检索结果-内蒙古大学图书馆

Journal of Applied Logics 2025年第3期12卷 787-823页

作者： Teze, Juan C. L. Godo, Lluis Simari, Gerardo I. Argentina Spain Argentina School of Computing and Augmented Intelligence Arizona State University United States

Many real-world applications of intelligent systems involve solving planning problems of different nature, oftentimes in dynamic environments and having to deal with potentially contradictory information, leading to what is commonly known as epistemic planning. In this context, defeasible argumentation is a powerful tool that has been developed for over three decades as a practical mechanism that allows for flexible handling of preferences and explainable reasoning. In this article, we first motivate the need to develop argumentationbased epistemic planning frameworks that can be leveraged in real-world applications, describe the related literature, and then provide an overview of a recently-proposed approach to incorporate defeasible argumentation and preferences into automated planning processes. In particular, the framework incorporates conditional expressions to select and change priorities regarding information upon which plans are constructed. We describe its main properties, analyze its strengths and limitations using an illustrative use case, and discuss several future research directions that can be taken to further develop it. © 2025, College Publications. All rights reserved.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

A-FSL: Adaptive Few-Shot Learning via Task-Driven Context Aggregation and Attentive Feature Refinement 27th

A-FSL: Adaptive Few-Shot Learning via Task-Driven Context Ag...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Paul, Riti Vora, Sahil Thakur, Nupur Li, Baoxin School of Computing and Augmented Intelligence Arizona State University TempeAZ85281 United States

ISBN: (纸本)9783031783944

Learning new categories with limited training samples presents a significant challenge for conventional deep learning frameworks. The few-shot learning (FSL) paradigm emerges as a potential solution to address practical constraints in this challenge. The primary difficulties in FSL are insufficient prior knowledge and ineffective alignment of clusters to their corresponding classification vectors in the pretrained feature space. While many FSL methods employ task-agnostic instances and class-specific embedding functions, we argue that incorporating task-specific knowledge is crucial for overcoming FSL challenges. To achieve adaptability in FSL, we propose an Adaptive Few-Shot Learning (A-FSL) framework which (1) aggregates task-specific knowledge and adapts the classification vectors in the pretrained feature space and (2) develops a query class correlation attention module to enhance cluster formation. By considering task-specific information at multiple scales of visual features, we can overcome the limitations of a fixed feature space and refine it to adapt classification and query vectors effectively. The A-FSL framework leads to well-formed clusters for novel classes where classification vectors are drawn toward the clusters, even in the 1-shot setting. Through comprehensive experimental evaluation, we show that our method outperforms the current state-of-the-art on benchmark datasets. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Neuro-Symbolic Embedding for Short and Effective Feature Selection via Autoregressive Generation

引用

ACM Transactions on Intelligent Systems and Technology 2025年第2期16卷 1-21页

作者： Gong, Nanxu Ying, Wangyang Wang, Dongjie Fu, Yanjie School of Computing and Augmented Intelligence Arizona State University TempeAZ United States Department of Computer Science University of Kansas LawrenceKS United States

Feature selection aims to identify the optimal feature subset for enhancing downstream models. Effective feature selection can remove redundant features, save computational resources, accelerate the model learning process, and improve the model overall performance. However, existing works are often time-intensive to identify the effective feature subset within high-dimensional feature spaces. Meanwhile, these methods mainly utilize a single downstream task performance as the selection criterion, leading to the selected subsets that are not only redundant but also lack generalizability. To bridge these gaps, we reformulate feature selection through a neuro-symbolic lens and introduce a novel generative framework aimed at identifying short and effective feature subsets. More specifically, we found that feature ID tokens of the selected subset can be formulated as symbols to reflect the intricate correlations among features. Thus, in this framework, we first create a data collector to automatically collect numerous feature selection samples consisting of feature ID tokens, model performance, and the measurement of feature subset redundancy. Building on the collected data, an encoder-decoder-evaluator learning paradigm is developed to preserve the intelligence of feature selection into a continuous embedding space for efficient search. Within the learned embedding space, we leverage a multi-gradient search algorithm to find more robust and generalized embeddings with the objective of improving model performance and reducing feature subset redundancy. These embeddings are then utilized to reconstruct the feature ID tokens for executing the final feature selection. Ultimately, comprehensive experiments and case studies are conducted to validate the effectiveness of the proposed framework. The associated data and code are publicly available (https://***/NanxuGong/feature-selection-via-autoregreesive-generation). © 2025 Copyright held by the owner/author(s). Publicat

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Automated Program Repair: Emerging Trends Pose and Expose Problems for Benchmarks

引用

ACM computing Surveys 2025年第8期57卷 1-18页

作者： Renzullo, Joseph Reiter, Pemma Weimer, Westley Forrest, Stephanie School of Computing and Augmented Intelligence Arizona State University Tempe United States Arizona State University Tempe United States University of Michigan Ann Arbor United States

