检索结果-内蒙古大学图书馆

Classifying Galaxy Morphologies with Few-Shot Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Zhirui Zou, Zhiqiang Li, Nan Chen, Yanli College of Computer Nanjing University of Posts and Telecommunications Nanjing China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Jiangsu Nanjing China Key Laboratory of Optical Astronomy National Astronomical Observatories Chinese Academy of Sciences Beijing China University of Chinese Academy of Science Beijing China

The taxonomy of galaxy morphology is critical in astrophysics as the morphological properties are powerful tracers of galaxy evolution. With the upcoming Large-scale Imaging Surveys, billions of galaxy images challenge astronomers to accomplish the classification task by applying traditional methods or human inspection. Consequently, machine learning, in particular supervised deep learning, has been widely employed to classify galaxy morphologies recently due to its exceptional automation, efficiency, and accuracy. However, supervised deep learning requires extensive training sets, which causes considerable workloads;also, the results are strongly dependent on the characteristics of training sets, which leads to biased outcomes potentially. In this study, we attempt Few-shot Learning to bypass the two issues. Our research adopts the dataset from Galaxy Zoo Challenge Project on Kaggle, and we divide it into five categories according to the corresponding truth table. By classifying the above dataset utilizing few-shot learning based on Siamese Networks and supervised deep learning based on AlexNet, VGG 16, and ResNet 50 trained with different volumes of training sets separately, we find that few-shot learning achieves the highest accuracy in most cases, and the most significant improvement is 21% compared to AlexNet when the training sets contain 1000 images. In addition, to guarantee the accuracy is no less than 90%, few-shot learning needs ∼6300 images for training, while ResNet 50 requires ∼13000 images. Considering the advantages stated above, foreseeably, few-shot learning is suitable for the taxonomy of galaxy morphology and even for identifying rare astrophysical objects, despite limited training sets consisting of observational data only. Copyright © 2022, The Authors. All rights reserved.

关键词： Galaxies

IMPACT: Importance-Informed Prefetching and Caching for I/O-Bound DNN Training

学校读者我要写书评

暂无评论

IEEE Transactions on Computers 2025年

作者： Chen, Weijian He, Shuibing Zhang, Ruidong Zhang, Xuechen Chen, Ping Yang, Siling Qu, Haoyang Zhan, Xuan Zhejiang University State Key Laboratory of Blockchain and Data Security China Institute of Blockchain and Data Security Hangzhou China Zhejiang Key Laboratory of Big Data Intelligent Computing China Washington State University Vancouver School of Engineering and Computer Science VancouverWA98686 United States

Fetching large amounts of DNN training data from storage systems causes high I/O latency and GPU stalls. Importance sampling can reduce data processing on GPUs while maintaining model accuracy, but current frameworks lack a prefetching and caching layer to optimize data fetches and cache management based on sample importance. This leads to unnecessary fetches, poor cache hit ratios, and random I/Os. We present ImPACT, an importance-informed prefetching and caching system, to accelerate I/O-bound DNN training. First, we propose an importance-informed prefetching technique to reduce the prefetching of unimportant data. Then, we introduce an importance-aware caching layer, partitioned into two regions: H-cache and L-cache, which store samples of high importance and low importance respectively. Rather than using recency or frequency, we manage data items in H-cache according to their corresponding sample importance. When there is a cache miss in L-cache, we use sample substitutability and dynamic packaging to improve the cache hit ratio and reduce the number of random I/Os. Our experimental results show that ImPACT has a negligible impact on training accuracy while speeding up DNN training by up to 3.5× compared to state-of-the-art prefetching and caching systems. © 1968-2012 IEEE.

关键词： Cache memory

Distributed Image Retrieval Base on LSH Indexing on Spark 1st

学校读者我要写书评

暂无评论

Distributed Image Retrieval Base on LSH Indexing on Spark

1st International Conference on big data and security, ICBDS 2019

作者： Hou, Zelei Huang, Chao Wu, Jiagao Liu, Linfeng School of Computer Nanjing University of Posts and Telecommunications NanjingJiangsu210023 China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing NanjingJiangsu210023 China

ISBN: (纸本)9789811575297

With the advent of the era of big data, how to process massive image, video and other multimedia data timely and accurately has become a new challenge in related fields. Aiming at the computational bottleneck and inefficiency of traditional image content retrieval system, in this paper, a distributed image retrieval framework base on Location Sensitive Hash (LSH) indexing is proposed on Spark, which combines with the distributed storage and computing characteristics of Spark big data platform. Then, distributed K-means based Bag of Visual Word (BoVW) algorithm and LSH algorithm are proposed to build LSH index vectors on Spark in parallel. The experiment shows that the retrieval time of our framework can be reduced significantly, and both retrieval recall and precision are high compared with the traditional retrieval method. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Indexing (of information)

