检索结果-内蒙古大学图书馆

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Mingqing Xiao Qingyan Meng Zongpeng Zhang Di He Zhouchen Lin Key Lab. of Machine Perception (MoE) School of Intelligence Science and Technology Peking University The Chinese University of Hong Kong Shenzhen and Shenzhen Research Institute of Big Data Center for Data Science Academy for Advanced Interdisciplinary Studies Peking University Key Lab. of Machine Perception (MoE) School of Intelligence Science and Technology Peking University and Institute for Artificial Intelligence Peking University and Peng Cheng Laboratory China

ISBN: (纸本)9781713871088

Spiking neural networks (SNNs) are promising brain-inspired energy-efficient models. Recent progress in training methods has enabled successful deep SNNs on large-scale tasks with low latency. Particularly, backpropagation through time (BPTT) with surrogate gradients (SG) is popularly used to enable models to achieve high performance in a very small number of time steps. However, it is at the cost of large memory consumption for training, lack of theoretical clarity for optimization, and inconsistency with the online property of biological learning rules and rules on neuromorphic hardware. Other works connect the spike representations of SNNs with equivalent artificial neural network formulation and train SNNs by gradients from equivalent mappings to ensure descent directions. But they fail to achieve low latency and are also not online. In this work, we propose online training through time (OTTT) for SNNs, which is derived from BPTT to enable forward-in-time learning by tracking presynaptic activities and leveraging instantaneous loss and gradients. Meanwhile, we theoretically analyze and prove that the gradients of OTTT can provide a similar descent direction for optimization as gradients from equivalent mapping between spike representations under both feedforward and recurrent conditions. OTTT only requires constant training memory costs agnostic to time steps, avoiding the significant memory costs of BPTT for GPU training. Furthermore, the update rule of OTTT is in the form of three-factor Hebbian learning, which could pave a path for online on-chip learning. With OTTT, it is the first time that the two mainstream supervised SNN training methods, BPTT with SG and spike representation-based training, are connected, and meanwhile it is in a biologically plausible form. Experiments on CIFAR-10, CIFAR-100, ImageNet, and CIFAR10-DVS demonstrate the superior performance of our method on large-scale static and neuromorphic datasets in a small number of time steps.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous peer effects of college roommates on academic performance

arXiv

引用

arXiv 2024年

作者： Cao, Yi Zhou, Tao Gao, Jian CompleX Lab University of Electronic Science and Technology of China Chengdu China Big Data Research Center University of Electronic Science and Technology of China Chengdu China Center for Science of Science and Innovation Northwestern University EvanstonIL United States Kellogg School of Management Northwestern University EvanstonIL United States Northwestern Institute on Complex Systems Northwestern University EvanstonIL United States Faculty of Social Sciences The University of Hong Kong Hong Kong

Understanding how student peers influence learning outcomes is crucial for effective education management in complex social systems. The complexities of peer selection and evolving peer relationships, however, pose challenges for identifying peer effects using static observational data. Here we use both null-model and regression approaches to examine peer effects using longitudinal data from 5,272 undergraduates, where roommate assignments are plausibly random upon enrollment and roommate relationships persist until graduation. Specifically, we construct a roommate null model by randomly shuffling students among dorm rooms and introduce an assimilation metric to quantify similarities in roommate academic performance. We find significantly larger assimilation in actual data than in the roommate null model, suggesting roommate peer effects, whereby roommates have more similar performance than expected by chance alone. Moreover, assimilation exhibits an overall increasing trend over time, suggesting that peer effects become stronger the longer roommates live together. Our regression analysis further reveals the moderating role of peer heterogeneity. In particular, when roommates perform similarly, the positive relationship between a student’s future performance and their roommates’ average prior performance is more pronounced, and their ordinal rank in the dorm room has an independent effect. Our findings contribute to understanding the role of college roommates in influencing student academic performance. © 2024, CC BY.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Memory Architecture Supporting Fine-Grained data Migration

SSRN

引用

SSRN 2022年

作者： Chi, Ye Yue, Jianhui Liao, Xiaofei Liu, Haikun Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Computer Science Michigan Technological University HoughtonMI United States

