检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wang, Yu Wang, Ke Nanjing University China Visa Research United States State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Jiangsu Nanjing210023 China Security Cryptography Visa Research Palo AltoCA United States

Study patterns that models have learned has long been a focus of pattern recognition research. Explaining what patterns are discovered from training data, and how patterns are generalized to unseen data are instrumental to understanding and advancing the pattern recognition methods. Unfortunately, the vast majority of the application domains deal with continuous data (i.e. statistical in nature) out of which extracted patterns can not be formally defined. For example, in image classification, there does not exist a principle definition for a label of cat or dog. Even in natural language, the meaning of a word can vary with the context it is surrounded by. Unlike the aforementioned data format, programs are a unique data structure with a well-defined syntax and semantics, which creates a golden opportunity to formalize what models have learned from source code. This paper presents the first formal definition of patterns discovered by code summarization models (i.e. models that predict the name of a method given its body), and gives a sound algorithm to infer a context-free grammar (CFG) that formally describes the learned patterns. We realize our approach in PATIC which produces CFGs for summarizing the patterns discovered by code summarization models. In particular, we pick two prominent instances, code2vec and code2seq, to evaluate PATIC. PATIC shows that the patterns extracted by each model are heavily restricted to local, and syntactic code structures with little to none semantic implication. Based on these findings, we present two example uses of the formal definition of patterns: a new method for evaluating the robustness and a new technique for improving the accuracy of code summarization models. Our work opens up this exciting, new direction of studying what models have learned from source code. © 2023, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Learning Self-Target Knowledge for Few-Shot Segmentation

SSRN

引用

SSRN 2023年

作者： Chen, Yadang Chen, Sihan Yang, Zhi-Xin Wu, Enhua Engineering Research Center of Digital Forensics Ministry of Education Nanjing University of Information Science and Technology Nanjing210044 China School of Computer Science Nanjing University of Information Science and Technology Nanjing210044 China State Key Laboratory of Internet of Things for Smart City Department of Electromechanical Engineering University of Macau 999078 China State Key Laboratory of Computer Science Institute of Software University of Chinese Academy of Sciences Beijing100190 China

Few-shot semantic segmentation uses a few annotated data of a specific class in the support set to segment the target of the same class in the query set. Most existing approaches fail to perform well when there are significant intra-class variances. This paper alleviates the problem by concentrating on mining the query image and using the support set as supplementary information. First, it proposes a Query Prototype Generation Module to generate a query foreground prototype from the query features. Specifically, we use both prototype-level and pixel-level similarity matching to generate two complementary initial prototypes, which we then integrate to create a discriminative query foreground prototype. Second, we propose a Support Auxiliary Refinement Module to further guide the final precise prediction of the query image by leveraging the target category information of the support set through step-by-step mining. Specifically, we generate a query-support mixture prototype based on the support prototype representation obtained using the attention mechanism. Then we generate a support supplement prototype to complement the missing information by encoding over the foreground regions that the query-support mixture prototype fails to segment out. Extensive experiments on PASCAL-5i and COCO-20i demonstrate that our model outperforms the prior works of few-shot segmentation. © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

ESM All-Atom: Multi-scale Protein Language Model for Unified Molecular Modeling

arXiv

引用

arXiv 2024年

作者： Zheng, Kangjie Long, Siyu Lu, Tianyu Yang, Junwei Dai, Xinyu Zhang, Ming Nie, Zaiqing Ma, Wei-Ying Zhou, Hao School of Computer Science National Key Laboratory for Multimedia Information Processing Peking University Anker Embodied AI Lab Peking University Beijing100871 China School of Artificial Intelligence National Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science Tsinghua University China Tsinghua University China PharMolix Inc

