检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zou, Xin Zhou, Zhengyu Xu, Jingyuan Liu, Weiwei School of Computer Science Wuhan University National Engineering Research Center for Multimedia Software Wuhan University Institute of Artificial Intelligence Wuhan University Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University

ADABOOST is a well-known algorithm in boosting. Schapire and Singer propose, an extension of ADABOOST, named ***, for multi-class classification problems. Kégl shows empirically that *** works better when the classical one-against-all base classifiers are replaced by factorized base classifiers containing a binary classifier and a vote (or code) vector. However, the factorization makes it much more difficult to provide a convergence result for the factorized version of ***. Then, Kégl raises an open problem in COLT 2014 to look for a convergence result for the factorized ***. In this work, we resolve this open problem by presenting a convergence result for *** with factorized multi-class classifiers. © 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

Zero-shot Image Classification with Logic Adapter and Rule Prompt 24

Zero-shot Image Classification with Logic Adapter and Rule P...

引用

33rd ACM Web Conference, WWW 2024

作者： Yu, Dongran Liu, Xueyan Yang, Bo Key Laboratory of Symbolic Computation and Knowledge Engineer Ministry of Education School of Artificial Intelligence Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineer Ministry of Education School of Computer Science and Technology Jilin University Changchun China

ISBN: (纸本)9798400701719

Zero-shot image classification, which aims to predict unseen classes whose samples have never appeared during the training phase, is crucial in the Web domain because many new web images appear on various websites. Attributes, as annotations for class-level characteristics, are widely used semantic information for this task. However, most current methods often fail to capture discriminative image features between similar images from different classes, leading to unsatisfactory zero-shot image classification results. This is because they solely focus on limited visual-attribute feature alignment. Therefore, we propose a Zero-Shot image Classification with Logic adapter and Rule prompt method called ZSCLR, which utilizes logic adapter and rule prompts to encourage the model to capture discriminative image features and achieve reasoning. Specifically, ZSCLR consists of a visual perception module and a logic adapter. The visual perception module extracts image features from training data. At the same time, the logic adapter utilizes the Markov logic network to encode the extracted image features and rule prompts for refining the discriminative image features. Due to predicates of rule prompts representing symbolic discriminative features, the proposed model can focus more on these discriminative features and achieve more precise image classification. Additionally, the logic adapter enables the model to adapt from recognizing images in seen classes to those in unseen classes through the reasoning of the Markov logic networks. We implement experiments on three standard zero-shot image classification benchmarks, and ZSCLR achieves competitive performance. Furthermore, ZSCLR can provide explanations for its predictions through rule prompts. © 2024 ACM.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Online Self-distillation and Self-modeling for 3D Brain Tumor Segmentation

引用

IEEE Journal of Biomedical and Health Informatics 2025年第6期29卷 4290-4302页

作者： Pang, Yan Li, Yunhao Huang, Teng Liang, Jiaming Wang, Zhen Dong, Changyu Kuang, Dongyang Hu, Ying Chen, Hao Lei, Tim Wang, Qiong The Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China The School of Artificial Intelligence Guangzhou University China The Zhejiang Lab Hangzhou China Sun Yat-sen University China The Department of Computer Science and Engineering The Department of Chemical and Biological Engineering Hong Kong University of Science and Technology China The Department of Electrical Engineering University of Colorado Denver United States

In the specialized domain of brain tumor segmentation, supervised segmentation approaches are hindered by the limited availability of high-quality labeled data, a condition arising from data privacy concerns, significant costs, and ethical issues. In response to this challenge, this paper presents a training framework that adeptly integrates a plug-and-play component, MOD, into current supervised learning models, boosting their efficacy in scenarios with limited data. The MOD consists of an Online Tokenizer and a Dense Predictor, which employs self-distillation and self-modeling on masked patches, promoting swift convergence and efficient representation learning. During the inference phase, the plug-and-play MOD component is excluded, preserving the computational efficiency of the original model without incurring extra processing costs. We substantiated the value of our approach through experiments on leading 3D brain tumor segmentation baselines. Remarkably, models augmented with the MOD consistently showcased superior results, achieving elevated Dice coefficients and HD95 scores on two datasets: BraTS 2021 and MSD 2019 Task-01 Brain Tumor. Code: https://***/aigzhusmart/MOD © 2013 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

ALIGNSUM: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preference

ALIGNSUM: Data Pyramid Hierarchical Fine-tuning for Aligning...