Traffic Engineering in Dynamic Hybrid Segment Routing Networks

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第7期68卷 655-670页

作者： Yingya Guo Kai Huang Cheng Hu Jiangyuan Yao Siyu Zhou College of Mathematics and Computer Science Fuzhou UniversityFuzhou350000China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou UniversityFuzhou350000China Key Laboratory of Spatial Data Mining&Information Sharing Ministry of EducationFuzhou350003China School of Information Science and Technology Guangdong University of Foreign StudiesGuangzhou510006China School of Computer Science and Cyberspace Security Hainan UniversityHaiKou570228China Tandon School of Engineering New York UniversityNew York10012USA Department of Computing Hong Kong Polytechnic UniversityHong Hom999077Hong Kong

The emergence of Segment Routing(SR)provides a novel routing paradigm that uses a routing technique called source packet *** SR architecture,the paths that the packets choose to route on are indicated at the ingress *** with shortest-path-based routing in traditional distributed routing protocols,SR can realize a flexible routing by implementing an arbitrary flow splitting at the ingress *** the advantages of SR,it may be difficult to update the existing IP network to a full SR deployed network,for economical and technical *** partial of the traditional IP network to the SR network,thus forming a hybrid SR network,is a preferable *** the traffic is dynamically changing in a daily time,in this paper,we propose a Weight Adjustment algorithm WASAR to optimize routing in a dynamic hybrid SR *** algorithm can be divided into three steps:firstly,representative Traffic Matrices(TMs)and the expected TM are obtained from the historical TMs through ultrascalable spectral clustering ***,given the network topology,the initial network weight setting and the expected TM,we can realize the link weight optimization and SR node deployment optimization through a Deep Reinforcement Learning(DRL)***,we optimize the flow splitting ratios of SR nodes in a centralized online manner under dynamic traffic demands,in order to improve the network *** the evaluation,we exploit historical TMs to test the performance of the obtained routing configuration in *** extensive experimental results validate that our proposed WASAR algorithm has superior performance in reducing Maximum Link Utilization(MLU)under the dynamic traffic.

关键词： Traffic engineering routing optimization segment routing deep reinforcement learning ultra-scalable spectral clustering

A Low-rank Matching Attention based Cross-modal Feature Fusion Method for Conversational Emotion Recognition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Shou, Yuntao Liu, Huan Cao, Xiangyong Meng, Deyu Dong, Bo School of Computer Science and Technology The Ministry of Education Key Laboratory for Intelligent Networks and Network Security The Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong Shaanxi Xi’an710049 China School of Computer Science and Technology Xi’an Jiaotong Shaanxi Xi’an710049 China The BigKE Joint Innovation Center SHMEEA Shanghai China School of Mathematics and Statistics Xi’an Jiaotong University Xi’an China

Conversational emotion recognition (CER) is an important research topic in human-computer interactions. Although recent advancements in transformer-based cross-modal fusion methods have shown promise in CER tasks, they tend to overlook the crucial intra-modal and inter-modal emotional interaction or suffer from high computational complexity. To address this, we introduce a novel and lightweight cross-modal feature fusion method called Low-Rank Matching Attention Method (LMAM). LMAM effectively captures contextual emotional semantic information in conversations while mitigating the quadratic complexity issue caused by the self-attention mechanism. Specifically, by setting a matching weight and calculating inter-modal features attention scores row by row, LMAM requires only one-third of the parameters of self-attention methods. We also employ the low-rank decomposition method on the weights to further reduce the number of parameters in LMAM. As a result, LMAM offers a lightweight model while avoiding overfitting problems caused by a large number of parameters. Moreover, LMAM is able to fully exploit the intra-modal emotional contextual information within each modality and integrates complementary emotional semantic information across modalities by computing and fusing similarities of intra-modal and inter-modal features simultaneously. Experimental results verify the superiority of LMAM compared with other popular cross-modal fusion methods on the premise of being more lightweight. Also, LMAM can be embedded into any existing state-of-the-art CER methods in a plug-and-play manner, and can be applied to other multi-modal recognition tasks, e.g., session recommendation and humour detection, demonstrating its remarkable generalization ability. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

Online Attentive Kernel-Based Temporal Difference Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Guang Chen, Xingguo Yang, Shangdong Wang, Huihui Dong, Shaokang Gao, Yang The the Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications National Engineering Laboratory for Agri-Product Quality Traceability Beijing Technology and Business University China The State Key Laboratory for Novel Software Technology Nanjing University China The PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China

