检索结果-内蒙古大学图书馆

Acta Mathematica Sinica,English Series 2025年第2期41卷 498-521页

作者： Xiangyu Zheng Songxi Chen JD Technology Beijing 100176P.R.China Department of Statistics and Data Science Tsinghua UniversityBeijing 100084P.R.China

Tree-based models have been widely applied in both academic and industrial settings due to the natural interpretability, good predictive accuracy, and high scalability. In this paper, we focus on improving the single-tree method and propose the segmented linear regression trees(SLRT) model that replaces the traditional constant leaf model with linear ones. From the parametric view, SLRT can be employed as a recursive change point detect procedure for segmented linear regression(SLR) models,which is much more efficient and flexible than the traditional grid search method. Along this way,we propose to use the conditional Kendall's τ correlation coefficient to select the underlying change points. From the non-parametric view, we propose an efficient greedy splitting method that selects the splits by analyzing the association between residuals and each candidate split variable. Further, with the SLRT as a single-tree predictor, we propose a linear random forest approach that aggregates the SLRTs by a weighted average. Both simulation and empirical studies showed significant improvements than the CART trees and even the random forest.

关键词： Regression trees segmented linear regression split selection tree pruning

来源：评论

学校读者我要写书评

暂无评论

Unsupervised multiplex graph diffusion networks with multi-level canonical correlation analysis for multiplex graph representation learning

引用

Science China(Information Sciences) 2025年第3期68卷 66-79页

作者： Sichao FU Qinmu PENG Yange HE Baokun DU Bin ZOU Xiao-Yuan JING Xinge YOU School of Electronic Information and Communications Huazhong University of Science and Technology Platform Operation and Marketing Center JD Retail Faculty of Mathematics and Statistics Hubei Key Laboratory of Applied Mathematics Hubei University School of Computer Science Wuhan University

In recent years, unsupervised multiplex graph representation learning(UMGRL) has received increasing research interest, which aims to learn discriminative node features from the multiplex graphs supervised by data without the guidance of labels. Although these designed UMGRL methods have obtained great success in various graph-related tasks, most existing UMGRL models still have the following issues: highly depending on complex self-supervised strategies(i.e., data augmentation,pretext tasks, and negative pairs sampling), restricted receptive fields, and only aggregating low-frequency information between nodes. In this paper, we propose a simple unsupervised multiplex graph diffusion network(UMGDN) with the aid of multi-level canonical correlation analysis to solve the above issues. Specifically, we first decouple the feature transform and propagation processes of the graph convolution layer to further improve the generalization of the learnable parameters. And then, we propose adaptive diffusion propagation to capture long-range dependency relationships between nodes, not the local neighborhood interactions. Finally, a multi-level canonical correlation analysis loss on both the feature transform and propagation processes is proposed to maximize the correlation of the same node features from multiple graphs for guiding model optimization. Compared to the existing UMGRL models, our proposed UMGDN does not need to introduce any data augmentation, negative pairs sampling techniques, complex pretext tasks, and also adaptively aggregates the optimal frequency information between nodes to generate more robust node embeddings. Extensive experiments on four popular datasets and two graph-related tasks demonstrate the effectiveness of the proposed method.

关键词： unsupervised multiplex graph representation learning graph neural networks node classification node clustering

来源：评论

学校读者我要写书评

暂无评论

Low-temperature active soldering of 5A06-Al alloy and Ti-Cu-Ni alloy mesh-reinforced SAC305 composite solder: Interfacial bonding behavior and joint properties

引用

Journal of Materials Science and technology 2025年 235卷 313-323页

作者： Li, Dan Xi, Bangfu Xiao, Yong Song, Lizhi Zhang, Jian Luo, Dan Goodall, Russell School of Materials Science and Engineering Wuhan University of Technology Wuhan430070 China State Key Laboratory of Advanced Technology for Materials Synthesis and Processing Wuhan University of Technology Wuhan430070 China Department of Materials Science and Engineering The University of Sheffield SheffieldS1 3JD United Kingdom

