检索结果-内蒙古大学图书馆

Model-enhanced Vector Index

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Hailin Wang, Yujing Chen, Qi Chang, Ruiheng Zhang, Ting Miao, Ziming Hou, Yingyan Ding, Yang Miao, Xupeng Wang, Haonan Pang, Bochen Zhan, Yuefeng Sun, Hao Deng, Weiwei Zhang, Qi Yang, Fan Xie, Xing Yang, Mao Cui, Bin School of Computer Science Key Lab of High Confidence Software Technologies Peking University China Microsoft United States Aerospace Information Research Institute Key Laboratory of Target Cognition and Application Technology Chinese Academy of Sciences China Institute of Information Engineering Chinese Academy of Sciences China Carnegie Mellon University United States National University of Singapore Singapore National Engineering Laboratory for Big Data Analysis and Applications Peking University China

Embedding-based retrieval methods construct vector indices to search for document representations that are most similar to the query representations. They are widely used in document retrieval due to low latency and decent recall performance. Recent research indicates that deep retrieval solutions offer better model quality, but are hindered by unacceptable serving latency and the inability to support document updates. In this paper, we aim to enhance the vector index with endto- end deep generative models, leveraging the differentiable advantages of deep retrieval models while maintaining desirable serving efficiency. We propose Modelenhanced Vector Index (MEVI), a differentiable model-enhanced index empowered by a twin-tower representation model. MEVI leverages a Residual Quantization (RQ) codebook to bridge the sequence-to-sequence deep retrieval and embeddingbased models. To substantially reduce the inference time, instead of decoding the unique document ids in long sequential steps, we first generate some semantic virtual cluster ids of candidate documents in a small number of steps, and then leverage the well-adapted embedding vectors to further perform a fine-grained search for the relevant documents in the candidate virtual clusters. We empirically show that our model achieves better performance on the commonly used academic benchmarks MSMARCO Passage and Natural Questions, with comparable serving latency to dense retrieval solutions. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

Internal drivers of the global pandemic of the Omicron variants of SARS-CoV-2

学校读者我要写书评

暂无评论

Medicine Advances

Medicine Advances 2024年第3期2卷 262-273页

作者： Yilin Niu Wuxiu Quan Yunyi Li Ziying Chen Yunfei Gao School of Public Health Southern Medical University Guangzhou Guangdong China Medical Big Data Center Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences) Southern Medical University Guangzhou Guangdong China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou Guangdong China School of Software Engineering South China University of Technology Guangzhou Guangdong China

Background The high transmissibility of the Omicron variants of severe acute respiratory syndrome coronavirus 2 continues to impose a significant burden on public health systems worldwide. Continuous mutations in the virus challenge the efficacy of vaccines and prior immunity from other variants, posing a severe threat to human health. Therefore, there is an urgent need to predict mutations of the Omicron variants and identify key factors influencing their spread. This study investigated critical amino acid mutations of the Omicron variants using epidemiological data and the mechanisms underlying their transmission. The aim was to understand the key factors driving the spread of the Omicron variants and provide insights for effective control and prevention strategies. Methods A total of 488,646 Omicron cases recorded between December 2021 and February 2023 were analyzed using a sliding time window and the Epi Score model, which has high accuracy for the identification of mutation sites. MutPred2, PolyPhen2 and VarSite tools were used to predict future mutations and identify factors driving the prevalence of the Omicron variants. Results Epi Scores showed fluctuating patterns at mutation sites, highlighting N969K, Y505H, N764K, T478K, and S371F mutations on the spike protein as significant for future prevention efforts. The spread of the Omicron variants was linked to changes in the viral entry pathway and improved angiotensin-converting enzyme 2 (ACE2) binding and immune evasion tactics. Conclusions The findings of this study reveal trends in the evolution of the Omicron variants, including altered cell entry, increased affinity for ACE2, and evasion of the immune system. These factors are critical for understanding the global spread of the Omicron variants and developing effective control strategies.

关键词： amino acids coronavirus immune evasion mutation public health SARS-CoV-2 spike glycoprotein

Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Tianfu Shen, Li Fan, Qilin Xu, Tong Liu, Tongliang Xiong, Hui Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science University of Science and Technology of China Hefei230027 China The School of Big Data and Software Engineering Chongqing University ChinaScience Chongqing401331 China JD Explore Academy The UBTECH Sydney Artificial Intelligence Centre The School of Information Technologies Faculty of Engineering and Information Technologies The University of Sydney DarlingtonNSW2008 Australia Thrust of Artificial Intelligence Nansha Guangdong Guangzhou511400 China The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong

