软件学院分论坛

讲座主题：关系型数据上的机器学习

主讲嘉宾：王彧弋

讲座时间：2018年11月23日上午10:00

讲座地点：沙河校区主楼中213室

王彧弋，博士，苏黎世联邦理工大学（ETH Zurich）信息技术与电气工程学院、计算机学院博士后研究员。研究方向是算法理论和机器学习，发表了30余篇学术论文，并且在FOCS，AAAI，IJCAI，UAI，FC和WINE等顶级学术会议做报告。算法理论方面目前主要关注分布式计算、网络科学以及区块链。2018年连续发表论文探讨了与区块链相关的诸多问题：1）Byzantine问题的扩展，2）Micropayment Channel设计的费用问题，3）Micropayment Channel设计的信用问题，4）基于Sleep模型的安全证明，5）Cross-chain问题和6）Watchtower在Channel中的应用等等。机器学习方面则更注重统计学习理论，尤其是关系型数据（非iid）上的学习理论。2018年也有多篇论文发表在AAAI，UAI和ECMLPKDD上。他还主持并参与了多项研究和工程项目：主持的研究项目有例如比利时FWO支持的“基于统计理论的图数据挖掘”和青年自然科学基金支持的“集中不等式理论及应用”。

内容摘要

In the propositional setting, the marginal problem is to find a (maximum-entropy) distribution that has some given marginals. We study this problem in a relational setting and make the following contributions. First, we compare two different notions of relational marginals. Second, we show a duality between the resulting relational marginal problems and the maximum likelihood estimation of the parameters of relational models, which generalizes a well-known duality from the propositional setting. Third, by exploiting the relational marginal formulation, we present a statistically sound method to learn the parameters of relational models that will be applied in settings where the number of constants differs between the training and test data. Furthermore, based on a relational generalization of marginal polytopes, we characterize cases where the standard estimators based on feature’s number of true groundings needs to be adjusted and we quantitatively characterize the consequences of these adjustments. Fourth, we prove bounds on expected errors of the estimated parameters, which allows us to lower-bound, among other things, the effective sample size of relational training data.

主办单位：信息与软件工程学院

承办单位：可信云计算与大数据工程实验室研究生党支部、网络空间安全实验室研究生党支部、数字信息系统实验室研究生党支部

编辑：王桂石

出品：软件学院学生发展指导中心

大学有问 大有学问