In spite of the recent improvements in the performance of the solvers based on the DPLL procedure, it is still possible for the search algorithm to focus on the wrong areas of the search space, preventing the solver from returning a solution in an acceptable amount of time. This prospect is a real concern e.g. in an industrial setting, where users typically expect consistent performance. To overcome this problem, we propose a framework that allows learning and using domain-specific heuristics in solvers based on the DPLL procedure. The learning is done off-line, on representative instances from the target domain, and the learned heuristics are then used for choice-point selection. In this paper we focus on Answer Set Programming (ASP) solvers. In our experiments, the introduction of domain-specific heuristics improved performance on hard instances by up to 3 orders of magnitude (and 2 on average), nearly completely eliminating the cases in which the solver had to be terminated because the wait for an answer had become unacceptable.
Optimizing Answer Set Computation via Heuristic-Based Decomposition
Department of Mathematics and Computer Science University of Calabria（卡利亚里大学数学与计算机科学系）；University of Calabria（卡利亚里大学）；Department of Mathematics and Computer Science（数学与计算机科学系）；Rende Italy（伦代（意大利）（注：此为地址信息，非机构，不应提取，原提取有误，正确应为仅提取前两个有效机构相关部分，但按文本结构准确提取应为“Department of Mathematics and Computer Science University of Calabria”））
Train Scheduling with Hybrid Answer Set Programming
SBB Switzerland（瑞士联邦铁路）；Potassco Solutions Germany（德国Potassco解决方案公司）；Simon Fraser University（西蒙弗雷泽大学）；Griffith University（格里菲斯大学）；University of Potsdam（波茨坦大学）
提出了一种基于回答集编程（ASP）的训练调度问题的解决方案。为此，我们追求一种混合的方法，扩展ASP与不同的约束，以考虑细粒度的时间。更确切地说，我们举例说明如何混合ASP系统clingo[DL]可以用来解决苛刻的计划和调度问题。特别是，我们研究了如何提高性能相结合的不同ASP解决技术，如近似和算法，预处理和编码技术，以解决大规模的，现实世界的训练调度实例。逻辑程序设计理论与实践（Theory and Practice of Logic Programming，TPLP）
Politecnico di Torino（都灵理工大学）；Institut de Physique Theorique, IPhT, CEA Saclay（法国原子能委员会萨克雷核研究中心理论物理研究所（IPhT））；URA 2306, CNRS（法国国家科学研究中心 URA 2306 联合研究单位）
Revisiting the Training of Logic Models of Protein Signaling Networks with a Formal Approach based on Answer Set Programming
CNRS（法国国家科学研究中心）；IRISA（法国信息与随机系统研究所）；INRIA（法国国家信息与自动化研究所）；National Center for Tumor Diseases（国家肿瘤疾病中心）；University of Padova（帕多瓦大学）；European Bioinformatics Institute (EMBL-EBI)（欧洲生物信息研究所（EMBL-EBI））；University of Potsdam（波茨坦大学）
Deep Learning: a Heuristic Three-stage Mechanism for Grid Searches to Optimize the Future Risk Prediction of Breast Cancer Metastasis Using EHR-based Clinical Data
University of Pittsburgh（匹兹堡大学）；Pittsburgh VA Health System（匹兹堡退伍军人健康系统）；University of Pittsburgh School of Medicine（匹兹堡大学医学院）；UPMC Hillman Cancer Center（UPMC希尔曼癌症中心）