As an essential resource management problem in network virtualization, virtual network embedding (VNE) aims to allocate the finite resources of physical network to sequentially arriving virtual network requests (VNRs) with different resource demands. Since this is an NP-hard combinatorial optimization problem, many efforts have been made to provide viable solutions. However, most existing approaches have either ignored the admission control of VNRs, which has a potential impact on long-term performances, or not fully exploited the temporal and topological features of the physical network and VNRs. In this paper, we propose a deep Hierarchical Reinforcement Learning approach to learn a joint Admission Control and Resource Allocation policy for VNE, named HRL-ACRA. Specifically, the whole VNE process is decomposed into an upper-level policy for deciding whether to admit the arriving VNR or not and a lower-level policy for allocating resources of the physical network to meet the requirement of VNR through the HRL approach. Considering the proximal policy optimization as the basic training algorithm, we also adopt the average reward method to address the infinite horizon problem of the upper-level agent and design a customized multi-objective intrinsic reward to alleviate the sparse reward issue of the lower-level agent. Moreover, we develop a deep feature-aware graph neural network to capture the features of VNR and physical network and exploit a sequence-to-sequence model to generate embedding actions iteratively. Finally, extensive experiments are conducted in various settings, and show that HRL-ACRA outperforms state-of-the-art baselines in terms of both the acceptance ratio and long-term average revenue. Our code is available at https://***/GeminiLight/hrl-acra. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

Region-level Contrastive and Consistency Learning for Semi-Supervised Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Jianrong Wu, Tianyi Ding, Chuanghao Zhao, Hongwei Guo, Guodong College of Computer Science and Technology Jilin University Changchun China Institute of Deep Learning Baidu Research Beijing China National Engineering Laboratory for Deep Learning Technology and Application Beijing China College of Software Jilin University Changchun China The Institute of Deep Learning Baidu Research China

Current semi-supervised semantic segmentation methods mainly focus on designing pixel-level consistency and contrastive regularization. However, pixel-level regularization is sensitive to noise from pixels with incorrect predictions, and pixel-level contrastive regularization has memory and computational cost with O(pixel num2). To address the issues, we propose a novel region-level contrastive and consistency learning framework (RC2L) for semi-supervised semantic segmentation. Specifically, we first propose a Region Mask Contrastive (RMC) loss and a Region Feature Contrastive (RFC) loss to accomplish region-level contrastive property. Furthermore, Region Class Consistency (RCC) loss and Semantic Mask Consistency (SMC) loss are proposed for achieving region-level consistency. Based on the proposed region-level contrastive and consistency regularization, we develop a region-level contrastive and consistency learning framework (RC2L) for semi-supervised semantic segmentation, and evaluate our RC2L on two challenging benchmarks (PASCAL VOC 2012 and Cityscapes), outperforming the state-of-the-art. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantic Segmentation

A cross Transformer for image denoising

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Tian, Chunwei Zheng, Menghua Zuo, Wangmeng Zhang, Shichao Zhang, Yanning Lin, Chia-Wen School of Software Northwestern Polytechnical University Shaanxi Xi’an710129 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Xi’an710129 China School of Computer Science and Technology Harbin Institute of Technology Heilongjiang Harbin150001 China Peng Cheng Laboratory Shenzhen518055 China School of Computer Science and Engineering Central South University Hunan Changsha410083 China School of Computer Science Northwestern Polytechnical University Shaanxi Xi’an710129 China Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Hsinchu30013 Taiwan

Deep convolutional neural networks (CNNs) depend on feedforward and feedback ways to obtain good performance in image denoising. However, how to obtain effective structural information via CNNs to efficiently represent given noisy images is key for complex scenes. In this paper, we propose a cross Transformer denoising CNN (CTNet) with a serial block (SB), a parallel block (PB), and a residual block (RB) to obtain clean images for complex scenes. A SB uses an enhanced residual architecture to deeply search structural information for image denoising. To avoid loss of key information, PB uses three heterogeneous networks to implement multiple interactions of multi-level features to broadly search for extra information for improving the adaptability of an obtained denoiser for complex scenes. Also, to improve denoising performance, Transformer mechanisms are embedded into the SB and PB to extract complementary salient features for effectively removing noise in terms of pixel relations. Finally, a RB is applied to acquire clean images. Experiments illustrate that our CTNet is superior to some popular denoising methods in terms of real and synthetic image denoising. It is suitable to mobile digital devices, i.e., phones. Codes can be obtained at https://***/hellloxiaotian/CTNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Image denoising

Pyscribe - Learning to Describe Python Code

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Guo, Juncai Liu, Jin Wan, Yao Zhao, Yanjie Li, Li Liu, Kui Klein, Jacques Bissyandé, Tegawendé F. School of Computer Science Wuhan University Wuhan China Key Laboratory of Network Assessment Technology Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Faculty of Information Technology Monash University VIC Australia Huawei Software Engineering Application Technology Lab Hangzhou China SnT Centre University of Luxembourg 1855 Luxembourg

Code comment generation, which aims to describe the functionality of source code in natural language, plays an important role in automatic software development. Currently, several structural neural networks have been exploited to preserve the syntax structure of source code based on Abstract Syntax Trees (ASTs). However, they can not well capture both the long-distance and local relations between nodes while retaining the overall structural information of AST. To mitigate this problem, we present to the community a prototype tool called PYSCRIBE, which expands the Transformer model to a new encoder-decoder architecture to incorporate triplet positions into the node-level and edge-level features of AST towards automatically generating comments for Python code. To the best of our knowledge, this paper makes the first attempt to consider the edges of AST as an explicit component for better code representation, as to generate higher qualified comments. By specifying triplet positions for each node and edge, the overall structural information can be well preserved in the learning process. In the decoder, we perform a two-stage decoding process over the extracted node and edge features to generate comments. To evaluate the effectiveness of PYSCRIBE, we resort to a large dataset of code-comment pairs by mining Jupyter notebooks from GitHub, for which we have made it publicly available to support further studies. The evaluation results show that PYSCRIBE is indeed effective, outperforming the state-of-the-art by achieving an average BLEU score (i.e., av-BLEU) of ≈0.28. © 2022, The Authors. All rights reserved.

