检索结果-内蒙古大学图书馆

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

作者： Haihong Guo Fengxin Li Jiao Li Hongyan Liu School of Information Renmin University of China China Institute of Medical Information / Medical Library Chinese Academy of Medical Sciences / Peking Union Medical College China Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education China School of Economics and Management Tsinghua University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Kolmogorov-Arnold Networks (KAN) is an emerging neural network architecture in machine learning. It has greatly interested the research community about whether KAN can be a promising alternative to the commonly used Multi-Layer Perceptions (MLP). Experiments in various fields demonstrated that KAN-based machine learning can achieve comparable if not better performance than MLP-based methods, but with much smaller parameter scales and are more explainable. In this paper, we explore the incorporation of KAN into the actor and critic networks for offline reinforcement learning (RL). We evaluated the performance, parameter scales, and training efficiency of various KAN and MLP-based conservative Q-learning (CQL) on the classical D4RL benchmark for offline RL. Our study demonstrates that KAN can achieve performance close to the commonly used MLP with significantly fewer parameters. This allows us to choose the base networks according to the offline RL task requirements.

关键词： Training Performance evaluation Hands Q-learning Neural networks Memory management Signal processing Benchmark testing Splines (mathematics) Speech processing

来源：评论

学校读者我要写书评

暂无评论

TraSculptor: Visual Analytics for Enhanced Decision-Making in Road Traffic Planning

引用

IEEE Transactions on Visualization and Computer Graphics 2025年 PP卷 PP页

作者： Deng, Zikun Liu, Yuanbang Zhu, Mingrui Xiang, Da Yu, Haiyue Su, Zicheng Lu, Qinglong Schreck, Tobias Cai, Yi South China University of Technology School of Software Engineering China South China University of Technology Ministry of Education Key Laboratory of Big Data and Intelligent Robot China Tongji University Key Laboratory of Road and Traffic Engineering of the Ministry of Education China National University of Singapore Department of Civil and Environmental Engineering Singapore Graz University of Technology Austria

The design of urban road networks significantly influences traffic conditions, underscoring the importance of informed traffic planning. Traffic planning experts rely on specialized platforms to simulate traffic systems, assessing the efficacy of the road network across various states of modifications. Nevertheless, a prevailing issue persists: many existing traffic planning platforms exhibit inefficiencies in flexibly interacting with the road network's structure and attributes and intuitively comparing multiple states during the iterative planning process. This paper introduces TraSculptor, an interactive planning decision-making system. To develop TraSculptor, we identify and address two challenges: interactive modification of road networks and intuitive comparison of multiple network states. For the first challenge, we establish flexible interactions to enable experts to easily and directly modify the road network on the map. For the second challenge, we design a comparison view with a history tree of multiple states and a road-state matrix to facilitate intuitive comparison of road network states. To evaluate TraSculptor, we provided a usage scenario where the Braess's paradox was showcased, invited experts to perform a case study on the Sioux Falls network, and collected expert feedback through interviews. © 1995-2012 IEEE.

关键词： Visual analytics

来源：评论

学校读者我要写书评

暂无评论

SecureCut: Federated Gradient Boosting Decision Trees with Efficient Machine Unlearning 27th

SecureCut: Federated Gradient Boosting Decision Trees with ...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Li, Bowen Zhang, Jian Li, Jie Wu, Chentao Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Yancheng Blockchain Research Institute Yancheng China Blockchain Advanced Research Center Shanghai China Shanghai Key Laboratory of Trusted Data Circulation and Governance and Web3 Shanghai China

ISBN: (纸本)9783031781681

In response to legislation, companies are now mandated to honor the right to be forgotten by erasing user data. Consequently, it has become imperative to enable data removal in Vertical Federated Learning (VFL), where multiple parties provide private features for model training. In VFL, data removal, i.e., machine unlearning, requires removing specific features across all samples, ensuring privacy in federated learning. To address this challenge, we propose SecureCut, a novel Gradient Boosting Decision Tree (GBDT) framework that effectively enables both instance unlearning and feature unlearning without the need for retraining from scratch. Leveraging a robust GBDT structure, we enable effective data deletion while reducing degradation of model performance. Extensive experimental results on popular datasets demonstrate that our method achieves superior model utility and forgetfulness compared to the state-of-the-art methods. To the best of our knowledge, this is the first work that investigates machine unlearning in VFL scenarios. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A review on global spatial distribution,sources and toxicity of perfluoroalkyl acid and prospect in the cryosphere

引用

Journal of Mountain Science 2025年第1期22卷 167-183页

作者： LI Bowen Du Wentao KANG Shichang CHEN Jizu JIANG Youyan YIN Lichen LU Changsheng LIU Hongyi State Key Laboratory of Cryospheric Science and frozen soil engineering Northwest Institute of Eco-Environment and ResourcesChinese Academy of Sciences(CAS)Lanzhou 730000China University of Chinese Academy of Sciences Beijing 100049China Gansu Provincial Industry Technology Center of Intelligent Equipment and Big Data for Disaster Prevention Northwest Institute of Eco-Environment and ResourcesChinese Academy of Sciences(CAS)Lanzhou 730000China Lanzhou Regional Climate Center Lanzhou 730000China School of Earth Sciences and Spatial Information Engineering Hunan University of Science and TechnologyXiangtan 411201China School of Energy and Power Engineering Lanzhou University of TechnologyLanzhou 730000China Zhangye Meteorological Service Zhangye 734000China

