检索结果-内蒙古大学图书馆

Sanity-checking pruning methods: random tickets can win the jackpot 20

学校读者我要写书评

暂无评论

Sanity-checking pruning methods: random tickets can win the ...

Proceedings of the 34th International Conference on Neural Information Processing Systems

作者： Jingtong Su Yihang Chen Tianle Cai Tianhao Wu Ruiqi Gao Liwei Wang Jason D. Lee Yuanpei College Peking University School of Mathematical Sciences Peking University Department of Electrical Engineering Princeton University and Zhongguancun Haihua Institute for Frontier Information Technology Key Laboratory of Machine Perception MOE School of EECS Peking University and Center for Data Science Peking University Department of Electrical Engineering Princeton University

ISBN: (纸本)9781713829546

Network pruning is a method for reducing test-time computational resource requirements with minimal performance degradation. Conventional wisdom of pruning algorithms suggests that: (1) Pruning methods exploit information from training data to find good subnetworks; (2) The architecture of the pruned network is crucial for good performance. In this paper, we conduct sanity checks for the above beliefs on several recent unstructured pruning methods and surprisingly find that: (1) A set of methods which aims to find good subnetworks of the randomly-initialized network (which we call "initial tickets"), hardly exploits any information from the training data; (2) For the pruned networks obtained by these methods, randomly changing the preserved weights in each layer, while keeping the total number of preserved weights unchanged per layer, does not affect the final performance. These findings inspire us to choose a series of simple data-independent prune ratios for each layer, and randomly prune each layer accordingly to get a subnetwork (which we call "random tickets"). Experimental results show that our zero-shot random tickets outperform or attain a similar performance compared to existing "initial tickets". In addition, we identify one existing pruning method that passes our sanity checks. We hybridize the ratios in our random ticket with this method and propose a new method called "hybrid tickets", which achieves further improvement.

关键词：

Dist-PU: Positive-Unlabeled Learning from a Label Distribution Perspective

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhao, Yunrui Xu, Qianqian Jiang, Yangbangyan Wen, Peisong Huang, Qingming School of Computer Science and Technology University of Chinese Academy of Sciences China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS China State Key Laboratory of Information Security Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences China

Positive-Unlabeled (PU) learning tries to learn binary classifiers from a few labeled positive examples with many unlabeled ones. Compared with ordinary semi-supervised learning, this task is much more challenging due to the absence of any known negative labels. While existing cost-sensitive-based methods have achieved state-of-the-art performances, they explicitly minimize the risk of classifying unlabeled data as negative samples, which might result in a negative-prediction preference of the classifier. To alleviate this issue, we resort to a label distribution perspective for PU learning in this paper. Noticing that the label distribution of unlabeled data is fixed when the class prior is known, it can be naturally used as learning supervision for the model. Motivated by this, we propose to pursue the label distribution consistency between predicted and ground-truth label distributions, which is formulated by aligning their expectations. Moreover, we further adopt the entropy minimization and Mixup regularization to avoid the trivial solution of the label distribution consistency on unlabeled data and mitigate the consequent confirmation bias. Experiments on three benchmark datasets validate the effectiveness of the proposed method. Code available at: https://***/Ray-rui/Dist-PU-Positive-UnlabeledLearning-from-a-Label-Distribution-Perspective. Copyright © 2022, The Authors. All rights reserved.

关键词： Entropy

Digital Mahjong System: Towards Precise Cognitive Assessment with IoT Technologies 1

学校读者我要写书评

暂无评论

24th International Conference on Human-Computer Interaction, HCII 2022

作者： An, Ning Hu, Enze Guo, Yanrui Yang, Jiaoyun Au, Rhoda Ding, Huitong School of Computer Science and Information Engineering Hefei University of Technology Hefei China Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei China National Smart Eldercare International S&T Cooperation Base Hefei University of Technology Hefei China Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Shenzhen Corecloud Innovation Technology Co. Ltd. Shenzhen China Key Laboratory of Knowledge Engineering with Big Data of Ministry of Education Hefei University of Technology Hefei China Department of Anatomy and Neurobiology Neurology and Framingham Heart Study Boston University School of Medicine Boston United States Department of Epidemiology Boston University School of Public Health Boston United States

