检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Heping Liu Songbai Liu Junkai Ji Qiuzhen Lin Jianyong Chen Kay Chen Tan College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computing The Hong Kong Polytechnic University

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Integrating personalization into federated learning is crucial for addressing data heterogeneity and surpassing the limitations of a single aggregated model. Personalized federated learning excels at capturing inter-client similarities and meeting diverse client needs through custom-made models. However, even with personalized approaches, it’s essential to aggregate knowledge among clients to ensure universal benefits. This paper proposes Federated Dual Objectives and Dual Models (FedDodm), a novel approach that employs two independent models to separately address explicit personalization and implicit generalization objectives in personalized federated learning. By treating these objectives as distinct loss functions and training models accordingly, we achieve a balance between the two through a fusion method. Extensive experiments across various models and learning tasks demonstrate that FedDodm outperforms state-of-the-art federated learning approaches, marking a significant advancement in effectively integrating personalized and generalized knowledge.

关键词： Training Federated learning Aggregates Neural networks data models

来源：评论

学校读者我要写书评

暂无评论

An Entropy Based Unsupervised Visual Vocabulary Optimization for Visual Loop Closure Detection

An Entropy Based Unsupervised Visual Vocabulary Optimization...

引用

2023 International Conference on Computer, Artificial Intelligence, and Control engineering, CAICE 2023

作者： Li, Bo Yu, Xiangdong Feng, Xin He, Ying Zhu, Zhaohan Ge, Yongxin Geng, Li Department of Criminal Science Technology Chongqing Police College Chongqing China College of Computer Science and Engineering Chongqing University of Technology Chongqing China School of Electrical Engineering Southwest Jiaotong University Sichuan China School of Big Data & Software Engineering Chongqing University Chongqing China New York City College of Technology City University of New York New York United States

ISBN: (纸本)9781510665040

In the task of simultaneous localization and mapping (SLAM), a mobile robot should be able to recognize the location that it has previously visited. This is termed as the loop closure detection. Current loop closure detection is implemented by matching of image features extracted from present image and previous images, where good feature representation is highly required. Bag-of-visual words (BoW) is known to be an effect feature representation for image and video matching task. However, to build the visual feature vocabulary in the unsupervised manner is still challenging. In this paper, we are aiming at evaluating the representability of the visual words and generating the discriminative vocabulary representation. We first present an entropy ranking based scheme to improve the spectral clustering algorithm by leveraging eigenvector selection and feature embedding simultaneously. We then propose to evaluate the representative ability of the visual vocabulary quantitatively based on the complexity of the decomposition of similarity matrix in the unsupervised manner. We perform experiments on the loop closure detection datasets. which contains strong perceptual aliasing in both indoor and outdoor scenarios. Results demonstrate that the proposed BoW based feature representation has strong representation ability in measuring the similarity of loop closure events and differentiating new visited places. © 2023 SPIE.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

An Encoder-Decoder Model Based On Spiking Neural Networks For Address Event Representation Object Recognition

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Du, Sichun Zhu, Haodi Zhang, Yang Hong, Qinghui Hunan University College of Computer Science and Electronic Engineering Changsha418002 China Shenzhen University Computer Vision Institute School of Computer Science and Software Engineering National Engineering Laboratory for Big Data System Computing Technology Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

Address event representation (AER) object recognition task has attracted extensive attention in neuromorphic vision processing. The spike-based and event-driven computation inherent in the spiking neural network (SNN) provides an energy-saving solution for AER object recognition. However, SNN with spike timing dependent plasticity (STDP) learning rule has not achieved satisfying AER object recognition performance. This work proposes an SNN-based encoder-decoder model to improve the recognition performance of AER objects. An STDP-based locally connected spiking neural network (LC-SNN) is proposed as an encoder to extract rich spatiotemporal features from AER event flows more flexibly. After the encoder extracts and learns primary features, we propose a fully connected spiking neural network (FC-SNN) based on the reward-modulated spike-timing-dependent plasticity (R-STDP) learning rule as a decoder to learn higher-level features for classification. In addition, we improved the winner-take-all (WTA) mechanisms and R-STDP learning rule in the decoder based on the reward and punish decision, enabling the network to perform better. The experiments are performed on the N-MNIST, MNIST-DVS, and the DVS Gesture datasets, improving the accuracy of the best existing plasticity-based SNN by 0.19%, 0.27% and 1.35%, respectively. © 2016 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

How to Select Pre-Trained Code Models for Reuse? A Learning Perspective

How to Select Pre-Trained Code Models for Reuse? A Learning ...