Perfluoroalkyl acid analogs(PFAAs)are a class of chemically stable environmentally persistent organic pollutants(POPs)that are difficult to degrade and have a strong capacity to accumulate in the human *** have been found to be biotoxic to humans and have been detected in various environmental media,especially in the cryosphere at trace *** cryosphere,sensitively responds to climate change,plays a crucial role in the global water,carbon and energy ***,researches on cryosphere PFAAs especially in Tibetan Plateau(TP)is ***,we summarize the physicochemical properties,physiological toxicity,spatiotemporal distribution,sources,diffusion and migration pathways,as well as analysis and removal methods of PFAAs in the cryosphere *** results show that PFAAs pollutants are mainly produced and distributed in the more economically developed countries in Europe and the United States,as well as in East Asia,and PFAAs can be transported by atmospheric circulation and water cycle to remote regions including cryosphere *** current detection methods for PFAAs in cryosphere need to be further refined for increased accuracy and *** is also a need to develop more effective removal methods that will reduce the environmental and human threats posed by these ***,we propose key scientific questions for future research in cryosphere including PFAAs redistribution influenced by cryosphere changes,human activities,and the interaction of other spheres.

关键词： Perfluoroalkyl acid Cryosphere Physiological toxicity Analytical method Removal method

来源：评论

学校读者我要写书评

暂无评论

NIR-II fluorescence molecular tomography based on transformer encoder architecture

NIR-II fluorescence molecular tomography based on transforme...

引用

Medical Imaging 2025: Clinical and Biomedical Imaging

作者： Bao, Jie Xiao, Anqi Han, keyi Pei, Ziyu Fu, Lidan Tian, Jie Hu, Zhenhua CAS Key Laboratory of Molecular Imaging Beijing Key Laboratory of Molecular Imaging Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine School of Engineering Medicine Beihang University Beijing China Engineering Research Center of Molecular and Neuro Imaging of Ministry of Education School of Life Science and Technology Xidian University Xi’an China National Key Laboratory of Kidney Diseases Beijing China

ISBN: (纸本)9781510685987

Fluorescence molecular tomography (FMT) is a highly sensitive method for depicting the three-dimensional distribution of fluorescent targets within biological tissues. However, traditional FMT reconstruction can be affected by the severe photon scattering and the modeling errors of the photon propagation model, making it difficult to obtain accurate reconstruction results. Deep learning methods can directly learn the nonlinear mapping between the photon intensity on the surface and the internal light sources, providing a promising approach for addressing the inverse problem in FMT. Since the second near-infrared window (NIR-II, 1000-1700) fluorescence imaging has a higher tissue penetration depth and imaging contrast, this work constructs a deep learning model suitable for the fluorescence images in this spectrum. The model introduced in this study, akin to grasping the contextual nuances of word vectors in the domain of machine translation, endeavors to comprehend the process of photon transmission within biological tissues. Inspired by the transformer encoder, we proposed a network mainly consist of positional encoding, dual-head attention mechanism, residual connection, and fully connected layers. It has achieved significantly better results than comparative methods on the NIR-II dataset constructed by the Monte Carlo method. © 2025 SPIE.

关键词： Fluorescence imaging

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

Enhancing Unsupervised Graph Few-shot Learning via Set Functions and Optimal Transport 25

Enhancing Unsupervised Graph Few-shot Learning via Set Funct...

引用

Proceedings of the 31st ACM SIGKDD Conference on knowledge Discovery and data Mining V.1

作者： Yonghao Liu Fausto Giunchiglia Ximing Li Lan Huang Xiaoyue Feng Renchu Guan Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University Changchun China Department of Information Engineering and Computer Science University of Trento Trento Italy

ISBN: (纸本)9798400712456

Graph few-shot learning has garnered significant attention for its ability to rapidly adapt to downstream tasks with limited labeled data, sparking considerable interest among researchers. Recent advancements in graph few-shot learning models have exhibited superior performance across diverse applications. Despite their successes, several limitations still exist. First, existing models in the meta-training phase predominantly focus on instance-level features within tasks, neglecting crucial set-level features essential for distinguishing between different categories. Second, these models often utilize query sets directly on classifiers trained with support sets containing only a few labeled examples, overlooking potential distribution shifts between these sets and leading to suboptimal performance. Finally, previous models typically require necessitate abundant labeled data from base classes to extract transferable knowledge, which is typically infeasible in real-world scenarios. To address these issues, we propose a novel model named STAR, which leverages Set funcTions and optimAl tRansport for enhancing unsupervised graph few-shot learning. Specifically, STAR utilizes expressive set functions to obtain set-level features in an unsupervised manner and employs optimal transport principles to align the distributions of support and query sets, thereby mitigating distribution shift effects. Theoretical analysis demonstrates that STAR can capture more task-relevant information and enhance generalization capabilities. Empirically, extensive experiments across multiple datasets validate the effectiveness of STAR. Our code can be found https://***/KEAML-JLU/STAR here.