We propose Mocha, a non-hierarchical caching architecture that organizes DRAM and NVM in a flat address space physically, but manages DRAM/NVM in a cache/memory hierarchy in this paper. Since the commercial NVM device-Intel Optane DC Persist Memory Modules (DCPMM) actually access the physical media at a granularity of 256 bytes (an Optane block), we manage the DRAM cache at the 256-byte size to adapt to this device feature of Optane. This design not only enables fine-grained data migration and management for the DRAM cache, but also avoids write amplification for Optane DCPMM. We also create a the \textit{ Indirect Address Cache} (IAC) in \textit{Hybrid Memory Controller}(HMC) and propose a reverse address mapping table in the DRAM to speed up address translation and cache replacement. Besides, we exploit an utility-based caching mechanism to filter cold blocks in the NVM, and further improve DRAM cache effectiveness. We implement Mocha in an architecture simulator. Experimental results indicate that MOCHA can improve performance of applications by 8.2\% on average (up to 24.6\%), provide 6.9\% reduction in average energy consumption and 25.9\% reduction in average data migration traffic, compared to the most advanced hybrid memory architecture-HSCC. © 2022, The Authors. All rights reserved.

关键词： Dynamic random access storage

来源：评论

学校读者我要写书评

暂无评论

LECF: recommendation via learnable edge collaborative filtering

引用

science China(Information sciences) 2022年第1期65卷 116-130页

作者： Shitao XIAO Yingxia SHAO Yawen LI Hongzhi YIN Yanyan SHEN Bin CUI School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing Key Lab of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and Telecommunications School of Information Technology and Electrical Engineering The University of Queensland Department of Computer Science and Engineering Shanghai Jiao Tong University Department of Computer Science and Technology Peking University National Engineering Laboratory for Big Data Analysis and Applications Peking University

The core of recommendation models is estimating the probability that a user will like an item based on historical interactions. Existing collaborative filtering(CF) algorithms compute the likelihood by utilizing simple relationships between objects, e.g., user-item, item-item, or user-user. They always rely on a single type of object-object relationship, ignoring other useful relationship information in data. In this paper, we model an interaction between user and item as an edge and propose a novel CF framework, called learnable edge collaborative filtering(LECF). LECF predicts the existence probability of an edge based on the connections among edges and is able to capture the complex relationship in data. Specifically, we first adopt the concept of line graph where each node represents an interaction edge; then calculate a weighted sum of similarity between the query edge and the observed edges(i.e., historical interactions) that are selected from the neighborhood of query edge in the line graph for a recommendation. In addition, we design an efficient propagation algorithm to speed up the training and inference of LECF. Extensive experiments on four public datasets demonstrate LECF can achieve better performance than the state-of-the-art methods.

关键词： collaborative filtering recommender system implicit feedback edge-edge similarity line graph

来源：评论

学校读者我要写书评

暂无评论

SPA: A Graph Spectral Alignment Perspective for Domain Adaptation

arXiv

引用

arXiv 2023年

作者： Xiao, Zhiqing Wang, Haobo Jin, Ying Feng, Lei Chen, Gang Huang, Fei Zhao, Junbo College of Computer Science and Technology Zhejiang University China School of Software Technology Zhejiang University China Key Lab of Intelligent Computing based Big Data of Zhejiang Province Zhejiang University China CUHK-SenseTime Joint Lab The Chinese University of Hong Kong Hong Kong School of Computer Science and Engineering Nanyang Technological University Singapore Alibaba Group China

Unsupervised domain adaptation (UDA) is a pivotal form in machine learning to extend the in-domain model to the distinctive target domains where the data distributions differ. Most prior works focus on capturing the inter-domain transferability but largely overlook rich intra-domain structures, which empirically results in even worse discriminability. In this work, we introduce a novel graph SPectral Alignment (SPA) framework to tackle the tradeoff. The core of our method is briefly condensed as follows: (i)-by casting the DA problem to graph primitives, SPA composes a coarse graph alignment mechanism with a novel spectral regularizer towards aligning the domain graphs in eigenspaces;(ii)-we further develop a fine-grained message propagation module — upon a novel neighbor-aware self-training mechanism — in order for enhanced discriminability in the target domain. On standardized benchmarks, the extensive experiments of SPA demonstrate that its performance has surpassed the existing cutting-edge DA methods. Coupled with dense model analysis, we conclude that our approach indeed possesses superior efficacy, robustness, discriminability, and transferability. Code and data are available at: https://***/CrownX/SPA. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Efficient COVID-19 detection using data mining algorithms: a comparison of basic and hybrid approaches

引用

Soft Computing 2025年第3期29卷 1437-1451页

作者： Saidi, Mohammad Gheibi, Mohammad Ghazikhani, Adel Lotfata, Aynaz Chahkandi, Benyamin Familsamavati, Sajad Behzadian, Kourosh Department of Computer Science Imam Reza International University Mashhad Iran MS of Software Engineering Information and Communication Technology Unit Mashhad Municipality Fire and Safety Services Organization Mashhad Iran Big Data Lab Imam Reza International University Mashhad Iran Institute for Nanomaterials Advanced Technologies and Innovation Technical University of Liberec Liberec46117 Czech Republic Tallinn10615 Estonia Department of Pathology Microbiology and Immunology School of Veterinary Medicine University of California Davis95616 United States Department of Urban and Regional Planning San Jose State University San Jose95192 United States Faculty of Civil and Environmental Engineering Gdansk University of Technology Narutowicza Street 11/12 80-233 Gdansk Poland Tecnologico de Monterrey Escuela de Ingeniería y Ciencias Monterrey Mexico School of Computing and Engineering University of West London London United Kingdom

Accurate and efficient diagnosis of COVID-19 remains a significant challenge due to the limitations of current detection methods, such as blood tests and chest scans, which can be time-consuming and error-prone. This study aims to compare the performance of basic and hybrid data mining algorithms in diagnosing COVID-19, using blood test results and clinical information to identify the most effective approach. A dataset of 200 records from suspected and infected COVID-19 patients, with 23 characteristics and one diagnostic class, was analysed. Nine data mining algorithms were tested: four basic algorithms (Naive Bayes, Support Vector Machine, Decision Tree, K-Nearest Neighbor) and five hybrid algorithms (Random Forest, AdaBoost, Majority Voting, XGBoost, Bagging). The study also integrated Response Surface Methodology (RSM) and Adaptive-Network-based Fuzzy Inference System (ANFIS) to enhance model performance. The Bagging algorithm demonstrated superior performance with an accuracy of 88%, sensitivity of 74%, and F-criterion of 78%. The integration of RSM and ANFIS further showed that a smart model could be developed for efficient pandemic crisis management, achieving up to 100% accuracy when considering key factors like AST, Albumin, and CRP. The findings suggest that Bagging and hybrid data mining algorithms can significantly improve COVID-19 detection, reducing time and errors in identifying exposed individuals. The study highlights the potential of combining machine learning techniques with RSM-ANFIS models for effective pandemic management and decision-making in medical settings. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrieval

arXiv

引用

arXiv 2023年

作者： Xie, Yi Zhang, Huaidong Xu, Xuemiao Zhu, Jianqing He, Shengfeng South China University of Technology China Huaqiao University China Singapore Management University Singapore State Key Laboratory of Subtropical Building Science China Ministry of Education Key Laboratory of Big Data and Intelligent Robot China Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information China

Previous Knowledge Distillation based efficient image retrieval methods employs a lightweight network as the student model for fast inference. However, the lightweight student model lacks adequate representation capacity for effective knowledge imitation during the most critical early training period, causing final performance degeneration. To tackle this issue, we propose a Capacity Dynamic Distillation framework, which constructs a student model with editable representation capacity. Specifically, the employed student model is initially a heavy model to fruitfully learn distilled knowledge in the early training epochs, and the student model is gradually compressed during the training. To dynamically adjust the model capacity, our dynamic framework inserts a learnable convolutional layer within each residual block in the student model as the channel importance indicator. The indicator is optimized simultaneously by the image retrieval loss and the compression loss, and a retrieval-guided gradient resetting mechanism is proposed to release the gradient conflict. Extensive experiments show that our method has superior inference speed and accuracy, e.g., on the VeRi-776 dataset, given the ResNet101 as a teacher, our method saves 67.13% model parameters and 65.67% FLOPs without sacrificing accuracy. Copyright © 2023, The Authors. All rights reserved.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Tail Quantile Estimation for Non-Preemptive Priority Queues 22

