Artificial Intelligence最新文献

Mitigating Data Reconstruction Attacks in Federated Learning: Conditions, Bounds, and Theoretical Guarantees 减轻联邦学习中的数据重构攻击：条件、界限和理论保证

IF 14.4 2区计算机科学

Artificial Intelligence Pub Date : 2026-10-01 DOI: 10.1016/j.artint.2026.104641

Xiaojin Zhang,Mingcong Xu,Wei Chen,Qiang Yang

引用次数: 0

ITEACH-Net: Inverted Teacher-studEnt seArCH Network for Emotion Recognition in Conversation 面向会话情感识别的逆向师生搜索网络

IF 14.4 2区计算机科学

Artificial Intelligence Pub Date : 2026-10-01 DOI: 10.1016/j.artint.2026.104643

Haiyang Sun,Zheng Lian,Chenglong Wang,Kang Chen,Licai Sun,Bin Liu,Jianhua Tao

引用次数: 0

Shapley Value Computation in Ontology-Mediated Query Answering 本体中介查询应答中的Shapley值计算

IF 14.4 2区计算机科学

Artificial Intelligence Pub Date : 2026-09-01 DOI: 10.1016/j.artint.2026.104619

Meghyn Bienvenu,Diego Figueira,Pierre Lafourcade

引用次数: 0

Predictable artificial intelligence 可预测的人工智能

IF 4.6 2区计算机科学

Artificial Intelligence Pub Date : 2026-04-01 Epub Date: 2026-01-30 DOI: 10.1016/j.artint.2026.104491

Lexin Zhou , Pablo A.M. Casares , Fernando Martínez-Plumed , John Burden , Ryan Burnell , Lucy Cheke , Cèsar Ferri , Alexandru Marcoci , Behzad Mehrbakhsh , Yael Moros-Daval , Seán Ó hÉigeartaigh , Danaja Rutar , Wout Schellaert , Konstantinos Voudouris , José Hernández-Orallo

引用次数: 0

One mind, many tongues: A deep dive into language-agnostic knowledge neurons in large language models 一个头脑，多种语言：深入研究大型语言模型中与语言无关的知识神经元

IF 4.6 2区计算机科学

Artificial Intelligence Pub Date : 2026-04-01 Epub Date: 2026-02-04 DOI: 10.1016/j.artint.2026.104490

Pengfei Cao , Yuheng Chen , Zhuoran Jin , Yubo Chen , Kang Liu , Jun Zhao

{"title":"One mind, many tongues: A deep dive into language-agnostic knowledge neurons in large language models","authors":"Pengfei Cao , Yuheng Chen , Zhuoran Jin , Yubo Chen , Kang Liu , Jun Zhao","doi":"10.1016/j.artint.2026.104490","DOIUrl":"10.1016/j.artint.2026.104490","url":null,"abstract":"<div><div>Large language models (LLMs) have learned vast amounts of factual knowledge through self-supervised pre-training on large-scale corpora. Meanwhile, LLMs have also demonstrated excellent multilingual capabilities, which can express the learned knowledge in multiple languages. However, the knowledge storage mechanism in LLMs still remains mysterious. Some researchers attempt to demystify the factual knowledge in LLMs from the perspective of knowledge neurons, and subsequently discover <em>language-agnostic knowledge neurons</em> that store factual knowledge in a form that transcends language barriers. However, the preliminary finding suffers from two limitations: 1) <em>High Uncertainty in Localization Results</em>. Existing study only uses a prompt-based probe to localize knowledge neurons for each fact, while LLMs cannot provide consistent answers for semantically equivalent queries. Thus, it leads to inaccurate localization results with high uncertainty. 2) <em>Lack of Analysis in More Languages</em>. The study only analyzes language-agnostic knowledge neurons on English and Chinese data, without exploring more language families and languages. Naturally, it limits the generalizability of the findings. To address aforementioned problems, we first construct a new benchmark called Rephrased Multilingual LAMA (<span>RML-LAMA</span>), which contains high-quality cloze-style multilingual parallel queries for each fact. Then, we propose a novel method named <em>Multilingual Integrated Gradients with Uncertainty Estimation</em> (<span>MaTrice</span>), which quantifies the uncertainty across queries and languages during knowledge localization. Extensive experiments show that our method can accurately localize language-agnostic knowledge neurons. We also further investigate the role of language-agnostic knowledge neurons in cross-lingual knowledge editing, knowledge enhancement and new knowledge injection.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"353 ","pages":"Article 104490"},"PeriodicalIF":4.6,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146135117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Defining defense and defeat in abstract argumentation from scratch – A generalizing approach 在抽象论证中从零开始定义辩护和失败——一种一般化的方法