Achieving reliable bonding is critical for low-temperature active soldering in Al alloys. In this study, a novel Ti-Cu-Ni alloy mesh-reinforced SAC305 composite solder was developed for active soldering of 5A06-Al alloy at 350 °C. Effects of soldering time on the microstructure and mechanical properties of joints were investigated, and the interfacial bonding mechanism of joints was analyzed. Results showed that the (Cu, Ni)6Sn5 phase was formed between alloy mesh and SAC305 solder in the active composite solder, while Ti atoms were uniformly released from the alloy mesh. Metallurgical products within joints mainly comprised (Cu, Ni)6Sn5 and Al3(Ni, Cu)2 phases, which developed with increasing soldering time. An amorphous Al2O3 layer and a Mg-containing layer were formed at the Al substrate/SAC305 solder interface. Mg atoms could enhance the charge transfer between Ti atoms and oxide film, attracting the diffusion of Ti atoms to oxide film. The oxide film removal processes relied on the synergistic impacts of Ti and Mg. The highest shear strength of joints reached 53.21 ± 0.91 MPa, exceeding previously reported properties for low-temperature active soldering by over 100 %. This exploration may provide insights into developing low-temperature active soldering technologies for Al alloys. © 2025

关键词： Titanium alloys

来源：评论

学校读者我要写书评

暂无评论

A Graph-Oriented Context-Aware Activity-Based Behavioural Model for Geriatric Care 11th

A Graph-Oriented Context-Aware Activity-Based Behavioural Mo...

引用

11th International Symposium on Applied Computing for Software and Smart Systems, ACSS 2024

作者： Ghosh, Moumita Choudhury, Sankhayan Haldia Institute of Technology Icare Complex West Bengal Haldia India University of Calcutta JD Block SaltLake Kolkata India

ISBN: (纸本)9789819797615

In lieu of activity recognition, the broader objective of a geriatric healthcare monitoring system is to identify cognitive impairments. The prerequisite of this identification is to model the behavioural pattern of the concerned person in terms of activity sequence. The behavioural pattern may change with the change in context parameters. Thus, a context-sensitive formal representation of behaviour is highly needed for apprehending the deviation within behavioural patterns. In this domain, most of the works are focused on activity discovery or activity recognition;minimal efforts are there on behavioural study. Moreover, the existing models handle simple transactional queries efficiently but for analytical queries, the situation is managed at run-time through the data retrieval from the lower-level recognition model. Instead of mining the entire dataset for each such query, an independent higher-level formal model for the representation of behaviour becomes effective. The caregiver can directly interact with the higher-level model for getting the output in less response time. In this paper, a graph-based behavioural analysis model is formally proposed on top of the underlying recognition model for achieving the above-said objective. The change in activity pattern for a specific context is carefully addressed within the proposed model. The model has been illustrated through a benchmark dataset and a rigorous experiment has been done on benchmark datasets ARUBA, TULUM, and KYOTO to measure the efficiency in terms of response time. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Geriatrics

来源：评论

学校读者我要写书评

暂无评论

Online Learning for Intelligent Thermal Management of Interference-Coupled and Passively Cooled Base Stations

IEEE Transactions on Machine Learning in Communications and ...

引用

IEEE Transactions on Machine Learning in Communications and Networking 2025年 3卷 64-79页

作者： Yu, Zhanwei Zhao, Yi Chu, Xiaoli Yuan, Di Uppsala University Department of Information Technology Uppsala751 05 Sweden University of Sheffield Department of Electronic and Electrical Engineering SheffieldS1 3JD United Kingdom

Passively cooled base stations (PCBSs) have emerged to deliver better cost and energy efficiency. However, passive cooling necessitates intelligent thermal control via traffic management, i.e., the instantaneous data traffic or throughput of a PCBS directly impacts its thermal performance. This is particularly challenging for outdoor deployment of PCBSs because the heat dissipation efficiency is uncertain and fluctuates over time. What is more, the PCBSs are interference-coupled in multi-cell scenarios. Thus, a higher-throughput PCBS leads to higher interference to the other PCBSs, which, in turn, would require more resource consumption to meet their respective throughput targets. In this paper, we address online decision-making for maximizing the total downlink throughput for a multi-PCBS system subject to constraints related on operating temperature. We demonstrate that a reinforcement learning (RL) approach, specifically soft actor-critic (SAC), can successfully perform throughput maximization while keeping the PCBSs cool, by adapting the throughput to time-varying heat dissipation conditions. Furthermore, we design a denial and reward mechanism that effectively mitigates the risk of overheating during the exploration phase of RL. Simulation results show that our approach achieves up to 88.6% of the global optimum. This is very promising, as our approach operates without prior knowledge of future heat dissipation efficiency, which is required by the global optimum. © 2023 CCBY.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Data Inference via Incomplete Multi-Granularity Data 25

Fine-Grained Data Inference via Incomplete Multi-Granularity...

