.png){kind=icon}
返回
SLISEMAP: supervised dimensionality reduction through local explanations
.png){kind=icon}
OA
AI
DOI：10.1007/s10994-022-06261-1.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Existing methods for explaining black box learning models often focus on building local explanations of the models' behaviour for particular data items. 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.
Keyword:
Manifold visualisation
Explainable AI
Local approximation
期刊
IF:
2.9
论文数:
2.7K
被引数:
3.4W
机构
引用论文
Awareness of activity limitations, goal setting and rehabilitation outcome in patients with brain injuries.png)
Brain Injury
Brain InjuryIF0
PREAI
分享收藏分享收藏Searching for exotic particles in high-energy physics with deep learning用深度学习寻找高能物理中的奇异粒子NATURE COMMUNICATIONS
NATURE COMMUNICATIONSIF15.7
PREAI
分享收藏分享收藏
Cell-free Protein Synthesis in an Autoinduction System for NMR Studies of Protein–Protein Interactions用于NMR研究蛋白质-蛋白质相互作用的自动诱导系统中的无细胞蛋白质合成
PREAI
分享收藏分享收藏
查看更多内容