IF 4.6 2区计算机科学

Artificial Intelligence Pub Date : 2026-03-01 Epub Date: 2025-12-05 DOI: 10.1016/j.artint.2025.104456

Lydia Blümel , Markus Ulbricht

{"title":"Defining defense and defeat in abstract argumentation from scratch – A generalizing approach","authors":"Lydia Blümel , Markus Ulbricht","doi":"10.1016/j.artint.2025.104456","DOIUrl":"10.1016/j.artint.2025.104456","url":null,"abstract":"<div><div>We propose a general framework to investigate semantics of Dung-style argumentation frameworks (AFs) by means of a generic defeat notion formalized by <em>refute operators</em>.The main idea underlying our approach is that, given a refute operator <em>δ</em>, counter-parts to all classical semantics can be deduced in a natural way. We demonstrate how classical as well as recent proposals can be captured by our approach when utilizing suitable refute operators. In addition, we showcase how our general scheme can be employed to propose novel semantics in a systematic manner. This results in what we call <em>cooperative semantics</em> which stem from a novel refute operator we will introduce. We perform an in-depth investigation of basic properties of refute operators and to which extent the induced semantics inherit desirable properties from it. Among others, we show under which conditions i) a counterpart to Dung’s fundamental lemma can be inferred, ii) the generalized version of the grounded extension is unique, or iii) the generalized version of stable semantics does not collapse. Moreover, we contribute to a principle-based study of AF semantics by discussing properties tailored to assess the behavior of different refute operators. This includes an investigation of means to compare refute operators in terms of their aggressiveness. Finally, we conclude the study by reporting computational complexity results for basic reasoning tasks which hold in our general framework.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"352 ","pages":"Article 104456"},"PeriodicalIF":4.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145689754","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Automated planning instance generation with neuro-symbolic AI 使用神经符号AI自动规划实例生成

IF 4.6 2区计算机科学

Artificial Intelligence Pub Date : 2026-03-01 Epub Date: 2025-12-28 DOI: 10.1016/j.artint.2025.104471

Carlos Núñez-Molina , Pablo Mesejo , Juan Fernández-Olivares

{"title":"Automated planning instance generation with neuro-symbolic AI","authors":"Carlos Núñez-Molina , Pablo Mesejo , Juan Fernández-Olivares","doi":"10.1016/j.artint.2025.104471","DOIUrl":"10.1016/j.artint.2025.104471","url":null,"abstract":"<div><div>In the field of Automated Planning there is often the need for a set of planning problems from a particular domain, e.g., to be used as training data for Machine Learning methods or as benchmarks in planning competitions. In most cases, these problems are created either by hand or by a domain-specific generator, putting a burden on the human designers. In this paper, we propose NeSIG (<em>Neuro-Symbolic Instance Generator</em>), to the best of our knowledge the first domain-independent method for automatically generating typed-STRIPS planning problems that are valid, diverse and difficult to solve. We formulate problem generation as a Markov Decision Process and train two generative policies with Deep Reinforcement Learning to generate problems with the desired properties. We conduct experiments on five classical domains, comparing our approach against handcrafted, domain-specific instance generators and various ablations. Results show NeSIG is able to automatically generate valid and diverse problems of much greater difficulty (6.8 times more on geometric average) than domain-specific generators, while simultaneously reducing human effort when compared to them. Additionally, it can generalize to problems more than twice the size of those seen during training.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"352 ","pages":"Article 104471"},"PeriodicalIF":4.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145845507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-scale signal modulation for variational graph autoencoders 变分图自编码器的多尺度信号调制

IF 4.6 2区计算机科学

Artificial Intelligence Pub Date : 2026-03-01 Epub Date: 2026-01-15 DOI: 10.1016/j.artint.2026.104488