Machine learning (ML) pervades the field of Automated Program Repair (APR). Algorithms deploy neural machine translation and large language models (LLMs) to generate software patches, among other tasks. But, there are important differences between these applications of ML and earlier work, which complicates the task of ensuring that results are valid and likely to generalize. A challenge is that the most popular APR evaluation benchmarks were not designed with ML techniques in mind. This is especially true for LLMs, whose large and often poorly-disclosed training datasets may include problems on which they are *** article reviews work in APR published in the field's top five venues since 2018, emphasizing emerging trends in the field, including the dramatic rise of ML models, including LLMs. ML-based articles are categorized along structural and functional dimensions, and a variety of issues are identified that these new methods raise. Importantly, data leakage and contamination concerns arise from the challenge of validating ML-based APR using existing benchmarks, which were designed before these techniques were popular. We discuss inconsistencies in evaluation design and performance reporting and offer pointers to solutions where they are available. Finally, we highlight promising new directions that the field is already taking. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Program translators

来源：评论

学校读者我要写书评

暂无评论

Abduction of Domain Relationships from Data for VQA 40

Abduction of Domain Relationships from Data for VQA

引用

40th International Conference on Logic Programming, ICLP 2024

作者： Chowdhury, Al Mehdi Saadat Shakarian, Paulo Simari, Gerardo I. School of Computing and Augmented Intelligence Arizona State University TempeAZ United States Bahia Blanca Argentina

In this paper, we study the problem of visual question answering (VQA) where the image and query are represented by ASP programs that lack domain data. We provide an approach that is orthogonal and complementary to existing knowledge augmentation techniques where we abduce domain relationships of image constructs from past examples. After framing the abduction problem, we provide a baseline approach, and an implementation that significantly improves the accuracy of query answering yet requires few examples. © 2025 Open Publishing Association. All rights reserved.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Application Analysis of Artificial intelligence Technology in Comprehensive Energy Service 14th

Application Analysis of Artificial Intelligence Technology i...

引用

14th International Conference on Frontier computing, FC 2024

作者： Fu, Dengwei Ira A. Fulton Schools of Engineering School of Computing and Augmented Intelligence Arizona State University TempeAZ United States

ISBN: (纸本)9789819627974

With the growing global demand for energy and the increasingly serious environmental problems, the comprehensive energy services based on artificial intelligence technology, as an efficient, intelligent and sustainable way of energy utilization, has attracted more and more attention. The market participating in the comprehensive energy service platform is a bilateral market dominated by energy suppliers and energy users. On the basis of high-quality power energy resources, a cloud platform for intelligent management of comprehensive energy services is constructed in order to realize the comprehensive integration of energy flow and information flow in the power energy service industry. The platform can provide enterprises and residents with a variety of intelligent services such as energy management, energy forecasting, energy optimization and value-added services, effectively mobilize energy utilization and service levels, efficiently drive the development of local economy, and provide more diverse user communication platforms and information exchange services for power energy services. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Energy development

来源：评论

学校读者我要写书评

暂无评论

OntoKGen: A Genuine Ontology and Knowledge Graph Generator using Large Language Model 71

OntoKGen: A Genuine Ontology and Knowledge Graph Generator u...

引用

71st Annual Reliability and Maintainability Symposium, RAMS 2025

作者： Abolhasani, Mohammad Sadeq Pan, Rong School of Computing and Augmented Intelligence Arizona State University 699 S. Mill Avenue Suite 225 TempeAZ85281 United States

ISBN: (纸本)9798350367744

Extracting relevant and structured knowledge from large, complex technical documents within the Reliability and Maintainability (RAM) domain is labor-intensive and prone to errors. Our work addresses this challenge by presenting OntoKGen, a Genuine pipeline for Ontology extraction and Knowledge Graph (KG) generation. OntoKGen leverages Large Language Models (LLMs) through an interactive user interface guided by our adaptive iterative Chain of Thought (CoT) algorithm to ensure that the ontology extraction process and, thus, KG generation align with user-specific requirements. Although KG generation follows a clear, structured path based on the confirmed ontology, there is no universally correct ontology as it is inherently based on the user’s preferences. OntoKGen recommends an ontology grounded in best practices, minimizing user effort and providing valuable insights that may have been overlooked, all while giving the user complete control over the final ontology. Having generated the KG based on the confirmed ontology, OntoKGen enables seamless integration into schemeless, non-relational databases like Neo4j. This integration allows for flexible storage and retrieval of knowledge from diverse, unstructured sources, facilitating advanced querying, analysis, and decision-making. Moreover, the generated KG serves as a robust foundation for future integration into Retrieval-augmented Generation (RAG) systems, offering enhanced capabilities for developing domain-specific intelligent applications. © 2025 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Diffusion on Graph: Augmentation of Graph Structure for Node Classification

arXiv

引用

arXiv 2025年

作者： Wang, Yancheng Liu, Changyu Yang, Yingzhen School of Computing and Augmented Intelligence Arizona State University United States