关键词： Large dataset

Fer-Chc: Facial Expression Recognition with Cross-Hierarchy Contrast

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Wu, Xuemei He, Jie Huang, Changqin Huang, Qionghao Zhu, Jia Huang, Xiaodi Fujita, Hamido Key Laboratory of Intelligent Education Technology and Application of Zhejiang Province Zhejiang Normal University Jinhua321004 China School of Computing Mathematics and Engineering Charles Sturt University NSW Australia Software and Information Science Iwate Prefectural University Takizawa020-0693 Japan

Remarkable progress has been made in facial expression recognition (FER) tasks with convolutional neural networks (CNNs). However, these CNN-based approaches do not well capture the detailed and crucial features that can distinguish different facial expressions from a global perspective among multiple facial expressions. The performance of existing CNN-based models for FER is still much room for improvement. As such, we propose a novel cross-hierarchy contrast (CHC) framework named FER-CHC for facial expression recognition tasks. The basic idea of FER-CHC is to employ a CHC to regularize the feature learning of the backbone network and enhance global representations of facial expressions. Specifically, the CHC captures common and differential features from different facial expressions with a cross-hierarchy contrast mechanism. The fusion network globally integrates the features learned from a backbone network and CHC to learn a more robust feature representation. Comprehensive experiments were conducted on six popular datasets: CK+, FER2013, FER+, RAF-DB, AffectNet, and JAFFE. The results show that our proposed FER-CHC achieves state-of-the-art performances on these datasets. In addition, the ablation study also demonstrates the effectiveness of the proposed components in FER-CHC. © 2022, The Authors. All rights reserved.

关键词： Convolutional neural networks

Adaptive Convolutional Neural Network for Image Super-resolution

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tian, Chunwei Zhang, Xuanyu Wang, Tao Zhang, Yongjun Zhu, Qi Lin, Chia-Wen The School of Software Northwestern Polytechnical University Xi’an710129 China The National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an710129 China The Yangtze River Delta Research Institute Northwestern Polytechnical University Taicang215400 China The School of Computer Science Northwestern Polytechnical University Xi’an710129 China The College of Computer Science and Technology Guizhou University Guiyang550025 China The School of Artificial Intelligence Nanjing University of Aeronautics and Astronautics Nanjing210016 China The Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Taiwan

Convolutional neural networks can automatically learn features via deep network architectures and given input samples. However, the robustness of obtained models may face challenges in varying scenes. Bigger differences in network architecture are beneficial to extract more diversified structural information to strengthen the robustness of an obtained superresolution model. In this paper, we proposed a adaptive convolutional neural network for image super-resolution (ADSRNet). To capture more information, ADSRNet is implemented by a heterogeneous parallel network. The upper network can enhance relation of context information, salient information relation of a kernel mapping and relations of shallow and deep layers to improve performance of image super-resolution. That can strengthen adaptability of an obtained super-resolution model for different scenes. The lower network utilizes a symmetric architecture to enhance relations of different layers to mine more structural information, which is complementary with a upper network for image super-resolution. The relevant experimental results show that the proposed ADSRNet is effective to deal with image resolving. Codes are obtained at https://***/hellloxiaotian/ADSRNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

Secure and Reliable Parking Protocol Based on Blockchain for VANETs

学校读者我要写书评

暂无评论

Secure and Reliable Parking Protocol Based on Blockchain for...

IEEE Conference on Wireless Communications and Networking

作者： Yan Zhang Lei Zhang Burong Kang Yue Ma Tong Chen Engineering Research Center of Software/Hardware Co-design Technology and Application Ministry of Education East China Normal University Shanghai China Shanghai Key Laboratory of Trustworthy Computing School of Software Engineering East China Normal University Shanghai China

ISBN: (纸本)9781728195056;9781728195063

With the development of vehicular ad hoc network (VANET) technology, more and more smart parking systems in VANETs are presented. However, existing solutions suffer from the challenges of dishonest parking lots that may claim there are more empty spots than they actually have, malicious occupation of parking spots and multi-reservation attack, etc. To address these challenges, we propose a secure and reliable smart parking protocol based on blockchain and linkable group signatures. For the security of our scheme, it not only realizes traditional authentication, privacy preservation and message confidentiality requirements but also prevents multi-reservation attack and the dishonest parking lots that claim more empty spots than they actually have.

关键词： Privacy Protocols Conferences Vehicular ad hoc networks Authentication Blockchain Reliability