引用

Proceedings of the ACM on Web Conference 2025

作者： Hepeng Gao Yijun Su Funing Yang Yongjian Yang Jilin University Changchun Jilin China JD Intelligent Cities Research Beijing China and JD iCity JD Technology China Beijing China

ISBN: (纸本)9798400712746

Urban fine-grained data map inference, leveraging information from coarse-grained maps, has emerged as a significant area of research due to the growing complexity and data heterogeneity in urban environments. Existing methods have a priori assumption that a coarse-grained data map, one fixed-size granularity, transforms into a fine-grained data map, also one fixed-size granularity. However, in actual scenarios, the collected coarse-grained data maps are often incomplete and have significantly distinct granularities in various urban areas, which results in incomplete heterogeneous data, i.e., multi-granularity data maps in terms of spatial information. Meanwhile, different granularity data maps are needed for various urban downstream tasks, which is a multi-task problem. To that end, this paper proposes a novel framework, a multi-granularity super-resolution data map inference framework (MGSR), designed to harness spatio-temporal information to transform incomplete coarse-grained multi-granularity data maps into fine-grained multi-granularity data maps. Specifically, we design a granularity alignment network to align multi-granularity information and address missing data on each granularity data map by leveraging the other granularity data maps with a well-designed self-supervised task. Then, we introduce a feature extraction network to capture spatio-temporal dependencies and extract features. Finally, we devise a recurrent super-resolution network with shared parameters to infer multi-granularity data maps. We conduct extensive experiments on three real-world benchmark datasets and demonstrate that MGSR significantly outperforms the state-of-the-art methods for multi-granularity urban data map inference and reduces RMSE and MAE by up to 40.1% and 50.3%, respectively. The source code has been released at https://***/wn13/MGSR\_code.

关键词： fine-grained inference

来源：评论

学校读者我要写书评

暂无评论

DFedADMM: Dual Constraint Controlled Model Inconsistency for Decentralize Federated Learning

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第6期47卷 4803-4815页

作者： Li, Qinglun Shen, Li Li, Guanghao Yin, Quanjun Tao, Dacheng National University of Defense Technology College of Systems Engineering China Shenzhen Campus of Sun Yat-Sen University School of Cyber Science and Technology Shenzhen518107 China JD Explore Academy Beijing100000 China Nanyang Technological University College of Computing & Data Science 50 Nanyang Avenue 639798 Singapore

To address the communication burden issues associated with Federated Learning (FL), Decentralized Federated Learning (DFL) discards the central server and establishes a decentralized communication network, where each client communicates only with neighboring clients. However, existing DFL methods still suffer from two major challenges: local inconsistency and local heterogeneous overfitting, which existing DFL methods have not fundamentally addressed. To tackle these issues, we propose novel DFL algorithms, DFedADMM and its enhanced version DFedADMM-SAM, to improve the performance for DFL. The DFedADMM algorithm employs primal-dual optimization (ADMM) by utilizing dual variables to control the model inconsistency raised from the decentralized heterogeneous data distributions. The DFedADMM-SAM algorithm further improves on DFedADMM by employing a Sharpness-Aware Minimization (SAM) optimizer, which uses gradient perturbations to generate locally flat models and searches for models with uniformly low loss values to mitigate local heterogeneous overfitting. Theoretically, we derive convergence rates of (Formula Presented) and (Formula Presented) in the non-convex setting for DFedADMM and DFedADMM-SAM, respectively, where 1−ψ represents the spectral gap of the gossip matrix. Empirically, extensive experiments on MNIST, CIFAR10, and CIFAR100 datasets demonstrate that our algorithms exhibit superior performance in terms of generalization, convergence speed, and communication overhead compared to existing state-of-the-art (SOTA) optimizers in DFL. © 2025 IEEE. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Large Language Models as an Indirect Reasoner: Contrapositive and Contradiction for Automated Reasoning 31

Large Language Models as an Indirect Reasoner: Contrapositiv...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zhang, Yanfang Sun, Yiliu Zhan, Yibing Tao, Dapeng Tao, Dacheng Gong, Chen Nanjing University of Science and Technology China JD Explore Academy Yunnan University China Nanyang Technological University Singapore Shanghai Jiao Tong University China