Protein language models have demonstrated significant potential in the field of protein engineering. However, current protein language models primarily operate at the residue scale, which limits their ability to provide information at the atom level. This limitation prevents us from fully exploiting the capabilities of protein language models for applications involving both proteins and small molecules. In this paper, we propose ESM-AA (ESM All-Atom), a novel approach that enables atom-scale and residue-scale unified molecular modeling. ESM-AA achieves this by pretraining on multi-scale code-switch protein sequences and utilizing a multi-scale position encoding to capture relationships among residues and atoms. Experimental results indicate that ESM-AA surpasses previous methods in protein-molecule tasks, demonstrating the full utilization of protein language models. Further investigations reveal that through unified molecular modeling, ESM-AA not only gains molecular knowledge but also retains its understanding of proteins. © 2024, CC BY-NC-ND.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Spatial-information Guided Adaptive Context-aware Network for Efficient RGB-D Semantic Segmentation

arXiv

引用

arXiv 2023年

作者： Zhang, Yang Xiong, Chenyun Liu, Junjie Ye, Xuhui Sun, Guodong The School of Mechanical Engineering Hubei University of Technology Wuhan430068 China The Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong The National Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing210023 China

Efficient RGB-D semantic segmentation has received considerable attention in mobile robots, which plays a vital role in analyzing and recognizing environmental information. According to previous studies, depth information can provide corresponding geometric relationships for objects and scenes, but actual depth data usually exist as noise. To avoid unfavorable effects on segmentation accuracy and computation, it is necessary to design an efficient framework to leverage cross-modal correlations and complementary cues. In this paper, we propose an efficient lightweight encoder-decoder network that reduces the computational parameters and guarantees the robustness of the algorithm. Working with channel and spatial fusion attention modules, our network effectively captures multi-level RGB-D features. A globally guided local affinity context module is proposed to obtain sufficient high-level context information. The decoder utilizes a lightweight residual unit that combines short- and long-distance information with a few redundant computations. Experimental results on NYUv2, SUN RGB-D, and Cityscapes datasets show that our method achieves a better trade-off among segmentation accuracy, inference time, and parameters than the state-of-the-art methods. © 2023, CC BY-NC-ND.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Temporal Feature Matters: A Framework for Diffusion Model Quantization

arXiv

引用

arXiv 2024年

作者： Huang, Yushi Gong, Ruihao Liu, Xianglong Liu, Jing Li, Yuhang Lu, Jiwen Tao, Dacheng Electrical and Computer Engineering Department Hong Kong University of Science and Technology Hong Kong State Key Laboratory of Software Development Environment Beihang University China Department of Data Science and AI Faculty of IT Monash University Australia Electrical Engineering Department Yale University United States Department of Automation Tsinghua University China School of Computer Science and Engineering Nanyang Technological University Singapore

The Diffusion models, widely used for image generation, face significant challenges related to their broad applicability due to prolonged inference times and high memory demands. Efficient Post-Training Quantization (PTQ) is crucial to address these issues. However, unlike traditional models, diffusion models critically rely on the time-step for the multi-round denoising. Typically, each time-step is encoded into a hypersensitive temporal feature by several modules. Despite this, existing PTQ methods do not optimize these modules individually. Instead, they employ unsuitable reconstruction objectives and complex calibration methods, leading to significant disturbances in the temporal feature and denoising trajectory, as well as reduced compression efficiency. To address these challenges, we introduce a novel quantization framework that includes three strategies: 1) TIB-based Maintenance: Based on our innovative Temporal Information Block (TIB) definition, Temporal Information-aware Reconstruction (TIAR) and Finite Set Calibration (FSC) are developed to efficiently align original temporal features. 2) Cache-based Maintenance: Instead of indirect and complex optimization for the related modules, pre-computing and caching quantized counterparts of temporal features are developed to minimize errors. 3) Disturbance-aware Selection: Employ temporal feature errors to guide a fine-grained selection between the two maintenance strategies for further disturbance reduction. This framework preserves most of the temporal information and ensures high-quality end-to-end generation. Extensive testing on various datasets, diffusion models and hardware confirms our superior performance and acceleration. © 2024, CC BY.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Realizing Emotional Interactions to Learn User Experience and Guide Energy Optimization for Mobile Architectures 22

Realizing Emotional Interactions to Learn User Experience an...