ISBN: (数字)9783031179020

ISBN: (纸本)9783031179013

To the best of our knowledge, this paper is the first to apply IoT technologies to transform the popular Mahjong game into a Digital Mahjong System (DMS) for digitally performing cognitive assessments. People have started exploring digital cognitive assessment tools for better objectivity and simplification. However, most of these tools are not friendly for older adults. This paper aims to address this issue by integrating IoT technologies with Mahjong to make cognitive assessment simpler and more engaging for older adults. DMS has the following features: 1) integrating motion tracking devices into Mahjong tiles and transferring them into Digital Mahjong Tiles (DMTs), which can precisely capture their moving trajectory during the assessment, 2) using a Near Field Communication reader to configure DMT’s primary data, 3) supporting Over-The-Air Device Firmware Update that can be done remotely via Bluetooth, and 4) developing a charging base that can charge 16 DMTs simultaneously using Qi wireless charging standard. With further testing, the DMS has the potential to become a digital platform to implement and test various cognitive assessment tools integrating Mahjong elements. © 2022, Springer Nature Switzerland AG.

关键词： Internet of things

Pathological brain detection based on online sequential extreme learning machine

学校读者我要写书评

暂无评论

Pathological brain detection based on online sequential extr...

IEEE International Conference on Progress in Informatics and Computing (PIC)

作者： Siyuan Lu Hainan Wang Xueyan Wu Shuihua Wang School of Computer Science and Technology Nanjing Normal University Nanjing Jiangsu China State Key Lab of CAD & CG Zhejiang University Hangzhou Zhejiang China Key laboratory of symbolic computation and knowledge engineering of ministry of education Jilin University Changchun Jilin China Key Laboratory of Statistical information technology and data mining State Statistics Bureau Chengdu Sichuan China Department of Electrical Engineering CUNY New York NY USA

ISBN: (纸本)9781509034857

Magnetic resonance imaging (MRI) is a kind of imaging modality, which offers clearer images of soft tissues than computed tomography (CT). It is especially suitable for brain disease detection. It is beneficial to detect diseases automatically and accurately. We proposed a pathological brain detection method based on brain MR images and online sequential extreme learning machine. First, seven wavelet entropies (WE) were extracted from each brain MR image to form the feature vector. Then, an online sequential extreme learning machine (OS-ELM) was trained to differentiate pathological brains from the healthy controls. The experiment results over 132 brain MRIs showed that the proposed approach achieved a sensitivity of 93.51%, a specificity of 92.22%, and an overall accuracy of 93.33%, which suggested that our method is effective.

关键词： Entropy Discrete wavelet transforms Feature extraction Pathology Training Magnetic resonance imaging Diseases

SLMP: A Scientific Literature Management Platform Based on Large Language Models

学校读者我要写书评

暂无评论

SLMP: A Scientific Literature Management Platform Based on L...

IEEE International Conference on Big knowledge (ICBK)

作者： Menghao Guo Jinling Jiang Fan Wu Shanxin Sun Chen Zhang Wenhui Li Zeyi Sun Guangyong Chen Xindong Wu Research Center for Life Sciences Computing Zhejiang Lab Hangzhou China Research Center for Data Hub and Security Zhejiang Lab Hangzhou China Research Center for High Efficiency Computing System Zhejiang Lab Hangzhou China Key Laboratory of Knowledge Engineering With Big Data Hefei University of Technology Hefei China

ISBN: (数字)9798331508821

ISBN: (纸本)9798331508838

This paper presents a Scientific Literature Management Platform (SLMP, demo link 1 ) based on large language models (LLMs). The platform consists of four modules: literature management, literature extraction, literature retrieval, and question answering. The core techniques used to support the four modules across the platform include a fine-tuned model PaperExtractGPT and a continual pre-training model ChatPaperGPT based on ChatGLM 2 using the data from scientific research literature, responsible for information extraction and communication, respectively. Due to their powerful capabilities in natural language understanding and generation, LLMs can understand complex scientific concepts based on the provided contexts, and thus generate high-quality texts and conduct in-depth information retrieval and question answering. Our platform can help researchers manage and utilize literature more effectively and efficiently for finding relevant literature, obtaining required information, and generating new knowledge.