引用

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

作者： Han, Yang Wang, Yiming Wang, Rui Chen, Lu Yu, Kai X-LANCE Lab Department of Computer Science and Engineering SJTU China MoE Key Lab of Artificial Intelligence SJTU AI Institute Shanghai Jiao Tong University Shanghai China Suzhou Laboratory Suzhou China

ISBN: (纸本)9798891761681

Text summarization tasks commonly employ Pre-trained Language Models (PLMs) to fit diverse standard *** these PLMs excel in automatic evaluations, they frequently underperform in human evaluations, indicating a deviation between their generated summaries and human summarization *** discrepancy is likely due to the low quality of fine-tuning datasets and the limited availability of high-quality human-annotated data that reflect true human *** address this challenge, we introduce a novel human summarization preference alignment framework *** framework consists of three parts: Firstly, we construct a Data Pymarid with extractive, abstractive, and human-annotated summary ***, we conduct the Gaussian Resampling to remove summaries with extreme ***, we implement the two-stage hierarchical fine-tuning with Data Pymarid after Gaussian *** apply ALIGNSUM to PLMs on the human-annotated CNN/DailyMail and BBC XSum *** show that with ALIGNSUM, PLMs like BART-Large surpass 175B GPT-3 in both automatic and human *** demonstrates that ALIGNSUM significantly enhances the alignment of language models with human summarization preferences. © 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

The Reliability of OKRidge Method in Solving Sparse Ridge Regression Problems 38

The Reliability of OKRidge Method in Solving Sparse Ridge Re...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Li, Xiyuan Wang, Youjun Liu, Weiwei School of Computer Science Wuhan University National Engineering Research Center for Multimedia Software Wuhan University Institute of Artificial Intelligence Wuhan University Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University

Sparse ridge regression problems play a significant role across various domains. To solve sparse ridge regression, [1] recently proposes an advanced algorithm, Scalable Optimal K-Sparse Ridge Regression (OKRidge), which is both faster and more accurate than existing approaches. However, the absence of theoretical analysis on the error of OKRidge impedes its large-scale applications. In this paper, we reframe the estimation error of OKRidge as a Primary Optimization (PO) problem and employ the Convex Gaussian min-max theorem (CGMT) to simplify the PO problem into an Auxiliary Optimization (AO) problem. Subsequently, we provide a theoretical error analysis for OKRidge based on the AO problem. This error analysis improves the theoretical reliability of OKRidge. We also conduct experiments to verify our theorems and the results are in excellent agreement with our theoretical findings. © 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

人工智能在化学逆合成中的应用

引用

Engineering 2023年第6期25卷 32-50,M0003页

作者： Yinjie Jiang Yemin Yu Ming Kong Yu Mei Luotian Yuan Zhengxing Huang Kun Kuang Zhihua Wang Huaxiu Yao James Zou Connor W.Coley Ying Wei College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China Department of Computer Science City University of Hong KongHong Kong 999077China Shanghai Institute for Advanced Study Zhejiang UniversityShanghai 201203China Shanghai Artificial Intelligence Laboratory Shanghai 201203China Department of Computer Science Stanford UniversityStanfordCA 94305–2004USA Department of Chemical Engineering&Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of TechnologyCambridgeMA 02139USA

近年来,人们对通过人工智能(AI)技术解决化学逆合成预测问题产生了巨大的兴趣。与化学家和基于规则的专家系统进行的逆合成预测不同,AI驱动的逆合成预测自动从现成的实验数据集中学习化学知识,以预测反应和逆合成路径。这提供了解决许... 详细信息

近年来,人们对通过人工智能(AI)技术解决化学逆合成预测问题产生了巨大的兴趣。与化学家和基于规则的专家系统进行的逆合成预测不同,AI驱动的逆合成预测自动从现成的实验数据集中学习化学知识,以预测反应和逆合成路径。这提供了解决许多传统挑战的机会,包括专业知识过于繁杂、路线的长度过大和计算成本高。本文描述了当前AI驱动的逆合成预测的概况。我们首先讨论了化学逆合成的数学定义,并回顾了这个问题中的研究挑战。然后,我们回顾相关的AI技术和最新进度,以实现逆合成预测。此外,我们提供了逆合成系统不同部分的全面分类,并调查了AI方法如何重塑每个子模块。最后,我们讨论了未来有希望的研究领域。

关键词：逆合成计算成本数学定义化学知识 AI技术基于规则的专家系统专业知识子模块

来源：评论

学校读者我要写书评

暂无评论

Unlocking the Potential of Model Merging for Low-Resource Languages

Unlocking the Potential of Model Merging for Low-Resource La...

引用

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

作者： Tao, Mingxu Zhang, Chen Huang, Quzhe Ma, Tianyao Huang, Songfang Zhao, Dongyan Feng, Yansong Wangxuan Institute of Computer Technology Peking University China State Key Laboratory of General Artificial Intelligence Peking University China Center for Data Science Peking University China College of Engineering Peking University China

ISBN: (纸本)9798891761681

Adapting large language models (LLMs) to new languages typically involves continual pre-training (CT) followed by supervised finetuning (SFT).However, this CT-then-SFT approach struggles with limited data in the context of low-resource languages, failing to balance language modeling and task-solving *** thus propose a new model merging solution as an alternative for low-resource languages, combining models with distinct capabilities into a single model without additional *** use model merging to develop task-solving LLMs for low-resource languages without SFT data in the target *** experiments based on Llama-2-7B demonstrate that model merging effectively endows LLMs for low-resource languages with task-solving abilities, outperforming CT-then-SFT in scenarios with extremely scarce *** performance saturation in model merging with increasingly more training tokens, we further analyze the merging process and introduce a slack variable to the model merging algorithm to mitigate the loss of important parameters, thereby enhancing model *** hope that model merging can benefit more human languages suffering from data scarcity with its higher data efficiency. © 2024 Association for Computational Linguistics.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

