SLISEMAP: Supervised dimensionality reduction through local explanations
University of Helsinki（赫尔辛基大学）
Anton Björklund, Jarmo Mäkelä, Kai Puolamäki
备注：
26 pages, 10 figures, 3 tables. This revision replaces the $λ_z$ parameter with $z_{radius}$, which is more intuitive and stable. There are also many typographical and clarity improvements. The source code for our implementation of the algorithm (and the experiments) are available from GitHub at https://github.com/edahelsinki/slisemap . Machine Learning (2022)
Existing methods for explaining black box learning models often focus on building local explanations of model behaviour for a particular data item. It is possible to create global explanations for all data items, but these explanations generally have low fidelity for complex black box models. We propose a new supervised manifold visualisation method, SLISEMAP, that simultaneously finds local explanations for all data items and builds a (typically) two-dimensional global visualisation of the black box model such that data items with similar local explanations are projected nearby. We provide a mathematical derivation of our problem and an open source implementation implemented using the GPU-optimised PyTorch library. We compare SLISEMAP to multiple popular dimensionality reduction methods and find that SLISEMAP is able to utilise labelled data to create embeddings with consistent local white box models. We also compare SLISEMAP to other model-agnostic local explanation methods and show that SLISEMAP provides comparable explanations and that the visualisations can give a broader understanding of black box regression and classification models.
Comparing Explanation Methods for Traditional Machine Learning Models Part 2: Quantifying Model Explainability Faithfulness and Improvements with Dimensionality Reduction
Cooperative Institute for Severe and High-Impact Weather Research and Operations, University of Oklahoma（俄克拉荷马大学强天气与高影响天气合作研究所）；University of Oklahoma（俄克拉荷马大学）；NOAA/OAR/National Severe Storms Laboratory（美国国家海洋和大气管理局/海洋与大气研究办公室/国家强风暴实验室）；Verisk Analytics Incorporated（Verisk分析公司）；NSF AI Institute for Research on Trustworthy AI in Weather, Climate, and Coastal Oceanography（美国国家科学基金会天气、气候与沿海海洋学可信人工智能研究人工智能研究所）
SHAPCA: Consistent and Interpretable Explanations for Machine Learning Models on Spectroscopy Data
School of Computer Science and Information Technology（计算机科学与信息技术学院）；Centre for Research Training in Artificial Intelligence（人工智能研究培训中心）；Insight Centre for Data Analytics（数据分析洞察中心）
Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis
Carney Institute for Brain Science, Brown University（布朗大学卡尼脑科学研究所）；Artificial and Natural Intelligence Toulouse Institute, Université de Toulouse（图卢兹大学图卢兹人工与自然智能研究所）；Institut de Recherche Technologique Saint-Exupery（圣埃克苏佩里技术研究所）；Sorbonne Université, CNRS（索邦大学、法国国家科学研究中心）
Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality
The University of Melbourne（墨尔本大学）；University of California, Berkeley（加利福尼亚大学伯克利分校）；Tsinghua University（清华大学）；University of Michigan（密歇根大学）；National Institute of Informatics（国立信息学研究所）
Surprisingly High Redundancy in Electronic Structure Data Across Materials Explained by Low Intrinsic Dimensionality
Department of Mechanical and Aerospace Engineering, Michigan Technological University, Houghton, MI, USA.（机械与航空航天工程系，密歇根技术大学，霍顿，MI，美国）；Hopkins Extreme Materials Institute, Johns Hopkins University, Baltimore, MD, USA.（霍普金斯极端材料研究所，约翰霍普金斯大学，巴尔的摩，MD，美国）；Department of Materials Science and Engineering, University of California, Los Angeles, CA, USA.（材料科学与工程系，加州大学洛杉矶分校，CA，美国）；Center for Artificial Intelligence, Michigan Technological University, Houghton, MI, USA.（人工智能中心，密歇根技术大学，霍顿，MI，美国）