With rising uncertainty in the real world, online Reinforcement Learning (RL) has been receiving increasing attention due to its fast learning capability and improving data efficiency. However, online RL often suffers from complex Value Function Approximation (VFA) and catastrophic interference, creating difficulty for the deep neural network to be applied to an online RL algorithm in a fully online setting. Therefore, a simpler and more adaptive approach is introduced to evaluate value function with the kernel-based model. Sparse representations are superior at handling interference, indicating that competitive sparse representations should be learnable, non-prior, non-truncated and explicit when compared with current sparse representation methods. Moreover, in learning sparse representations, attention mechanisms are utilized to represent the degree of sparsification, and a smooth attentive function is introduced into the kernel-based VFA. In this paper, we propose an Online Attentive Kernel-Based Temporal Difference (OAKTD) algorithm using two-timescale optimization and provide convergence analysis of our proposed algorithm. Experimental evaluations showed that OAKTD outperformed several Online Kernel-based Temporal Difference (OKTD) learning algorithms in addition to the Temporal Difference (TD) learning algorithm with Tile Coding on public Mountain Car, Acrobot, CartPole and Puddle World tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Learning algorithms

ReconBoost: boosting can achieve modality reconcilement 24

学校读者我要写书评

暂无评论

ReconBoost: boosting can achieve modality reconcilement

Proceedings of the 41st International Conference on Machine Learning

作者： Cong Hua Qianqian Xu Shilong Bao Zhiyong Yang Qingming Huang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China and School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China and School of Cyber Security University of Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China and Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China and Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost.

关键词：

Tile Classification Based Viewport Prediction with Multi-modal Fusion Transformer

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Zhihao Chen, Yiwei Zhang, Weizhan Yan, Caixia Zheng, Qinghua Wang, Qi Chen, Wangdu School of Computer Science and Technology Xi'an Jiaotong University Key Laboratory of Intelligent Networks and Network Security Ministry of Education Xi'an Jiaotong University Xi’an China School of Computer Science and Technology Xi'an Jiaotong University & National Engineering Lab for Big Data Analytics Xi'an Jiaotong University Xi’an China MIGU Video Shanghai China

Viewport prediction is a crucial aspect of tile-based 360◦ video streaming system. However, existing trajectory based methods lack of robustness, also oversimplify the process of information construction and fusion between different modality inputs, leading to the error accumulation problem. In this paper, we propose a tile classification based viewport prediction method with Multi-modal Fusion Transformer, namely MFTR. Specifically, MFTR utilizes transformer-based networks to extract the long-range dependencies within each modality, then mine intra- and inter-modality relations to capture the combined impact of user historical inputs and video contents on future viewport selection. In addition, MFTR categorizes future tiles into two categories: user interested or not, and selects future viewport as the region that contains most user interested tiles. Comparing with predicting head trajectories, choosing future viewport based on tile's binary classification results exhibits better robustness and interpretability. To evaluate our proposed MFTR, we conduct extensive experiments on two widely used PVS-HM and Xu-Gaze dataset. MFTR shows superior performance over state-of-the-art methods in terms of average prediction accuracy and overlap ratio, also presents competitive computation efficiency. © 2023, CC BY.

关键词： Forecasting

Vulnerability Detection With Graph Attention Network And Metric Learning

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2022年

作者： Zhang, Chunyong Liu, Bin Fan, Qi Xin, Yang Zhu, Hongliang School of Cyberspace Security Beijing University of Posts and Telecommunications Beijing100876 China College of Information and Network Engineering Anhui Science and Technology University Bengbu233030 China State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China

Static code vulnerability detection is a critical topic in software security. Existing software analysis methods have a high rate of false positives and false negatives. Researchers are interested in employing deep learning to discover vulnerabilities automatically, thanks to the recent success of deep learning algorithms in other application *** paper aims at the problem of insufficient and effective extraction of syntax and semantics, the issue of data imbalance, and the problem of overlapping feature distributions between vulnerable and non-vulnerable samples. We illustrate how to create models in a more principled way. We build GSM, a systematic vulnerability detection model based on Graph Attention Network, Sampling methods, and Metric Learning, one phase for one problem solution. When compared to the state-of-the-art approaches, our method achieves 11.5%, 12.3%, 12.57%, and 7.90% improvement in Precision, Recall, F1-Score, and AUC, respectively. Finally, based on the methods proposed in each stage of this paper, we put forward directions and suggestions for more efficient vulnerability detection tasks in the following research. © 2022, CC BY.

关键词： Learning algorithms