A deep convolutional neural network for diabetic retinopathy detection via mining local and long-range dependence

引用

CAAI Transactions on intelligence Technology 2024年第1期9卷 153-166页

作者： Xiaoling Luo Wei Wang Yong Xu Zhihui Lai Xiaopeng Jin Bob Zhang David Zhang Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of TechnologyShenzhenChina Peng Cheng Laboratory ShenzhenChina Shenzhen Institute of Artificial Intelligence and Robotics for Society ShenzhenChina College of Big Data and Internet Shenzhen Technology UniversityShenzhenChina The Department of Computer and Information Science University of MacaoMacaoMacaoChina The Chinese University of Hong Kong(Shenzhen) ShenzhenChina

Diabetic retinopathy(DR),the main cause of irreversible blindness,is one of the most common complications of *** present,deep convolutional neural networks have achieved promising performance in automatic DR detection *** convolution operation of methods is a local cross-correlation operation,whose receptive field de-termines the size of the local neighbourhood for ***,for retinal fundus photographs,there is not only the local information but also long-distance dependence between the lesion features(*** and exudates)scattered throughout the whole *** proposed method incorporates correlations between long-range patches into the deep learning framework to improve DR ***-wise re-lationships are used to enhance the local patch features since lesions of DR usually appear as *** Long-Range unit in the proposed network with a residual structure can be flexibly embedded into other trained *** experimental results demon-strate that the proposed approach can achieve higher accuracy than existing state-of-the-art models on Messidor and EyePACS datasets.

关键词： image classification medical image processing pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Large Language Model-based Human-Agent Collaboration for Complex Task Solving

Large Language Model-based Human-Agent Collaboration for Com...

引用

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

作者： Feng, Xueyang Chen, Zhi-Yuan Qin, Yujia Lin, Yankai Chen, Xu Liu, Zhiyuan Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9798891761681

In recent developments within the research community, the integration of Large Language Models (LLMs) in creating fully autonomous agents has garnered significant interest. Despite this, LLM-based agents frequently demonstrate notable shortcomings in adjusting to dynamic environments and fully grasping human needs. In this work, we introduce the problem of LLM-based human-agent collaboration for complex task-solving, exploring their synergistic potential. To tackle the problem, we propose a Reinforcement Learning-based HumanAgent Collaboration method, ReHAC, which trains a policy model designed to determine the most opportune stages for human intervention within the task-solving process. We conduct experiments under real and simulated human-agent collaboration scenarios. Experimental results demonstrate that the synergistic efforts of humans and LLM-based agents significantly improve performance in complex tasks, primarily through well-planned, limited human intervention. Datasets and code are available at: https://***/XueyangFeng/ReHAC/. © 2024 Association for Computational Linguistics.

关键词： Autonomous agents

来源：评论

学校读者我要写书评

暂无评论

Exploiting Associations among Multi-Aspect Node Properties in Heterogeneous Graphs for Link Prediction 24

Exploiting Associations among Multi-Aspect Node Properties i...

引用

33rd Companion of the ACM World Wide Web Conference, WWW 2023

作者： Du, Chenguang Geng, Hao Wang, Deqing Zhuang, Fuzhen Zhang, Zhiqiang Zhang, Lanshan SKLSDE School of Computer Science Beihang University Beijing China Institute of Artificial Intelligence and SKLSDE School of Computer Science Beihang University Beijing China Ant Group Hangzhou China Beijing Key Laboratory of Network System and Network Culture Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9798400701726

Recent years have witnessed the abundant emergence of heterogeneous graph neural networks (HGNNs) for link prediction. In heterogeneous graphs, different meta-paths connected to nodes reflect different aspects of the nodes’ properties. Existing work fuses the multi-aspect properties of each node into a single vector representation, which makes them fail to capture fine-grained associations between multiple node properties. To this end, we propose a heterogeneous graph neural network with Multi-Aspect Node Association awareness, namely MANA. MANA leverages key associations among multi-aspect node properties to achieve link prediction. Specifically, to avoid the loss of effective association information for link prediction, we design a transformer-based Multi-Aspect Association Mining module to capture multi-aspect associations between nodes. Then, we introduce the Multi-Aspect Link Prediction module, empowering MANA to focus on the key associations among all, thus avoiding the negative impact of ineffective associations on the model’s performance. We conduct extensive experiments on three widely used datasets from Heterogeneous Graph Benchmark (HGB). Experimental results show that our proposed method outperforms state-of-the-art baselines. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Graph neural networks

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：