Beyond Distribution Estimation: Simplex Anchored Structural Inference Towards Universal Semi-Supervised Learning
超越分布估计:基于简单集锚定的结构推断以实现通用半监督学习
机构 * Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing, China(新一代人工智能技术及其交叉应用重点实验室(东南大学),教育部,南京,中国) ; School of Computer Science and Engineering, Southeast University, Nanjing, China(计算机科学与工程学院,东南大学,南京,中国) ; School of Electrical Engineering, Southeast University, Nanjing, China(电气工程学院,东南大学,南京,中国)
AI总结 本文提出SAGE方法,通过在表示层面进行结构推断,避免分布估计,利用简单集锚定框架提升半监督学习性能,实验表明其在五个基准数据集上平均准确率提升8.52%。
Comments The paper is accepted by ICML 2026