引用

IEEE International Conference on software Analysis, Evolution and Reengineering (SANER)

作者： Zhangqian Bi Yao Wan Zhaoyang Chu Yufei Hu Junyi Zhang Hongyu Zhang Guandong Xu Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Big Data and Software Engineering Chongqing University Chongqing China School of Computer Science University of Technology Sydney Sydney Australia

ISBN: (数字)9798331535100

ISBN: (纸本)9798331535117

Pre-training a language model and then fine-tuning it has shown to be an efficient and effective technique for a wide range of code intelligence tasks, such as code generation, code summarization, and vulnerability detection. However, pre-training language models on a large-scale code corpus is compu-tationally expensive. Fortunately, many off-the-shelf Pre-trained Code Models (PCMs), such as CodeBERT, CodeT5, CodeGen, and Code Llama, have been released publicly. These models acquire general code understanding and generation capability during pre-training, which enhances their performance on downstream code intelligence tasks. With an increasing number of these public pre-trained models, selecting the most suitable one to reuse for a specific task is essential. In this paper, we systematically investigate the reusability of PCMs. We first explore three intuitive model selection methods that select by size, training data, or brute-force fine-tuning. Experimental results show that these straightforward techniques either perform poorly or suffer high costs. Motivated by these findings, we explore learning-based model selection strategies that utilize pre-trained models without altering their parameters. Specifically, we train proxy models to gauge the performance of pre-trained models, and measure the distribution deviation between a model's latent features and the task's labels, using their closeness as an indicator of model transferability. We conduct experiments on 100 widely-used open-source PCMs for code intelligence tasks, with sizes ranging from 42.5 million to 3 billion parameters. The results demonstrate that learning-based selection methods reduce selection time to 100 seconds, compared to 2,700 hours with brute-force fine-tuning, with less than 6% performance degradation across related tasks.

关键词： Phase change materials Analytical models Adaptation models Codes Costs Computational modeling Training data Machine learning software software development management

来源：评论

学校读者我要写书评

暂无评论

Improving Cancer Gene Identification by Enhancing Common Information Between the PPI Network and Gene Functional Association 39

Improving Cancer Gene Identification by Enhancing Common Inf...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Deng, Chao Li, Hongdong Wang, Jianxin School of Computer Science and Engineering Central South University Changsha410083 China Hunan Provincial Key Lab on Bioinformatics Central South University Changsha410083 China Xinjiang Engineering Research Center of Big Data and Intelligent Software School of Software Xinjiang University Urumqi830091 China

ISBN: (纸本)157735897X

Identifying cancer genes is crucial for treatment and understanding pathogenesis. Recent methods typically leverage protein-protein interaction (PPI) networks or gene functional association data from annotated gene sets. There may be some shared neighborhood structure information between these two types of gene association data. While this common information may contain more accurate gene association information, existing methods often overlook this potential. To address this gap, we introduce DISFusion, which integrates multi-omics cancer data, PPI networks, and gene functional associations to identify cancer genes. A key innovation of DISFusion is the cross-view decorrelation loss, which enhances the common information between PPI networks and gene functional associations, thereby improving prediction accuracy. Extensive experiments indicate that DISFusion outperforms state-of-the-art methods and exhibits greater generalization ability. Moreover, analysis of CPTAC pan-cancer proteomic data highlights significant associations between the 30 novel cancer genes predicted by DISFusion and multiple cancer types, underscoring its practical utility. These findings validate the effectiveness of enhancing common information and provide new insights into cancer gene identification. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IPM-LSTM: A Learning-Based Interior Point Method for Solving Nonlinear Programs

arXiv

引用

arXiv 2024年

作者： Gao, Xi Xiong, Jinxin Wang, Akang Duan, Qihong Xue, Jiang Shi, Qingjiang School of Mathematics and Statistics Xi’an Jiaotong University Xi’an China Shenzhen Research Institute of Big Data China School of Data Science The Chinese University of Hong Kong Shenzhen China School of Software Engineering Tongji University Shanghai China

Solving constrained nonlinear programs (NLPs) is of great importance in various domains such as power systems, robotics, and wireless communication networks. One widely used approach for addressing NLPs is the interior point method (IPM). The most computationally expensive procedure in IPMs is to solve systems of linear equations via matrix factorization. Recently, machine learning techniques have been adopted to expedite classic optimization algorithms. In this work, we propose using Long Short-Term Memory (LSTM) neural networks to approximate the solution of linear systems and integrate this approximating step into an IPM. The resulting approximate NLP solution is then utilized to warm-start an interior point solver. Experiments on various types of NLPs, including Quadratic Programs and Quadratically Constrained Quadratic Programs, show that our approach can significantly accelerate NLP solving, reducing iterations by up to 60% and solution time by up to 70% compared to the default solver. © 2024, CC BY.

