi Guo, Jianxiong Tang, Zhiqing Wang, Tian Jia, Weijia The Guangdong Key Lab of Ai and Multi-Modal Data Processing Department of Computer Science Bnuhkbu United International College 519087 Zhuhai China The Advanced Institute of Natural Sciences Beijing Normal University Zhuhai519087 China The Guangdong Key Lab of Ai and Multi-Modal Data Processing BNU-HKBU United International College Zhuhai519087 China

Terahertz communication networks and intelligent reflecting surfaces exhibit significant potential in advancing wireless networks, particularly within the domain of aerial-based multi-access edge computing systems. These technologies enable efficient offloading of computational tasks from user electronic devices to Unmanned Aerial Vehicles or local execution. For the generation of high-quality task-offloading allocations, conventional numerical optimization methods often struggle to solve challenging combinatorial optimization problems within the limited channel coherence time, thereby failing to respond quickly to dynamic changes in system conditions. To address this challenge, we propose a deep learning-based optimization framework called Iterative Order-Preserving policy Optimization (IOPO), which enables the generation of energy-efficient task-offloading decisions within milliseconds. Unlike exhaustive search methods, IOPO provides continuous updates to the offloading decisions without resorting to exhaustive search, resulting in accelerated convergence and reduced computational complexity, particularly when dealing with complex problems characterized by extensive solution spaces. Experimental results demonstrate that the proposed framework can generate energy-efficient task-offloading decisions within a very short time period, outperforming other benchmark methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Iterative methods

multi-attribute Based Influence Maximization in Social Networks 15th

学校读者我要写书评

暂无评论

Multi-attribute Based Influence Maximization in Social Netw...

15th International Conference on Algorithmic Aspects in Information and Management, AaiM 2021

作者： Ni, Qiufen Guo, Jianxiong Du, Hongmin W. School of Computers Guangdong University of Technology Guangzhou510006 China BNU-UIC Institute of Artificial Intelligence and Future Networks Beijing Normal University at Zhuhai Guangdong Zhuhai519087 China Guangdong Key Lab of AI and Multi-Modal Data Processing BNU-HKBU United International College Guangdong Zhuhai519087 China Accounting and Information Systems Department Rutgers University PiscatawayNJ08854 United States

ISBN: (纸本)9783030931759

Viral marketing on social networks is an important application and hot research problem. Most of the related work on viral marketing focuses on the spread of single information, while a product may associate with multi-attribute in real life. Information on multiple attributes of a product propagates in the social networks simultaneously and independently. The attribute information that a user receives will determine whether he would purchase the product or not. We extend the traditional single information influence maximization problem to the multi-attribute based Influence Maximization Problem (MIMP). We present the multi-dimensional IC model (MIC model) for the proposed problem. The objective function for MIMP is proved to be non-submodular, then we solve the problem with the Sandwich Algorithm, which can get a max{f(SU)f¯(SU),f̲(SL∗)f(So∗)}(1-1/e) approximation ratio to the optimal solution. Experiments are conducted in two real world datasets to verify the correctness and effectiveness of the proposed algorithm. © 2021, Springer Nature Switzerland AG.

关键词： Approximation algorithms

Efficient Serverless Function Scheduling at the Network Edge

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lou, Jiong Tang, Zhiqing Yuan, Shijing Li, Jie Wu, Chengtao Department of Computer Science and Engineering Shanghai Jiao Tong University China Guangdong Key Lab of AI and Multi-Modal Data Processing BNU-HKBU United International College China