关键词： few-shot learning

来源：评论

学校读者我要写书评

暂无评论

Mining User–Item Interactions via knowledge Graph for Recommendation

引用

ACM Transactions on Recommender Systems 2025年第3期3卷 1-19页

作者： Shenghao Liu Lingyun Lu Bang Wang Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Hubei Key Laboratory of Smart Internet Technology School of Electronic Information and Communications Huazhong University of Science and Technology (HUST) Wuhan China

Introducing a knowledge Graph (KG) to facilitate a recommender system has become a tendency in recent years. Many existing methods leverage KGs to obtain side information of items to promote item representation learning for enhancing recommendation performance. However, they ignore that KGs also may contribute to better user representation learning. To solve this issue, we propose a novel algorithm, the KIGR (knowledge-aware Interaction Graph for Recommendation), to mine user–item interactions via KGs for assisting user representation learning. Specifically, a user–item interaction is encoded by attentively summing up the relation embedding about the item in the KG. Then, an unsupervised learning method is used to group the user–item interactions into different latent types. Further, a user–item interaction graph is divided into several subgraphs, which is referred to as a knowledge-aware Interaction Graph, making each subgraph only contain one latent type of interaction. Finally, user representation is the fusion of user interest embedding, which is learned on the knowledge-aware interaction graph, whereas item representation is learned on the KG. Experimental results on MovieLens, LastFM and Amazon-Book validate that the proposed KIGR has a superior performance compared with the state-of-the-art algorithms.

关键词： Recommendation system knowledge graph graph neural network

来源：评论

学校读者我要写书评

暂无评论

Priority-Based Reward Mechanism for Dual-Robot Path Planning in Dynamic Environments

引用

IEEE Access 2025年 13卷 92519-92530页

作者： Hu, Yibo Wei, Lai Guo, Xiaoyu Li, Zhenyao Wei, Yanding Fang, Qiang Zhejiang University The State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering Hangzhou310027 China Zhejiang University Key Laboratory of Advanced Manufacturing Technology of Zhejiang Province School of Mechanical Engineering Hangzhou310027 China The Chinese University of Hong Kong School of Data Science Shenzhen518172 China

The definition of motion priority enables robot groups to handle competition and cooperation better when performing physical tasks. In this paper, we propose a priority-based step reward mechanism, which is a new reward mechanism for deep reinforcement learning of multi-robot systems and can improve collaboration between robotic arms in shared workspaces. The intention of each agent is provided to other agents, presenting a 2D map of the head that is visually consistent, with state and action representations aligned spatially. Guided by priority-based step rewards, the dual-robots are sequentially assigned high priority, enabling them to pass through complex environments in sequence. We validated our method on a path planning task where two robots collaborate to transport cubes in dynamic environments. The two robots need to consider obstacle avoidance while handing cubes to the human operator. The experimental environment includes Free space, obstacles in the middle, obstacles on both sides, and combinations of several environments. The results show that priority step rewards improve the performance of robot collaborative tasks and significantly enhance cooperative behavior. © 2013 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

EDSep: An Effective Diffusion-Based Method for Speech Source Separation

EDSep: An Effective Diffusion-Based Method for Speech Source...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Dong, Jinwei Wang, Xinsheng Mao, Qirong School of Computer Science and Communication Engineering Jiangsu University China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications China Provincial Key Laboratory of Computational Intelligence and New Technologies in Low-Altitude Digital Agriculture Zhenjiang China Audio Speech and Language Processing Group School of Computer Science Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9798350368741

Generative models have attracted considerable attention for speech separation tasks, and among these, diffusion-based methods are being explored. Despite the notable success of diffusion techniques in generation tasks, their adaptation to speech separation has encountered challenges, notably slow convergence and suboptimal separation outcomes. To address these issues and enhance the efficacy of diffusion-based speech separation, we introduce EDSep, a novel single-channel method grounded in score matching via stochastic differential equation (SDE). This method enhances generative modeling for speech source separation by optimizing training and sampling efficiency. Specifically, a novel denoiser function is proposed to approximate data distributions, which obtains ideal denoiser outputs. Additionally, a stochastic sampler is carefully designed to resolve the reverse SDE during the sampling process, gradually separating speech from mixtures. Extensive experiments on databases such as WSJ0-2mix, LRS2-2mix, and VoxCeleb2-2mix demonstrate our proposed method's superior performance over existing diffusion and discriminative models, validating its efficacy. © 2025 IEEE.

关键词： diffusion score matching speech separation stochastic differential equation

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：