The DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.
Interpreting machine-learning models in transformed feature space with an application to remote-sensing classification
Abstract
Model-agnostic tools for the post-hoc interpretation of machine-learning models struggle to summarize the joint effects of strongly dependent features in high-dimensional feature spaces, which play an important role in semantic image classification, for example in remote sensing of landcover. This contribution proposes a novel approach that interprets machine-learning models through the lens of feature-space transformations. It can be used to enhance unconditional as well as conditional post-hoc diagnostic tools including partial-dependence plots, accumulated local effects (ALE) plots, permutation feature importance, or Shapley additive explanations (SHAP). While the approach can also be applied to nonlinear transformations, linear ones are particularly appealing, especially principal component analysis (PCA) and a proposed partial orthogonalization technique. Moreover, structured PCA and model diagnostics along user-defined synthetic features offer opportunities for representing domain knowledge. The new approach is implemented in the R package , which can be combined with existing explainable machine-learning packages. A case study on remote-sensing landcover classification with 46 features is used to demonstrate the potential of the proposed approach for model interpretation by domain experts. It is most useful in situations where groups of feature are linearly dependent and PCA can provide meaningful multivariate data summaries.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Greedy function approximation: A gradient boosting machine
Friedman, J. H. (2001) · The Annals of Statistics · doi:10.1214/aos/1013203451 · Cited by 30,731
Support vector machines in remote sensing: a review
Mountrakis, G., Im, J., & Ogole, C. (2011) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2010.11.001 · Cited by 3,473
Conditional variable importance for random forests
Strobl, C., Boulesteix, A.-L., Kneib, T., