检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhao, Gongpei Wang, Tao Lang, Congyan Jin, Yi Li, Yidong Ling, Haibin Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education China School of Computer Science & Technology Beijing Jiaotong University China Department of Computer Science Stony Brook University United States

Graph neural networks (GNNs) are recognized for their strong performance across various applications, with the backpropagation (BP) algorithm playing a central role in the development of most GNN models. However, despite its effectiveness, BP has limitations that challenge its biological plausibility and affect the efficiency, scalability and parallelism of training neural networks for graph-based tasks. While several non-backpropagation (non-BP) training algorithms, such as the direct feedback alignment (DFA), have been successfully applied to fully-connected and convolutional network components for handling Euclidean data, directly adapting these non-BP frameworks to manage non-Euclidean graph data in GNN models presents significant challenges. These challenges primarily arise from the violation of the independent and identically distributed (i.i.d.) assumption in graph data and the difficulty in accessing prediction errors for all samples (nodes) within the graph. To overcome these obstacles, in this paper we propose DFA-GNN, a novel forward learning framework tailored for GNNs with a case study of semi-supervised learning. The proposed method breaks the limitations of BP by using a dedicated forward training mechanism. Specifically, DFA-GNN extends the principles of DFA to adapt to graph data and unique architecture of GNNs, which incorporates the information of graph topology into the feedback links to accommodate the non-Euclidean characteristics of graph data. Additionally, for semi-supervised graph learning tasks, we developed a pseudo error generator that spreads residual errors from training data to create a pseudo error for each unlabeled node. These pseudo errors are then utilized to train GNNs using DFA. Extensive experiments on 10 public benchmarks reveal that our learning framework outperforms not only previous non-BP methods but also the standard BP methods, and it exhibits excellent robustness against various types of noise and attacks. © 2024 Neura

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Pre-selected Local Weighted Method for Improving the Performance of LMKNN Classifier 6

A Pre-selected Local Weighted Method for Improving the Perfo...

引用

6th IEEE International Conference on Power, Intelligent Computing and Systems, ICPICS 2024

作者： Zhang, Yuzhi Guan, Ziyan Xiong, Chen School of Aeronautic Science and Engineering Beihang University Beijing China School of Big Data & Software Engineering Chongqing University Chongqing China School of Computer Science Xi'an Jiaotong University City College Xi'an China

ISBN: (纸本)9798350374315

The K-nearest neighbor (KNN) algorithm and its variant Local Mean K-nearest neighbor (LMKNN) have been widely used in the field of data mining due to their simplicity and intuition. However, these methods have limitations when dealing with unbalanced datasets and edge samples, such as sensitivity to the choice of nearest neighbor size and degradation of classification performance for outlier points. To address these issues, this paper proposes a pre-selected locally weighted mean K-nearest neighbor (PLWMKNN) algorithm, which aims to improve the performance of LMKNN through an advanced pre-selection mechanism and a weighted average method. PLWMKNN firstly pre-selects favorable classes as the nearest neighbors based on the distance weights, and then computes the weighted center vectors of each class to classify them by the minimum distance principle. Through experimental validation on four real datasets, PLWMKNN shows significant performance improvement over traditional KNN and LMKNN for unbalanced datasets. Our results demonstrate the effectiveness of the PLWMKNN algorithm in improving classification accuracy and robustness, especially when dealing with extremely unbalanced datasets. © 2024 IEEE.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Unified Graph and Hypergraph Neural Network for Next-item Recommendation

Unified Graph and Hypergraph Neural Network for Next-item Re...

引用

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

作者： Zhang, Xinyu Jiang, Qize Zhang, Hanyuan Sun, Weiwei School of Computer Science Shanghai Key Laboratory of Data Science Fudan University Shanghai China Shanghai Institute of Intelligent Electronics & Systems Shanghai China

ISBN: (纸本)9798350368741

The task of next-item recommendation is a crucial component in recommendation systems. The challenge of this task lies in extracting complex interaction information from users' historical interactions with items. While prior research has transformed users' interaction histories into graphs and hypergraphs to mine high-order interactions, the integration of both remains uncharted. Existing methods treat graphs and hypergraphs separately in representation learning, missing out on their shared attributes. Addressing this gap, we introduce a novel unified framework that integrates graphs and hypergraphs into one unified message passing paradigm. Our method employs graph neural networks and hypergraph neural networks to continuously conduct representation learning, achieving end-to-end next item recommendation. Specifically, our framework consists of the following components: 1) a unique method for graph and hypergraph construction from interaction histories, with items as nodes and users as hyperedges;2) a novel message passing framework compatible with both graph and hypergraph neural networks;and 3) an innovative hypergraph neural network aggregation module enhanced with time and position encoders. The test results on multiple public benchmarks verify that our method outperforms current best practices in performance. © 2025 IEEE.

关键词： Graph Neural Network Hypergraph Neural Network Next-item Recommendation User Modeling

来源：评论

学校读者我要写书评

暂无评论

Position-aware Hypergraph Message-Passing Neural Network

Position-aware Hypergraph Message-Passing Neural Network

引用

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

ISBN: (纸本)9798350368741

Hypergraph neural networks can model more flexible connectivity relationships, are used to model higher-order interactions, and have produced strong results in many real-world applications. However, the currently existing hypergraph neural networks need more exploration in capturing the global positional information of nodes in hypergraphs. Although there have been many explorations of the problem in graph neural networks, extending these approaches to hypergraphs is fraught with challenges. The major challenge is that hyperedges in hypergraphs are the other dimensional element of the incidence structure, have more flexible definitions than edges in graphs, and require more attention when learning global positional information. We propose a novel position-aware hypergraph message-passing neural network framework to address the above challenges. Specifically, we propose a global positional embedding learning approach that can separately model global positional information for nodes and hyperedges. At the same time, we also optimize the learning of local structures with hyperedges. Experiments on several publicly available benchmark datasets find that our proposed method outperforms many state-of-the-art methods. © 2025 IEEE.

关键词： Hypergraph Learning Hypergraph Neural Network Message Passing Neural Network

来源：评论

学校读者我要写书评

暂无评论

Neural Machine Translation Models with Attention-Based Dropout Layer

引用

computers, Materials & Continua 2023年第5期75卷 2981-3009页

作者： Huma Israr Safdar Abbas Khan Muhammad Ali Tahir Muhammad Khuram Shahzad Muneer Ahmad Jasni Mohamad Zain School of Electrical Engineering and Computer Science(SEECS) National University of Science and TechnologyIslamabadPakistan Institute for Big Data Analytics and Artificial Intelligence(IBDAAI) Kompleks Al-KhawarizmiUniversiti Teknologi MARA40450Shah AlamSelangorMalaysia

In bilingual translation,attention-based Neural Machine Translation(NMT)models are used to achieve synchrony between input and output sequences and the notion of *** model has obtained state-of-the-art performance for several language ***,there has been little work exploring useful architectures for Urdu-to-English machine *** conducted extensive Urdu-to-English translation experiments using Long short-term memory(LSTM)/Bidirectional recurrent neural networks(Bi-RNN)/Statistical recurrent unit(SRU)/Gated recurrent unit(GRU)/Convolutional neural network(CNN)and *** results show that Bi-RNN and LSTM with attention mechanism trained iteratively,with a scalable data set,make precise predictions on unseen *** trained models yielded competitive results by achieving 62.6%and 61%accuracy and 49.67 and 47.14 BLEU scores,*** a qualitative perspective,the translation of the test sets was examined manually,and it was observed that trained models tend to produce repetitive output more *** attention score produced by Bi-RNN and LSTM produced clear alignment,while GRU showed incorrect translation for words,poor alignment and lack of a clear ***,we considered refining the attention-based models by defining an additional attention-based dropout *** dropout fixes alignment errors and minimizes translation errors at the word *** empirical demonstration and comparison with their counterparts,we found improvement in the quality of the resulting translation system and a decrease in the perplexity and over-translation *** ability of the proposed model was evaluated using Arabic-English and Persian-English datasets as *** empirically concluded that adding an attention-based dropout layer helps improve GRU,SRU,and Transformer translation and is considerably more efficient in translation quality and speed.

关键词： Natural language processing neural machine translation word embedding attention perplexity selective dropout regularization Urdu Persian Arabic BLEU

来源：评论

学校读者我要写书评

暂无评论

High-Order Resting-State Functional Connectivity is Predictive of Working Memory Decline After Brain Tumor Resection 46

High-Order Resting-State Functional Connectivity is Predicti...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Tran, Triet M. Tran, Thi T. Khanmohammadi, Sina University of Oklahoma Data Science And Analytics Institute NormanOK73109 United States University of Oklahoma School of Computer Science NormanOK73109 United States

ISBN: (纸本)9798350371499

Surgical resection is one of the main treatment options for brain tumors. However, there is a risk of postoperative cognitive deterioration associated with resective surgery. Recent studies suggest that pre-surgery brain dynamics captured using functional Magnetic Resonance Imaging (fMRI) could provide valuable information about the risk of post-surgery cognitive decline. However, most of these studies are based on simple regression analysis of the raw fMRI signals that do not capture the underlying complex brain dynamics. Here, we investigated the role of higher-order functional brain networks in predicting cognitive decline after surgical resection of brain tumors. More specifically, we looked at the predictive power of second-order functional brain networks in estimating post-surgery working memory (WM) performance. Our results show that the second-order functional brain networks can accurately predict the working memory decline in patients with glioma and meningioma tumors. These findings suggest that there is an interesting relationship between pre-surgical higher-order brain dynamics and the risk of cognitive decline after surgery, which could potentially yield a better prognostic marker for treatment planning of brain tumor patients. © 2024 IEEE.

关键词： Transplantation (surgical)

来源：评论

学校读者我要写书评

暂无评论

Few-shot Prompting for Pairwise Ranking: An Effective Non-Parametric Retrieval Model

Few-shot Prompting for Pairwise Ranking: An Effective Non-Pa...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Sinhababu, Nilanjan Parry, Andrew Ganguly, Debasis Samanta, Debasis Mitra, Pabitra Centre for Computational and Data Sciences IIT Kharagpur India School of Computing Science University of Glasgow United Kingdom Department of Computer Science and Engineering IIT Kharagpur India

ISBN: (纸本)9798891761681

A supervised ranking model, despite its effectiveness over traditional approaches, usually involves complex processing - typically multiple stages of task-specific pre-training and fine-tuning. This has motivated researchers to explore simpler pipelines leveraging large language models (LLMs) that can work in a zero-shot manner. However, since zero-shot inference does not make use of a training set of pairs of queries and their relevant documents, its performance is mostly worse than that of supervised models, which are trained on such example pairs. Motivated by the existing findings that training examples generally improve zero-shot performance, in our work, we explore if this also applies to ranking models. More specifically, given a query and a pair of documents, the preference prediction task is improved by augmenting examples of preferences for similar queries from a training set. Our proposed pairwise few-shot ranker demonstrates consistent improvements over the zero-shot baseline on both in-domain (TREC DL) and out-domain (BEIR subset) retrieval benchmarks. Our method also achieves a close performance to that of a supervised model without requiring any complex training pipeline. © 2024 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

Nuclei Segmentation in Histopathology Images Using Structure-Preserving Color Normalization Based Ensemble Deep Learning Frameworks

引用

computers, Materials & Continua 2023年第12期77卷 3077-3094页

作者： Manas Ranjan Prusty Rishi Dinesh Hariket Sukesh Kumar Sheth Alapati Lakshmi Viswanath Sandeep Kumar Satapathy Centre for Cyber-Physical Systems Vellore Institute of TechnologyChennai600127India School of Computer Science and Engineering Vellore Institute of TechnologyChennai600127India Centre for Advanced Data Science Vellore Institute of TechnologyChennai600127India