Serverless computing is a promising approach for edge computing since its inherent features, e.g., lightweight virtualization, rapid scalability, and economic efficiency. However, previous studies have not studied well the issues of significant cold start latency and highly dynamic workloads in serverless function scheduling, which are exacerbated at the resource-limited network edge. In this paper, we formulate the Serverless Function Scheduling (SFS) problem for resource-limited edge computing, aiming to minimize the average response time. To efficiently solve this intractable scheduling problem, we first consider a simplified offline form of the problem and design a polynomial-time optimal scheduling algorithm based on each function’s weight. Furthermore, we propose an Enhanced Shortest Function First (ESFF) algorithm, in which the function weight represents the scheduling urgency. To avoid frequent cold starts, ESFF selectively decides the initialization of new function instances when receiving requests. To deal with dynamic workloads, ESFF judiciously replaces serverless functions based on the function weight at the completion time of requests. Extensive simulations based on real-world serverless request traces are conducted, and the results show that ESFF consistently and substantially outperforms existing baselines under different settings. © 2023, CC BY.

关键词： Polynomial approximation

A Feature Weighting Particle Swarm Optimization Method to Identify Biomarker Genes

学校读者我要写书评

暂无评论

A Feature Weighting Particle Swarm Optimization Method to Id...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xubin Wang Weijia Jia Guangdong Key Lab of AI and Multi-Modal Data Processing BNU-HKBU United International College Institute of Artificial Intelligence and Future Networks Beijing Normal University Zhuhai China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

The discovery of biomarker genes from gene expression data is a hot topic for understanding the mechanisms underlying disease etiology. However, while the collection of high-dimensional gene expression data has been made possible by the adoption of technologies such as DNA microarray, it also poses challenges for the identification of key disease-causing genes due to its high-dimensional nature. To address this problem, we propose a feature weighting particle swarm optimization method (FWPSO) for efficiently identifying biomarker genes from high-dimensional microarray data. Specifically, there are two significant phases in FWPSO: 1) Feature Weighting Phase: Features will be discriminated into relevant and irrelevant based on the evolutionary performance of individuals in the PSO population in each generation, and features will be assigned weights based on this. 2) Feature Selection Phase: By focusing the search on a feature set that have been determined to be relevant based on the results of the previous phase, the PSO population will improve the efficiency of removing redundant features and discovering the most related genes. Both phases work together and operate in synergy to achieve the optimized results. The experimental results on four microarray datasets shows that FWPSO not only reduces the number of feature dimensions to a large extent, but also achieves higher classification accuracy compared to other methods, demonstrating the effectiveness of our method. Our implementation of FWPSO is available at https://***/wangxb96/FWPSO.

关键词： Sociology Focusing DNA Feature extraction Gene expression Particle swarm optimization Statistics

A result based portable framework for spoken language understanding

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cheng, Lizhi Jia, Weijai Yang, Wenmian Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Guangdong Key Lab of AI and Multi-Modal Data Processing BNU-HKBU United International College Zhuhai Guangdong China

Spoken language understanding (SLU), which is a core component of the task-oriented dialogue system, has made substantial progress in the research of single-turn dialogue. However, the performance in multi-turn dialogue is still not satisfactory in the sense that the existing multi-turn SLU methods have low portability and compatibility for other single-turn SLU models. Further, existing multi-turn SLU methods do not exploit the historical predicted results when predicting the current utterance, which wastes helpful information. To gap those shortcomings, in this paper, we propose a novel Result-based Portable Framework for SLU (RPFSLU). RPFSLU allows most existing single-turn SLU models to obtain the contextual information from multi-turn dialogues and takes full advantage of predicted results in the dialogue history during the current prediction. Experimental results on the public dataset KVRET have shown that all SLU models in baselines acquire enhancement by RPFSLU on multi-turn SLU tasks. Copyright © 2021, The Authors. All rights reserved.