ISBN: (纸本)9798891761964

Recently, increasing attention has been focused on improving the ability of Large Language Models (LLMs) to perform complex reasoning. Advanced methods, such as Chain-of-Thought (CoT) and its variants, are found to enhance their reasoning skills by designing suitable prompts or breaking down complex problems into more manageable sub-problems. However, little concentration has been put on exploring the reasoning process, i.e., we discovered that most methods resort to Direct Reasoning (DR) and disregard Indirect Reasoning (IR). This can make LLMs difficult to solve IR tasks, which are often encountered in the real world. To address this issue, we propose a Direct-Indirect Reasoning (DIR) method, which considers DR and IR as multiple parallel reasoning paths that are merged to derive the final answer. We stimulate LLMs to implement IR by crafting prompt templates incorporating the principles of contrapositive and contradiction. These templates trigger LLMs to assume the negation of the conclusion as true, combine it with the premises to deduce a conclusion, and utilize the logical equivalence of the contrapositive to enhance their comprehension of the rules used in the reasoning process. Our DIR method is simple yet effective and can be straightforwardly integrated with existing variants of CoT methods. Experimental results on four datasets related to logical reasoning and mathematic proof demonstrate that our DIR method, when combined with various baseline methods, significantly outperforms all the original methods. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Scaling Down Text Encoders of Text-to-Image Diffusion Models

arXiv

引用

arXiv 2025年

作者： Wang, Lifu Liu, Daqing Liu, Xinchen He, Xiaodong JD Explore Academy *** Inc China Georgia Institute of Technology United States

Text encoders in diffusion models have rapidly evolved, transitioning from CLIP to T5-XXL. Although this evolution has significantly enhanced the models’ ability to understand complex prompts and generate text, it also leads to a substantial increase in the number of parameters. Despite T5 series encoders being trained on the C4 natural language corpus, which includes a significant amount of non-visual data, diffusion models with T5 encoder do not respond to those non-visual prompts, indicating redundancy in representational power. Therefore, it raises an important question: "Do we really need such a large text encoder?" In pursuit of an answer, we employ vision-based knowledge distillation to train a series of T5 encoder models. To fully inherit T5-XXL’s capabilities, we constructed our dataset based on three criteria: image quality, semantic understanding, and text-rendering. Our results demonstrate the scaling down pattern that the distilled T5-base model can generate images of comparable quality to those produced by T5-XXL, while being 50 times smaller in size. This reduction in model size significantly lowers the GPU requirements for running state-of-the-art models such as FLUX and SD3, making high-quality text-to-image generation more accessible. Our code is available at https://***/LifuWang-66/DistillT5. © 2025, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

MHAD: Multimodal Home Activity Dataset with Multi-Angle Videos and Synchronized Physiological Signals

MHAD: Multimodal Home Activity Dataset with Multi-Angle Vide...

引用

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

作者： Yu, Lei Fei, Jintao Liu, Xinyi Yao, Yang Zhao, Jun Wang, Guoxin Li, Xin JD Health Beijing China School of Software Engineering Huazhong University of Science and Technology Wuhan China College of Biomedical Engineering and Instrument Science Zhejiang University Hangzhou China

ISBN: (纸本)9798350368741

Video-based physiology, exemplified by remote photoplethysmography (rPPG), extracts physiological signals such as pulse and respiration by analyzing subtle changes in video recordings. This non-contact, real-time monitoring method holds great potential for home settings. Despite the valuable contributions of public benchmark datasets to this technology, there is currently no dataset specifically designed for passive home monitoring. Existing datasets are often limited to close-up, static, frontal recordings and typically include only 1-2 physiological signals. To advance video-based physiology in real home settings, we introduce the MHAD dataset. It comprises 1, 440 videos from 40 subjects, capturing 6 typical activities from 3 angles in a real home environment. Additionally, 5 physiological signals were recorded, making it a comprehensive video-based physiology dataset. MHAD is compatible with the rPPG-toolbox [1] and has been validated using several unsupervised and supervised methods. Our dataset is publicly available at https://***/jdh-algo/MHAD-Dataset. © 2025 IEEE.

关键词： Home Environment MHAD Dataset Non-contact Monitoring Remote Photoplethysmography (rPPG) Video-based Physiology

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：