关键词： Training Large language models knowledge graphs Information retrieval data models Question answering (information retrieval)

CloudBrain-NMR: An Intelligent Cloud Computing Platform for NMR Spectroscopy Processing, Reconstruction and Analysis

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Guo, Di Li, Sijin Liu, Jun Tu, Zhangren Qiu, Tianyu Xu, Jingjing Feng, Liubin Lin, Donghai Hong, Qing Lin, Meijin Lin, Yanqin Qu, Xiaobo School of Computer and Information Engineering Fujian Engineering Research Center for Medical Data Mining and Application Xiamen University of Technology Xiamen361024 China Department of Electronic Science Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance Xiamen University Xiamen361005 China The Key Laboratory for Chemical Biology of Fujian Province MOE Key Laboratory of Spectrochemical Analysis & Instrumentation College of Chemistry and Chemical Engineering Xiamen University Xiamen361005 China Department of Applied Marine Physics and Engineering College of Ocean and Earth Sciences Xiamen University Xiamen361102 China The China Mobile Group Xiamen361005 China

Nuclear Magnetic Resonance (NMR) spectroscopy has served as a powerful analytical tool for studying molecular structure and dynamics in chemistry and biology. However, the processing of raw data acquired from NMR spectrometers and subsequent quantitative analysis involves various specialized tools, which necessitates comprehensive knowledge in programming and NMR. Particularly, the emerging deep learning tools is hard to be widely used in NMR due to the sophisticated setup of computation. Thus, NMR processing is not an easy task for chemist and biologists. In this work, we present CloudBrain-NMR, an intelligent online cloud computing platform designed for NMR data reading, processing, reconstruction, and quantitative analysis. The platform is conveniently accessed through a web browser, eliminating the need for any program installation on the user side. CloudBrain-NMR uses parallel computing with graphics processing units and central processing units, resulting in significantly shortened computation time. Furthermore, it incorporates state-of-the-art deep learning-based algorithms offering comprehensive functionalities that allow users to complete the entire processing procedure without relying on additional software. This platform has empowered NMR applications with advanced artificial intelligence processing. CloudBrain-NMR is openly accessible for free usage at https://***/***. © 2023, CC BY.

关键词： Deep learning

ConsistencyDet: A Robust Object Detector with a Denoising Paradigm of Consistency Model

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jiang, Lifan Wang, Zhihui Wang, Changmiao Li, Ming Leng, Jiaxu Wu, Xindong the College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266510 China Shenzhen Research Institute of Big Data Shenzhen518172 China Key Laboratory of Intelligent Education Technology and Application Zhejiang Normal University Jinhua321004 China the Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications Chongqing400065 China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing210094 China the Key Laboratory of Knowledge Engineering with Big Data the Ministry of Education of China China School of Computer Science and Information Technology Hefei University of Technology Hefei230009 China

Object detection, a quintessential task in the realm of perceptual computing, can be tackled using a generative methodology. In the present study, we introduce a novel framework designed to articulate object detection as a denoising diffusion process, which operates on the perturbed bounding boxes of annotated entities. This framework, termed ConsistencyDet, leverages an innovative denoising concept known as the Consistency Model. The hallmark of this model is its self-consistency feature, which empowers the model to map distorted information from any temporal stage back to its pristine state, thereby realizing a "one-step denoising" mechanism. Such an attribute markedly elevates the operational efficiency of the model, setting it apart from the conventional Diffusion Model. Throughout the training phase, ConsistencyDet initiates the diffusion sequence with noise-infused boxes derived from the ground-truth annotations and conditions the model to perform the denoising task. Subsequently, in the inference stage, the model employs a denoising sampling strategy that commences with bounding boxes randomly sampled from a normal distribution. Through iterative refinement, the model transforms an assortment of arbitrarily generated boxes into definitive detections. Comprehensive evaluations employing standard benchmarks, such as MS-COCO and LVIS, corroborate that ConsistencyDet surpasses other leading-edge detectors in performance metrics. Our code is available at https://***/Tankowa/ConsistencyDet. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