Junwei Cheng , Chaobo He , Pengxing Feng , Weixiong Liu , Ke Liang

{"title":"Multi-scale signal modulation for variational graph autoencoders","authors":"Junwei Cheng , Chaobo He , Pengxing Feng , Weixiong Liu , Ke Liang","doi":"10.1016/j.artint.2026.104488","DOIUrl":"10.1016/j.artint.2026.104488","url":null,"abstract":"<div><div>Variational graph autoencoder (VGAE) has emerged as a prominent framework for graph representation learning, owing to its probabilistic modeling flexibility and expressive power. Most existing VGAE-based methods assume that the posterior distribution of node embeddings follows a Gaussian distribution and rely on graph convolutional networks with low-pass filtering properties to infer the posterior mean and variance. However, our empirical findings reveal that the variance exhibits non-stationary spectral characteristics, indicating a spectral mismatch between the variance signal and the low-pass nature of conventional inference mechanisms. Further analysis reveals a spectral asymmetry between the posterior mean and variance, as they exhibit distinct signal allocations within the node embeddings. Motivated by these insights, we propose MS-VGAE, a novel variational graph autoencoder with multi-scale signal modulation. Specifically, MS-VGAE leverages a Gabor-based wavelet network to perform fine-grained spectral convolution and signal modulation of the posterior variance across multiple frequency scales. Additionally, a compact optimization objective is derived to enable homophily-aware modulation of frequency-band contributions in the variance. To reduce the computational overhead, we develop MS-VGAE<sub><em>cheby</em></sub>, which replaces the spectral filtering operation in MS-VGAE with a Chebyshev polynomial approximation. Comprehensive experiments results demonstrate that MS-VGAE achieves satisfactory performance on both node clustering and link prediction tasks. Moreover, MS-VGAE<sub><em>cheby</em></sub> offers an efficient alternative to MS-VGAE, while maintaining comparable performance on large graphs. The code is available at <span><span>https://github.com/GDM-SCNU/MS-VGAE</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"352 ","pages":"Article 104488"},"PeriodicalIF":4.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145995524","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SHACL validation in the presence of ontologies: Semantics and rewriting techniques 存在本体的SHACL验证：语义和重写技术

IF 4.6 2区计算机科学

Artificial Intelligence Pub Date : 2026-03-01 Epub Date: 2026-01-13 DOI: 10.1016/j.artint.2026.104483

Anouk Oudshoorn, Magdalena Ortiz, Mantas Šimkus

{"title":"SHACL validation in the presence of ontologies: Semantics and rewriting techniques","authors":"Anouk Oudshoorn, Magdalena Ortiz, Mantas Šimkus","doi":"10.1016/j.artint.2026.104483","DOIUrl":"10.1016/j.artint.2026.104483","url":null,"abstract":"<div><div>SHACL and OWL are two prominent W3C standards for managing RDF data. These languages share many features, but they have one fundamental difference: OWL, designed for inferring facts from incomplete data, makes the <em>open-world assumption</em>, whereas SHACL is a constraint language that treats the data as complete and must be validated under the <em>closed-world assumption</em>. The combination of both formalisms is very appealing and has been called for, but their semantic gap is a major challenge, semantically and computationally. In this paper, we advocate a semantics for SHACL validation in the presence of ontologies based on <em>core universal models</em>. We provide a technique for constructing these models for ontologies in the rich data-tractable description logic Horn-<span><math><mi>ALCHIQ</mi></math></span>. Furthermore, we use a finite representation of this model to develop a <em>rewriting technique</em> that reduces SHACL validation in the presence of ontologies to standard validation. Finally, we study the complexity of SHACL validation in the presence of ontologies, and show that even very simple ontologies make the problem <span>ExpTime</span>-complete, and <span>PTime</span>-complete in data complexity.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"352 ","pages":"Article 104483"},"PeriodicalIF":4.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145962643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

LAD2025, A constraint-based solver for the subgraph isomorphism problem 基于约束的子图同构问题求解器LAD2025

IF 4.6 2区计算机科学

Artificial Intelligence Pub Date : 2026-03-01 Epub Date: 2025-12-25 DOI: 10.1016/j.artint.2025.104474

Christine Solnon

引用次数: 0