引用

Proceedings of the 55th Annual IEEE/ACM International Symposium on Microarchitecture

作者： Xueliang Li Zhuobin Shi Junyang Chen Yepang Liu National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China Research Institute of Trustworthy Autonomous Systems Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation and Department of Computer Science and Engineering Southern University of Science and Technology China

ISBN: (纸本)9781665462723

In the age of AI, mobile architectures such as smartphones are still "cold machines"; machines do not feel. If the architecture is able to feel users' feelings and runtime user experience (UX), it will accordingly adapt performance/energy to find the optimal system-operating state that consumes the least energy to satisfy users. In this paper, we will utilize users' facial expressions (FEs) to learn their runtime UX. We know that FEs are the natural and direct way for humans to convey their emotions and feelings. Our study reveals that FEs also reflect UX. Our research for the first time quantifies the link between FEs and UX. Leveraging this link, the architecture will be able to use the front camera to see FEs and feel users' UX. Based on UX, the architecture can appropriately provision computing resources. We propose Vi-energy system to realize the above idea. Our evaluation shows that Vi-energy reduces energy consumption by 52.9% at maximum and secures UX.

关键词：

来源：评论

学校读者我要写书评

暂无评论

pFedLVM: A Large Vision Model (LVM)-Driven and Latent Feature-Based Personalized Federated Learning Framework in Autonomous Driving

arXiv

引用

arXiv 2024年

作者： Kou, Wei-Bin Lin, Qingfeng Tang, Ming Xu, Sheng Ye, Rongguang Leng, Yang Wang, Shuai Li, Guofa Chen, Zhenyu Zhu, Guangxu Wu, Yik-Chung Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Shenzhen Research Institute of Big Data Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Research Institute of Electronic Science and Technology University of Electronic Science and technology Chengdu China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China College of Mechanical and Vehicle Engineering Chongqing University Chongqing China

Deep learning-based Autonomous Driving (AD) semantic segmentation (SSeg) models often exhibit poor generalization due to data heterogeneity in an ever domain-shifting environment. While Federated Learning (FL) could improve the generalization of an AD SSeg model (known as FedAD system), conventional models often struggle with under-fitting as the amount of accumulated training data progressively increases. To address this issue, instead of conventional small models, employing Large Vision Models (LVMs) in FedAD is a viable option for better learning of representations from a vast volume of data. However, implementing LVMs in FedAD introduces three challenges: (I) the extremely high communication overheads associated with transmitting LVMs between participating vehicles and a central server;(II) lack of computing resource to deploy LVMs on each vehicle;(III) the performance drop due to LVM focusing on shared features but overlooking local vehicle characteristics. To overcome these challenges, we propose pFedLVM, a LVM-Driven, Latent Feature-Based Personalized Federated Learning framework. In this approach, the LVM is deployed only on central server, which effectively alleviates the computational burden on individual vehicles. Furthermore, the exchange between central server and vehicles are the learned features rather than the LVM parameters, which significantly reduces communication overhead. In addition, we utilize both shared features from all participating vehicles and individual characteristics from each vehicle to establish a personalized learning mechanism. This enables each vehicle’s model to learn features from others while preserving its personalized characteristics, thereby outperforming globally shared models trained in general FL. Extensive experiments demonstrate that pFedLVM outperforms the existing state-of-the-art approach by 18.47%, 25.60%, 51.03% and 14.19% in terms of mIoU, mF1, mPrecision and mRecall, respectively. © 2024, CC BY-NC-ND.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Blockwise Stochastic Variance-Reduced Methods with Parallel Speedup for Multi-Block Bilevel Optimization

arXiv

引用

arXiv 2023年

作者： Hu, Quanqi Qiu, Zi-Hao Guo, Zhishuai Zhang, Lijun Yang, Tianbao Department of Computer Science and Engineering Texas A&M University College StationTX United States National Key Laboratory for Novel Software Technology Nanjing University Nanjing China

In this paper, we consider non-convex multi-block bilevel optimization (MBBO) problems, which involve m 1 lower level problems and have important applications in machine learning. Designing a stochastic gradient and controlling its variance is more intricate due to the hierarchical sampling of blocks and data and the unique challenge of estimating hyper-gradient. We aim to achieve three nice properties for our algorithm: (a) matching the state-of-the-art complexity of standard BO problems with a single block;(b) achieving parallel speedup by sampling I blocks and sampling B samples for each sampled block per-iteration;(c) avoiding the computation of the inverse of a high-dimensional Hessian matrix estimator. However, it is non-trivial to achieve all of these by observing that existing works only achieve one or two of these properties. To address the involved challenges for achieving (a, b, c), we propose two stochastic algorithms by using advanced blockwise variance-reduction techniques for tracking the Hessian matrices (for low-dimensional problems) or the Hessian-vector products (for high-dimensional problems), and prove an iteration −3 complexity of (formula presented) for finding an ϵ-stationary point under appropriate conditions. We also conduct experiments to verify the effectiveness of the proposed algorithms comparing with existing MBBO algorithms. © 2023, CC BY.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Migrant Resettlement by Evolutionary Multi-objective Optimization