Graph diffusion models have recently been proposed to synthesize entire graphs, such as molecule graphs. Although existing methods have shown great performance in generating entire graphs for graph-level learning tasks, no graph diffusion models have been developed to generate synthetic graph structures, that is, synthetic nodes and associated edges within a given graph, for node-level learning tasks. Inspired by the research in the computer vision literature using synthetic data for enhanced performance, we propose Diffusion on Graph (DoG), which generates synthetic graph structures to boost the performance of GNNs. The synthetic graph structures generated by DoG are combined with the original graph to form an augmented graph for the training of node-level learning tasks, such as node classification and graph contrastive learning (GCL). To improve the efficiency of the generation process, a Bi-Level Neighbor Map Decoder (BLND) is introduced in DoG. To mitigate the adverse effect of the noise introduced by the synthetic graph structures, a low-rank regularization method is proposed for the training of graph neural networks (GNNs) on the augmented graphs. Extensive experiments on various graph datasets for semi-supervised node classification and graph contrastive learning have been conducted to demonstrate the effectiveness of DoG with low-rank regularization. The code of DoG is available at https://***/Statistical-Deep-Learning/DoG. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Generating Customized Prompts for Zero-Shot Rare Event Medical Image Classification Using LLM

Generating Customized Prompts for Zero-Shot Rare Event Medic...

引用

IEEE International Symposium on Biomedical Imaging

作者： Payal Kamboj Ayan Banerjee Bin Xu Sandeep Gupta School of Computing and Augmented Intelligence Arizona State University Tempe USA

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Rare events, due to their infrequent occurrences, do not have much data, and hence deep learning techniques fail in estimating the distribution for such data. Open-vocabulary models represent an innovative approach to image classification. Unlike traditional models, these models classify images into any set of categories specified with natural language prompts during inference. These prompts usually comprise manually crafted templates (e.g., 'a photo of a {}‘) that are filled in with the names of each category. This paper introduces a simple yet effective method for generating highly accurate and contextually descriptive prompts containing discriminative characteristics. Rare event detection, especially in medicine, is more challenging due to low inter-class and high intra-class variability. To address these, we propose a novel approach that uses domain-specific expert knowledge on rare events to generate customized and contextually relevant prompts, which are then used by large language models for image classification. Our zero-shot, privacy-preserving method enhances rare event classification without additional training, outperforming state-of-the-art techniques. Code available at https://***/payalkamboj/CuPKL.

关键词： Training Ethics Accuracy Zero shot learning Natural languages Medical services Medical diagnostic imaging Standards Image classification Testing

来源：评论

学校读者我要写书评

暂无评论

OntoKGen: A Genuine Ontology and Knowledge Graph Generator Using Large Language Model

OntoKGen: A Genuine Ontology and Knowledge Graph Generator U...

引用

Annual Symposium on Reliability and Maintainability (RAMS)

作者： Mohammad Sadeq Abolhasani Rong Pan School of Computing and Augmented Intelligence Arizona State University Tempe AZ

ISBN: (数字)9798350367744

ISBN: (纸本)9798350367751

Extracting relevant and structured knowledge from large, complex technical documents within the Reliability and Maintainability (RAM) domain is labor-intensive and prone to errors. Our work addresses this challenge by presenting OntoKGen, a Genuine pipeline for Ontology extraction and Knowledge Graph (KG) generation. OntoKGen leverages Large Language Models (LLMs) through an interactive user interface guided by our adaptive iterative Chain of Thought (CoT) algorithm to ensure that the ontology extraction process and, thus, KG generation align with user-specific requirements. Although KG generation follows a clear, structured path based on the confirmed ontology, there is no universally correct ontology as it is inherently based on the user's preferences. OntoKGen recommends an ontology grounded in best practices, minimizing user effort and providing valuable insights that may have been overlooked, all while giving the user complete control over the final ontology. Having generated the KG based on the confirmed ontology, OntoKGen enables seamless integration into schemeless, non-relational databases like Neo4j. This integration allows for flexible storage and retrieval of knowledge from diverse, unstructured sources, facilitating advanced querying, analysis, and decision-making. Moreover, the generated KG serves as a robust foundation for future integration into Retrieval-augmented Generation (RAG) systems, offering enhanced capabilities for developing domain-specific intelligent applications.

关键词： Large language models Retrieval augmented generation Pipelines Random access memory Knowledge graphs Ontologies User interfaces Reliability engineering Generators Prompt engineering

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：