This paper presents a novel computerized technique for the segmentation of nuclei in hematoxylin and eosin(H&E)stained histopathology *** purpose of this study is to overcome the challenges faced in automated nuclei segmentation due to the diversity of nuclei structures that arise from differences in tissue types and staining protocols,as well as the segmentation of variable-sized and overlapping *** this extent,the approach proposed in this study uses an ensemble of the UNet architecture with various Convolutional Neural Networks(CNN)architectures as encoder backbones,along with stain normalization and test time augmentation,to improve segmentation ***,this paper employs a Structure-Preserving Color Normalization(SPCN)technique as a preprocessing step for stain *** proposed model was trained and tested on both single-organ and multi-organ datasets,yielding an F1 score of 84.11%,mean Intersection over Union(IoU)of 81.67%,dice score of 84.11%,accuracy of 92.58%and precision of 83.78%on the multi-organ dataset,and an F1 score of 87.04%,mean IoU of 86.66%,dice score of 87.04%,accuracy of 96.69%and precision of 87.57%on the single-organ *** findings demonstrate that the proposed model ensemble coupled with the right pre-processing and post-processing techniques enhances nuclei segmentation capabilities.

关键词： Nuclei segmentation image segmentation ensemble U-Net deep learning histopathology image convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Localized Zeroth-Order Prompt Optimization 38

Localized Zeroth-Order Prompt Optimization

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Hu, Wenyang Shu, Yao Yu, Zongmin Wu, Zhaoxuan Lin, Xiaoqiang Dai, Zhongxiang Ng, See-Kiong Low, Bryan Kian Hsiang Dept. of Computer Science National University of Singapore Singapore Institute of Data Science National University of Singapore Singapore China Singapore-MIT Alliance for Research and Technology Singapore School of Data Science The Chinese University of Hong Kong Shenzhen China

The efficacy of large language models (LLMs) in understanding and generating natural language has aroused a wide interest in developing prompt-based methods to harness the power of black-box LLMs. Existing methodologies usually prioritize a global optimization for finding the global optimum, which however will perform poorly in certain tasks under budget constraints. This thus motivates us to re-think the necessity of finding a global optimum in prompt optimization. To answer this, we conduct a thorough empirical study on prompt optimization and draw two major insights. Contrasting with the rarity of global optimum, local optima are usually prevalent and well-performed, which can be more worthwhile for efficient prompt optimization (Insight I). The choice of the input domain, including both the generation and the representation of prompts, affects the identification of well-performing local optima (Insight II). Inspired by these insights, we propose a novel algorithm, namely localized zeroth-order prompt optimization (ZOPO), which incorporates a Neural Tangent Kernel-based derived Gaussian process into standard zeroth-order optimization for an efficient search of well-performing local optima in prompt optimization. Remarkably, ZOPO outperforms existing baselines in terms of both the optimization performance and the query efficiency, which we demonstrate through extensive experiments. Our implementation is available at https://***/allen4747/ZOPO. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IoT-Enhanced Agricultural Water Management System Utilizing Conventional Machine Learning Methods

IoT-Enhanced Agricultural Water Management System Utilizing ...

引用

2023 IEEE International Conference on Modelling, Simulation and Intelligent Computing, MoSICom 2023

作者： Singh, Jagendra Garg, Neha Kukreja, Sonal Saini, Mayank Singh, Ishaan Mall, Shachi Bennett University School of Computer Science Engineering and Technology Greater Noida India Publicis Sapient Manager Data Science Greater Noida India Galgotias University School of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798350393415

This study delves into IoT-enhanced Agricultural Water Management, aspiring to transform farming for enhanced crop output and sustainability. It focuses on an intelligent system incorporating a sensor network and varied machine learning methods for climate monitoring and yield prediction in tomato cultivation. Notably, the Convolutional Neural Network (CNN) stood out with a 95.2% accuracy rate in predicting yields, highlighting its potential as a pivotal tool in effective irrigation management. This adaptive, data-driven system promises advanced water management, addressing pressing global concerns of food security and resource conservation by aligning agricultural practices with environmental parameters and enabling heightened crop productivity. © 2023 IEEE.

关键词： Water 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：