arXiv

引用

arXiv 2023年

作者： Liu, Dan-Xuan Gu, Yu-Ran Qian, Chao Mu, Xin Tang, Ke National Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China School of Artificial Intelligence Nanjing University Nanjing210023 China Peng Cheng Laboratory Shenzhen518000 China Shenzhen Key Laboratory of Computational Intelligence Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

Migration has been a universal phenomenon, which brings opportunities as well as challenges for global development. As the number of migrants (e.g., refugees) increases rapidly in recent years, a key challenge faced by each country is the problem of migrant resettlement. This problem has attracted scientific research attention, from the perspective of maximizing the employment rate. Previous works mainly formulated migrant resettlement as an approximately submodular optimization problem subject to multiple matroid constraints and employed the greedy algorithm, whose performance, however, may be limited due to its greedy nature. In this paper, we propose a new framework MR-EMO based on Evolutionary Multi-objective Optimization, which reformulates Migrant Resettlement as a bi-objective optimization problem that maximizes the expected number of employed migrants and minimizes the number of dispatched migrants simultaneously, and employs a Multi-Objective Evolutionary Algorithm (MOEA) to solve the bi-objective problem. We implement MR-EMO using three MOEAs, the popular NSGA-II, MOEA/D as well as the theoretically grounded GSEMO. To further improve the performance of MR-EMO, we propose a specific MOEA, called GSEMO-SR, using matrix-swap mutation and repair mechanism, which has a better ability to search for feasible solutions. We prove that MR-EMO using either GSEMO or GSEMO-SR can achieve better theoretical guarantees than the previous greedy algorithm. Experimental results under the interview and coordination migration models clearly show the superiority of MR-EMO (with either NSGA-II, MOEA/D, GSEMO or GSEMO-SR) over previous algorithms, and that using GSEMO-SR leads to the best performance of MR-EMO. Copyright © 2023, The Authors. All rights reserved.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Knowledge-aware Multi-view Cross Learning for Edge-based Collaborative Recommendation

Knowledge-aware Multi-view Cross Learning for Edge-based Col...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Yang Dai Shunmei Meng Huanhuan Gu Nan Liu Longchuan Tu School of Cyberspace Security NanJing University of Science and Technology Nanjing China State Key Lab. for Novel Software Technology NanJing University Nanjing China Department of Computer Science and Engineering NanJing University of Science and Technology Nanjing China Nanjing Sinovatio Technology Co. Ltd. Nanjing China

In order to effectively overcome the sparsity and cold start challenges of collaborative filtering in actual scenarios, and provide more accurate suggestions, knowledge graphs are commonly utilized in recommender systems. Graph neural networks are increasingly used in knowledge graph-based recommender systems. Nevertheless, conventional recommender systems overlook the relationship information between items and entities as well as the sparse supervision signal, potentially leading to a decline in the actual recommendation performance. In this investigation, we propose KMCL, a Knowledge-aware Multi-view Cross-learning framework for edge-based collaborative recommendation. In contrast to the typical manner of dealing with knowledge graphs, our approach investigates three different graph views to improve users’ and items’ embedding representations, respectively. Firstly, the merged user-item KG graph is utilized to integrate the multi-hop neighbor information of each user, with the Graph Attention Network assigning various weights to different neighbors. Secondly, Graph Neural Network collects the top-x neighbor nodes for learning in the collaborative view of user-item graph and item-entity graph. Finally, a cross module is developed to share high-level information between embeddings with the same features. In addition, we also introduce the idea of edge computing, which preprocesses and calculates the locally obtained user preferences first, and then inputs them into different views to improve the recommendation efficiency. Experimental results demonstrate that KMCL delivers better suggestions than state-of-the-art baseline models in delivering superior recommendations. Furthermore, our approach maintains higher accuracy in predicting outcomes in less familiar interaction scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：