SAT-Based PAC Learning of Description Logic Concepts
ILLC, University of Amsterdam（阿姆斯特丹大学语言、逻辑与计算研究所）；Leipzig University（莱比锡大学）；Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI)（可扩展数据分析与人工智能中心（ScaDS.AI））；TU Dortmund University（多特蒙德工业大学）
Balder ten Cate, Maurice Funk, Jean Christoph Jung, Carsten Lutz
备注：
19 pages, Long version of paper accepted at IJCAI 2023
We propose bounded fitting as a scheme for learning description logic concepts in the presence of ontologies. A main advantage is that the resulting learning algorithms come with theoretical guarantees regarding their generalization to unseen examples in the sense of PAC learning. We prove that, in contrast, several other natural learning algorithms fail to provide such guarantees. As a further contribution, we present the system SPELL which efficiently implements bounded fitting for the description logic $\mathcal{ELH}^r$ based on a SAT solver, and compare its performance to a state-of-the-art learner.
Unicast and Multicast Qos Routing with Soft Constraint Logic Programming
Università di Chieti-Pescara（基耶蒂-佩斯卡拉大学）；Institute for Informatics and Telematics（信息学与电信学研究所）；Università di Pisa（比萨大学）；Università di Padova（帕多瓦大学）；IMT - Institute for Advanced Studies（IMT高等研究院）
Università di Udine（乌迪内大学）；GNCS-INdAM（意大利国家高等数学研究院-国家科学计算小组）；University of Texas at Dallas（德克萨斯大学达拉斯分校）；IMDEA Software Institute（IMDEA 软件研究所）；Universidad Politécnica de Madrid（马德里理工大学）；New Mexico State University（新墨西哥州立大学）；CRACS/INESC TEC（CRACS/INESC TEC 研究所）；University of Porto（波尔图大学）
