题    目：Data organization limits the predictability of binary classification

主讲人：张子柯 教授

单    位：浙江大学

时    间：2025年5月24日 9:00

地    点：学院南阶教室

摘    要：The structure of data organization is widely recognized as having a substantial influence on the efficacy of machine learning algorithms, particularly in binary classification tasks. Our research provides a theoretical framework suggesting that the maximum potential of binary classifiers on a given dataset is primarily constrained by the inherent qualities of the data. Through both theoretical reasoning and empirical examination, we employed standard objective functions, evaluative metrics, and binary classifiers to arrive at two principal conclusions. Firstly, we show that the theoretical upper bound of binary classification performance on actual datasets can be theoretically attained. This upper boundary represents a calculable equilibrium between the learning loss and the metric of evaluation. Secondly, we have computed the precise upper bounds for three commonly used evaluation metrics, uncovering a fundamental uniformity with our overarching thesis: the upper bound is intricately linked to the dataset's characteristics, independent of the classifier in use. Additionally, our subsequent analysis uncovers a detailed relationship between the upper limit of performance and the level of class overlap within the binary classification data. This relationship is instrumental for pinpointing the most effective feature subsets for use in feature engineering. This work is generally has potential applications in data driven researches to quantitatively evaluate the dilemma of promoting algorithm performance and improving data quality.

简    介：张子柯，教授，博士生导师，浙江大学数字沟通研究中心副主任，浙江大学人工智能通识教育课程教材建设组副组长。主要研究兴趣为计算驱动的复杂社会系统。已正式发表期刊论文100余篇，引用6600余次，授权国家发明专利20项。主持国家自然科学基金3项，国家自然科学基金重大项目子课题，教育部人文社科重点研究基地重大项目子课题，欧盟第七科技框架、浙江省杰青等项目。荣获中国计算机协会自然科学二等奖、青海省自然科学三等奖、杭州市优秀学术成果一等奖等。近年来入选浙江省优秀教师、浙江省师德先进个人、浙江省中青年学科带头人、杭州市优秀教师、浙江省钱江人才计划等。兼任中国人工智能学会社会计算与社会智能专业委员会副主任、复杂性科学研究会秘书长，中国新闻史学会智能与计算传播专委会常务理事等。