Tail Quantile Estimation for Non-Preemptive Priority Queues

引用

Proceedings of the Winter Simulation Conference

作者： Jin Guang Guiyu Hong Xinyun Chen Xi Peng Li Chen Bo Bai Gong Zhang Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen Shenzhen Guangdong P. R. CHINA School of Data Science The Chinese University of Hong Kong Shenzhen Shenzhen Guangdong P. R. CHINA Theory Lab Central Research Institute Labs Huawei Technologies Co. Ltd. Shatin N.T. Hong Kong P. R. CHINA

Motivated by applications in computing and telecommunication systems, we investigate the problem of estimating p-quantile of steady-state sojourn times in a single-server multi-class queueing system with non-preemptive priorities for p close to 1. The main challenge in this problem lies in efficient sampling from the tail event. To address this issue, we develop a regenerative simulation algorithm with importance sampling. In addition, we establish a central limit theorem for the estimator to construct the confidence interval. Numerical experiments show that our algorithm outperforms benchmark simulation methods. Our result contributes to the literature on rare event simulation for queueing systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluating Interpolation and Extrapolation Performance of Neural Retrieval Models

arXiv

引用

arXiv 2022年

作者： Zhan, Jingtao Xie, Xiaohui Mao, Jiaxin Liu, Yiqun Guo, Jiafeng Zhang, Min Ma, Shaoping Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Beijing Key Laboratory of Big Data Management and Analysis Methods Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

A retrieval model should not only interpolate the training data but also extrapolate well to the queries that are different from the training data. While neural retrieval models have demonstrated impressive performance on ad-hoc search benchmarks, we still know little about how they perform in terms of interpolation and extrapolation. In this paper, we demonstrate the importance of separately evaluating the two capabilities of neural retrieval models. Firstly, we examine existing ad-hoc search benchmarks from the two perspectives. We investigate the distribution of training and test data and find a considerable overlap in query entities, query intent, and relevance labels. This finding implies that the evaluation on these test sets is biased toward interpolation and cannot accurately reflect the extrapolation capacity. Secondly, we propose a novel evaluation protocol to separately evaluate the interpolation and extrapolation performance on existing benchmark datasets. It resamples the training and test data based on query similarity and utilizes the resampled dataset for training and evaluation. Finally, we leverage the proposed evaluation protocol to comprehensively revisit a number of widely-adopted neural retrieval models. Results show models perform differently when moving from interpolation to extrapolation. For example, representation-based retrieval models perform almost as well as interaction-based retrieval models in terms of interpolation but not extrapolation. Therefore, it is necessary to separately evaluate both interpolation and extrapolation performance and the proposed resampling method serves as a simple yet effective evaluation tool for future IR studies. Copyright © 2022, The Authors. All rights reserved.

关键词： Extrapolation

来源：评论

学校读者我要写书评

暂无评论

Enhanced Attention-Based Pedestrian Trajectory Prediction Model: Integration of Dynamic Social Relationships and Spatial Correlations

SSRN

引用

SSRN 2024年

作者： Lu, Xu Li, Zhize Gao, Xiang de Albuquerque, Victor Hugo C. Liu, Jun School of Computer Science Guangdong Polytechnic Normal University Guangzhou510665 China Guangdong Provincial Key Laboratory of Intellectual Property & Big Data Guangzhou510665 China Pazhou Lab Guangzhou510330 China Department of Teleinformatics Engineering Federal University of Ceará Fortaleza60020-181 Brazil School of automation Guangdong Polytechnic Normal University Guangzhou510665 China

Existing pedestrian trajectory prediction models inadequately consider the impact of evolving dynamic social relationships among pedestrians on roadways and insufficiently address spatial correlation relationships. This paper introduces an attention-enhanced pedestrian trajectory prediction model. It aims to address limitations in traditional models regarding dynamic pedestrian social information and spatial positional correlations. To begin with, it incorporates a dynamic social relationship module based on attention mechanisms. This module captures the dynamic features within pedestrian social relationships effectively, thereby enhancing the modeling capabilities for social interactions. Additionally, to address the issue of insufficient spatial positional correlation, the model introduces dynamic correlation modeling for historical trajectories. This enables a more comprehensive understanding of the internal connections among positional points. Experimental results demonstrate significant performance improvements compared to traditional methods on both the SDD dataset and the inD dataset under the TrajNet benchmark. The model achieves average displacement errors of 7.15 and 11.33, and final displacement errors of 12.51 and 21.21 respectively. © 2024, The Authors. All rights reserved.

关键词： Dynamics

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：