关键词： Matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Bilinear-Experts Network with Self-Adaptive Sampler for Long-Tailed Visual Recognition

SSRN

引用

SSRN 2024年

作者： Wang, Qin Wang, Xizhao Big Data Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

Long-tail distributed data hinders the practical application of state-of-the-art deep models in computer vision. Consequently, exclusive methodologies for handling the long-tailed problem are proposed, focusing on different hierarchies. For embedding hierarchy, existing works manually augment the diversity of tail-class features for specific datasets. However, prior knowledge about datasets is not always available for practical use, which brings unsatisfactory generalization ability in human fine-turned augmentation under such circumstances. To figure out this problem, we introduce a novel model named Bilinear-Experts Network (BENet) with Self-Adaptive Sampler (SAS). This model leverages model-driven perturbations to tail-class embeddings while preserving generalization capability on head classes through a designed bilinear experts system. The designed perturbations adaptively augment tail-class space and shift the class boundary away from the tail-class centers. Moreover, we surprisingly find that SAS automatically assigns more significant perturbations to specific tail classes rather than fewer-sample classes, which is against the common assumption that fewer-sample classes deserve greater attention. Also, experiments conducted across various long-tailed benchmarks validate the comparable efficacy of proposed BENet. © 2024, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Fall Prediction by a Spatio-Temporal Multi-Channel Causal Model from Wearable Sensors data

Fall Prediction by a Spatio-Temporal Multi-Channel Causal Mo...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Guorui Liao Jiawei Liu Yuxuan Liang Shu Wang Li Liu School of Big Data & Software Engineering Chongqing University Chongqing China The Hong Kong University of Science and Technology (Guangzhou) Guangzhou China School of Materials & Energy Southwest University Chongqing China

Predicting human falls from wearable devices is a complex task due to the inherent diversity and causality of multivariate physical changes, where each instance exhibits a unique style of motion events and their spatio-temporal causal dependencies. Consequently, we propose a multichannel causal model that utilizes the Granger causality test to explicitly delineate these internal configurations of motion events and their causal relationships from a spatio-temporal perspective. Particularly, our model incorporates a multi-head attention mechanism with a distillation component to capture the spatio-temporal dependencies among multiple channels of motion sensors in an end-to-end fashion. Empirical evaluations conducted on two benchmark datasets, as well as one in-house dataset collected by ourselves, indicate that our model significantly surpasses state-of-the-art approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Event Coreference Resolution Using Prompt Learning and U-shaped Module

Improving Event Coreference Resolution Using Prompt Learning...

引用

Computer Science and Blockchain (CCSB), International Conference on

作者： Mengyao Zhang Jun Long Wenti Huang School of Software Xinjiang University Urumqi China Institute of Big Data Central South University Changsha China School of Computer Science and Engineering Hunan University of Science and Technology Changsha China

ISBN: (数字)9798350356502

ISBN: (纸本)9798350356519

Event Coreference Resolution (ECR) focuses on clustering event mentions that allude to identical actual events. Previous research primarily focuses on encoding event mentions without incorporating human interpretations, making it difficult to integrate human-summarized rules for guiding the ECR task. Furthermore, the semantic relations between event mentions have not been thoroughly explored, which impacts coreference judgment. To address these issues, we first utilize the powerful Longformer to acquire event representations at the document level. In addition, we introduce a prompt learning template to better emphasize event types and parameters, enhancing the interaction between event modeling and coreference judgment. Ultimately, we create matching vectors for event mentions using tensor matching and incorporate a U-shaped module to effectively identify the semantic relationships among these mentions, which enhances coreference discrimination. DPTU surpasses other ECR models on the KBP2017 dataset in cause of some experiments.

关键词： Computer science Tensors Computational modeling Semantics Vectors Encoding Blockchains

来源：评论

学校读者我要写书评

暂无评论

A Self-adaptive Indicator Selection Approach for Solving Credit Risk Assessment

A Self-adaptive Indicator Selection Approach for Solving Cre...

引用

IEEE Annual International Computer software and Applications Conference (COMPSAC)

作者： Yongfeng Gu Yue Ning Hao Ding Kecai Gu Daohong Jian Zhou Xu Hua Wu Jun Zhou Ant Group Hangzhou China School of Big Data and Software Engineering Chongqing University Chongqing China

ISBN: (数字)9781665488105

ISBN: (纸本)9781665488112

Credit risk assessment, which aims at identifying high-risk users, plays a critical role in financial institutions. A common method is to use the greedy strategy to generate an interpretable rule set to classify all the users into high-risk or non-risk users. During each iteration, the greedy strategy utilizes a pre-defined indicator function to evaluate which rule is the best and then adds it to the rule set. However, in reality, the indicator function is designed manually and requires much domain knowledge and expert experience. Worse still, we need to design a suitable indicator for every situation, which is tedious and time-consuming work. This motivates us to propose a self-adaptive indicator that can be adapted to different situations without too much human intervention. In this paper, we see the indicator as a weighted sum of several sub-indicators. By tuning the weights, the indicator can be adapted to different situations automatically. That is, we transform this indicator selection problem into a weights tuning problem. To find the best weight of self-adaptive indicators, machine learning methods and black-box optimization are utilized. The experimental results demonstrated that our self-adaptive indicator can select a better rule set to identify more high-risk users compared to the human-defined indicator.

关键词： Conferences Optimization methods Machine learning Transforms Real-time systems software Risk management

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：