Model Interpretation aims at the extraction of insights from the internals of a trained model. A common approach to address this task is the characterization of relevant features internally encoded in the model that are critical for its proper operation. Despite recent progress of these methods, they come with the weakness of being computationally expensive due to the dense evaluation of datasets that they require. As a consequence, research on the design of these methods have focused on smaller data subsets which may led to reduced insights. To address these computational costs, we propose a coreset-based interpretation framework that utilizes coreset selection methods to sample a representative subset of the large dataset for the interpretation task. Towards this goal, we propose a similarity-based evaluation protocol to assess the robustness of model interpretation methods towards the amount data they take as input. Experiments considering several interpretation methods, DNN models, and coreset selection methods show the effectiveness of the proposed framework.
GraphSculptor: Sculpting Pre-training Coreset for Graph Self-supervised Learning
Sangfor Technologies Inc.（Sangfor 技术公司）；Wuhan University（武汉大学）；The University of Melbourne（墨尔本大学）；Dalian Maritime University（大连海事大学）；Hunan University of Technology and Business（湖南工业大学；湘江实验室）；Xiangjiang Laboratory
Scalable Learning of Multivariate Distributions via Coresets
Lamarr Institute for ML & AI, TU Dortmund（拉马尔人工智能与机器学习研究所，多特蒙德技术大学）；Scientific Computing Center, Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院科学计算中心）；Department of Statistics, TU Dortmund（多特蒙德技术大学统计学系）
Efficient Neural Architectures for Real-Time ECG Interpretation on Limited Hardware
Department of Computer Science（计算机科学系）；University of Victoria（维多利亚大学）；Department of Electrical and Computer Engineering（电气与计算机工程系）；University of British Columbia（不列颠哥伦比亚大学）；Faculty of Medicine（医学院）；School of Biomedical Engineering（生物医学工程学院）；Division of Cardiology（心内科）；Department of Radiology（放射科）；Department of Emergency Medicine（急诊医学科）
Robust Semi-Supervised CT Radiomics for Lung Cancer Prognosis: Cost-Effective Learning with Limited Labels and SHAP Interpretation
University of British Columbia（不列颠哥伦比亚大学）；BC Cancer Research Institute（BC癌症研究所）；TECVICO Corp.（TECVICO公司）；Amirkabir University of Technology（阿米尔卡比尔理工大学）；Nooshirvani University of Technology（努什拉尼理工大学）；Guilan University of Medical Sciences（吉兰医科大学）；Motamed Cancer Institute（莫塔梅德癌症研究所）；Hamadan University of Medical Sciences（哈马丹医科大学）
Learning to Limit Data Collection via Scaling Laws: A Computational Interpretation for the Legal Principle of Data Minimization
Massachusetts Institute of Technology（麻省理工学院）；Microsoft Research（微软研究院）；University of Tübingen（图宾根大学）；Max Planck Institute for Security and Privacy（马克斯·普朗克安全与隐私研究所）
Multimodal Deep Learning for Scientific Imaging Interpretation
Science and Technology Division, Corning Incorporated（康宁公司科技事业部）；Robert Frederick Smith School of Chemical and Biomolecular Engineering, Cornell University（康奈尔大学罗伯特·弗雷德里克·史密斯化学与生物分子工程学院）
本文提出多模态深度学习框架 GlassLLaVA，结合论文图文数据与 GPT-4，实现玻璃材料 SEM 图像的类人解释、特征识别和缺陷检测，并建立可对照研究答案的评估指标。
