This work explores the novel idea of learning a submodular scoring function to improve the specificity/selectivity of existing feature attribution methods. Submodular scores are natural for attribution as they are known to accurately model the principle of diminishing returns. A new formulation for learning a deep submodular set function that is consistent with the real-valued attribution maps obtained by existing attribution methods is proposed. The final attribution value of a feature is then defined as the marginal gain in the induced submodular score of the feature in the context of other highly attributed features, thus decreasing the attribution of redundant yet discriminatory features. Experiments on multiple datasets illustrate that the proposed attribution method achieves higher specificity along with good discriminative power. The implementation of our method is publicly available at https://github.com/Piyushi-0/SEA-NN.
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）
Improving Adversarial Robustness of Attribution via Implicit Regularization
Department of Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden（瑞典皇家理工学院计算机科学系）；Science for Life Laboratory, Stockholm, Sweden（瑞典斯德哥尔摩科学生命实验室）；Department of Computer Science, Brown University, USA（美国布朗大学计算机科学系）
Advancing climate model interpretability: Feature attribution for Arctic melt anomalies
Institute for Harnessing Data and Model Revolution in the Polar Regions（极地地区数据与模型利用研究所）；University of Maryland, Baltimore County（马里兰大学巴尔的摩分校）；National Oceanic and Atmospheric Administration（美国国家海洋和大气管理局）
Frequency-Aware Model Parameter Explorer: A new attribution method for improving explainability
Center for Medical Physics and Biomedical Engineering（医学物理与生物医学工程中心）；Medical University of Vienna（维也纳医科大学）；Dept. of Computer Engineering（计算机工程系）；Sharif University of Technology（沙菲公司技术大学）；MANO Group, CIR Lab, Dept. of Biomedical Imaging and Image-Guided Therapy（MANO集团、CIR实验室、生物医学成像与图像引导治疗系）；Comprehensive Center for AI in Medicine（医学人工智能综合中心）
Scalable Combinatorial Bayesian Optimization with Tractable Statistical models
Washington State University（华盛顿州立大学）
我们研究了在组合空间上优化昂贵的黑盒函数的问题（例如，集合、序列、树和图）。BOCS（Baptista和Poloczek，2018）是一种用于易处理统计模型的最先进的贝叶斯优化方法，它执行基于半定规划的获取函数优化（AFO）来选择下一个结构进行评估。不幸的是，BOCS规模不佳，大量的二进制和/或分类变量。基于求解二次规划的子模块松弛（Ito and Fujimaki，2016）的最新进展，我们研究了一种称为参数化子模块松弛（PSR）的方法，以提高求解BOCS模型AFO问题的可扩展性和准确性。PSR方法依赖于两个关键思想。首先，将AFO问题转化为带未知参数的次模松弛问题，利用最小图割算法可以有效地求解该问题。第二，构造一个优化问题来估计与真实目标非常接近的未知参数。在不同的基准问题上的实验表明，PSR对BOCS模型有显著的改进。源代码可在https://github.com/aryandeshwal/Submodular_Relaxation_BOCS上获得。
Department of Artificial Intelligence, Fraunhofer Heinrich Hertz Institute（人工智能系，弗劳恩霍夫海因里希·赫兹研究所）；Department of Electrical Engineering and Computer Science, Technische Universität Berlin（电气工程与计算机科学系，柏林技术大学）；BIFOLD - Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所）；Centre of eXplainable Artificial Intelligence, Technological University Dublin（可解释人工智能中心，都柏林技术大学）
Distributional Training Data Attribution: What do Influence Functions Sample?
University of Cambridge（剑桥大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Bristol（布里斯托大学）；Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Alan Turing Institute（艾伦·图灵研究所）
When New Generators Arrive: Lifelong Machine-Generated Text Attribution via Ridge Feature Transfer
Wuhan University（武汉大学）；Ant Group（蚂蚁集团）；The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；Institute of Deep Perception Technology, JITRI（感知技术研究院，JITRI）