PWG-IDS: An intrusion detection model for solving class imbalance in IIoT networks using generative adversarial networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Lei Jiang, Shuaimin Shen, Xiajiong Gupta, Brij B. Tian, Zhihong Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng47500 China Institute of Data and Knowledge Engineering Henan University Kaifeng47500 China School of Computer and Information Engineering Henan University Kaifeng47500 China National Institute of Technology Kurukshetra India Asia University Taichung Taiwan The Department of Cyberspace Insitute of Advanced Technology GuangZhou University GuangZhou510006 China

With the continuous development of industrial IoT (IIoT) technology, network security is becoming more and more important. And intrusion detection is an important part of its security. However, since the amount of attack traffic is very small compared to normal traffic, this imbalance makes intrusion detection in it very difficult. To address this imbalance, an intrusion detection system called pretraining Wasserstein generative adversarial network intrusion detection system (PWG-IDS) is proposed in this paper. This system is divided into two main modules: 1) In this module, we introduce the pretraining mechanism in the Wasserstein generative adversarial network with gradient penalty (WGAN-GP) for the first time, firstly using the normal network traffic to train the WGAN-GP, and then inputting the imbalance data into the pre-trained WGAN-GP to retrain and generate the final required data. 2) Intrusion detection module: We use LightGBM as the classification algorithm to detect attack traffic in IIoT networks. The experimental results show that our proposed PWG-IDS outperforms other models, with F1-scores of 99% and 89% on the 2 datasets, respectively. And the pretraining mechanism we proposed can also be widely used in other GANs, providing a new way of thinking for the training of GANs. Copyright © 2021, The Authors. All rights reserved.

关键词： Intrusion detection

LEGNN: A Label Ensemble Perspective for Training a Label-Noise-Resistant GNN with Reduced Complexity

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhao, Rui Shi, Bin Liang, Zhiming Ruan, Jianfei Dong, Bo Lin, Lu School of Computer Science and Technology Xi'an Jiaotong University China Ministry of Education Key Laboratory of Intelligent Networks and Network Security China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering China School of Distance Education Xi'an Jiaotong University China College of Information Sciences and Technology Penn State University United States

Graph Neural Networks (GNNs) have been widely employed for semi-supervised node classification tasks on graphs. However, the performance of GNNs is significantly affected by label noise, that is, a small amount of incorrectly labeled nodes can substantially misguide model training. Mainstream solutions define node classification with label noise (NCLN) as a reliable labeling task, often introducing node similarity with quadratic computational complexity to more accurately assess label reliability. To this end, in this paper, we introduce the Label Ensemble Graph Neural Network (LEGNN), a lower complexity method for robust GNNs training against label noise. LEGNN reframes NCLN as a label ensemble task, gathering informative multiple labels instead of constructing a single reliable label, avoiding high-complexity computations for reliability assessment. Specifically, LEGNN conducts a two-step process: bootstrapping neighboring contexts and robust learning with gathered multiple labels. In the former step, we apply random neighbor masks for each node and gather the predicted labels as a high-probability label set. This mitigates the impact of inaccurately labeled neighbors and diversifies the label set. In the latter step, we utilize a partial label learning based strategy to aggregate the high-probability label information for model training. Additionally, we symmetrically gather a low-probability label set to counteract potential noise from the bootstrapped high-probability label set. Extensive experiments on six datasets demonstrate that LEGNN achieves outstanding performance while ensuring efficiency. Moreover, it exhibits good scalability on dataset with over one hundred thousand nodes and one million edges. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks