Submodular functions and variants, through their ability to characterize diversity and coverage, have emerged as a key tool for data selection and summarization. Many recent approaches to learn submodular functions suffer from limited expressiveness. In this work, we propose FLEXSUBNET, a family of flexible neural models for both monotone and non-monotone submodular functions. To fit a latent submodular function from (set, value) observations, FLEXSUBNET applies a concave function on modular functions in a recursive manner. We do not draw the concave function from a restricted family, but rather learn from data using a highly expressive neural network that implements a differentiable quadrature procedure. Such an expressive neural model for concave functions may be of independent interest. Next, we extend this setup to provide a novel characterization of monotone α-submodular functions, a recently introduced notion of approximate submodular functions. We then use this characterization to design a novel neural model for such functions. Finally, we consider learning submodular set functions under distant supervision in the form of (perimeter-set, high-value-subset) pairs. This yields a novel subset selection method based on an order-invariant, yet greedy sampler built around the above neural set functions. Our experiments on synthetic and real data show that FLEXSUBNET outperforms several baselines.
英文摘要:
Submodular functions and variants, through their ability to characterize diversity and coverage, have emerged as a key tool for data selection and summarization. Many recent approaches to learn submodular functions suffer from limited expressiveness. In this work, we propose FLEXSUBNET, a family of flexible neural models for both monotone and non-monotone submodular functions. To fit a latent submodular function from (set, value) observations, FLEXSUBNET applies a concave function on modular functions in a recursive manner. We do not draw the concave function from a restricted family, but rather learn from data using a highly expressive neural network that implements a differentiable quadrature procedure. Such an expressive neural model for concave functions may be of independent interest. Next, we extend this setup to provide a novel characterization of monotone α-submodular functions, a recently introduced notion of approximate submodular functions. We then use this characterization to design a novel neural model for such functions. Finally, we consider learning submodular set functions under distant supervision in the form of (perimeter-set, high-value-subset) pairs. This yields a novel subset selection method based on an order-invariant, yet greedy sampler built around the above neural set functions. Our experiments on synthetic and real data show that FLEXSUBNET outperforms several baselines.
Less is More: Fewer Interpretable Region via Submodular Subset Selection
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络安全学院);School of Computing, National University of Singapore(新加坡国立大学计算机学院);School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University(中山大学深圳校区网络空间安全学院)
UniPROT: Uniform Prototype Selection via Partial Optimal Transport with Submodular Guarantees
Department of Computer Science and Engineering, Indian Institute of Technology Bombay(印度理工学院孟买分校计算机科学与工程系);Centre for Machine Intelligence and Data Science, Indian Institute of Technology Bombay(印度理工学院孟买分校机器智能与数据科学中心);Microsoft Research India(微软研究院印度);Walmart Global Tech, India(沃尔玛全球技术印度);Microsoft India(微软印度)
City University of Hong Kong(香港城市大学);University of Nebraska-Lincoln(内布拉斯加大学林肯分校);King’s College London(伦敦国王学院);City University of Hong Kong Shenzhen Research Institute(香港城市大学深圳研究院)
Multinoulli Extension: A Lossless Continuous Relaxation for Partition-Constrained Subset Selection
college of computing and data science, Nanyang Technological University, Singapore(南洋理工大学计算与数据科学学院,新加坡);Hong Kong University of Science and Technology(香港科学大学)
An efficient branch-and-bound algorithm for submodular function maximization
RIKEN Center for Advanced Intelligence Project(理化学研究所先进智能项目中心);Graduate School of Information Science and Technology, Osaka University(大阪大学信息科学与技术研究生院);The Institute of Scientific and Industrial Research, Osaka University(大阪大学科学与工业研究所)
Redundancy Meets Synergy: Dependency-aware Expert Selection for MoE via Submodular Optimization
Interdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg(卢森堡大学安全、可靠性与信任跨学科中心);Department of Computer Science, Peking University(北京大学计算机科学系);Institute of Space Internet, Fudan University(复旦大学空间互联网研究院);Department of Electrical and Computer Engineering, The University of British Columbia(不列颠哥伦比亚大学电气与计算机工程系);Department of Computer Science, City University of Hong Kong(香港城市大学计算机科学系);School of Engineering, Edith Cowan University(埃迪斯科文大学工程学院);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院)
Sub-SA: Strengthen In-context Learning via Submodular Selective Annotation
School of Electrical and Electronic Engineering, Nanyang Technological University(南洋理工大学电气与电子工程学院);School of Automation, Southeast University(东南大学自动化学院);State Key Laboratory of ASIC and System, Fudan University(复旦大学专用集成电路与系统国家重点实验室)
Quantum and Classical Algorithms for Approximate Submodular Function Minimization
Université de Paris(巴黎大学);IRIF(法国信息与自动化研究所(IRIF));CNRS(法国国家科学研究中心);Centre for Quantum Technologies, National University of Singapore(新加坡国立大学量子技术中心);National University of Singapore(新加坡国立大学);MajuLab UMI 3654(MajuLab国际联合实验室(UMI 3654))