关键词： Speech processing

An Effective Non-Autoregressive Model for Spoken Language Understanding

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cheng, Lizhi Jia, Weijia Yang, Wenmian Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Guangdong Key Lab of AI and Multi-Modal Data Processing BNU-HKBU United International College Zhuhai Guangdong China

Spoken Language Understanding (SLU), a core component of the task-oriented dialogue system, expects a shorter inference latency due to the impatience of humans. Non-autoregressive SLU models clearly increase the inference speed but suffer uncoordinated-slot problems caused by the lack of sequential dependency information among each slot chunk. To gap this shortcoming, in this paper, we propose a novel non-autoregressive SLU model named Layered-Refine Transformer, which contains a Slot label Generation (SLG) task and a Layered Refine Mechanism (LRM). SLG is defined as generating the next slot label with the token sequence and generated slot labels. With SLG, the non-autoregressive model can efficiently obtain dependency information during training and spend no extra time in inference. LRM predicts the preliminary SLU results from Transformer’s middle states and utilizes them to guide the final prediction. Experiments on two public datasets indicate that our model significantly improves SLU performance (1.5% on Overall accuracy) while substantially speed up (more than 10 times) the inference process over the state-of-the-art baseline. © 2021, CC0.

关键词： Speech processing

Improving the efficiency and robustness of deepfakes detection through precise geometric features

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Sun, Zekun Han, Yujie Hua, Zeyu Ruan, BNa Jia, Weijia Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Guangdong China Key Lab of AI and Multi-Modal Data Processing BNU-HKBU United International College Guangdong China

Deepfakes is a branch of malicious techniques that transplant a target face to the original one in videos, resulting in serious problems such as infringement of copyright, confusion of information, or even public panic. Previous efforts for Deepfakes videos detection mainly focused on appearance features, which have a risk of being bypassed by sophisticated manipulation, also resulting in high model complexity and sensitiveness to noise. Besides, how to mine the temporal features of manipulated videos and exploit them is still an open question. We propose an efficient and robust framework named LRNet for detecting Deepfakes videos through temporal modeling on precise geometric features. A novel calibration module is devised to enhance the precision of geometric features, making it more discriminative, and a two-stream Recurrent Neural Network (RNN) is constructed for sufficient exploitation of temporal features. Compared to previous methods, our proposed method is lighter-weighted and easier to train. Moreover, our method has shown robustness in detecting highly compressed or noise corrupted videos. Our model achieved 0.999 AUC on FaceForensics++ dataset. Meanwhile, it has a graceful decline in performance (-0.042 AUC) when faced with highly compressed videos. © 2021, CC BY.

关键词： Recurrent neural networks

Online Container Scheduling for Low-Latency IoT Services in Edge Cluster Upgrade: A Reinforcement Learning Approach

学校读者我要写书评

暂无评论

Online Container Scheduling for Low-Latency IoT Services in ...

2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

作者： Cui, Hanshuai Tang, Zhiqing Lou, Jiong Jia, Weijia Beijing Normal University Institute of Artificial Intelligence and Future Networks Zhuhai519087 China Beijing Normal University School of Artificial Intelligence Beijing100875 China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200240 China BNU-HKBU United International College Guangdong Key Lab of Ai and Multi-Modal Data Processing Zhuhai519087 China

ISBN: (纸本)9798350345384

In Mobile Edge Computing (MEC), Internet of Things (IoT) devices offload computationally-intensive tasks to edge nodes, where they are executed within containers, reducing the reliance on centralized cloud infrastructure. Frequent up-grades are essential to maintain the efficient and secure operation of edge clusters. However, traditional cloud cluster upgrade strategies are ill-suited for edge clusters due to their geographically distributed nature and resource limitations. Therefore, it is crucial to properly schedule containers and upgrade edge clusters to minimize the impact on running tasks. In this paper, we propose a low-latency container scheduling algorithm for edge cluster upgrades. Specifically: 1) We formulate the online container scheduling problem for edge cluster upgrade to minimize the total task latency. 2) We propose a policy gradient-based reinforcement learning algorithm to address this problem, considering the unique characteristics of MEC. 3) Experimental results demonstrate that our algorithm reduces total task latency by approximately 27% compared to baseline algorithms. © 2023 IEEE.

关键词： Reinforcement learning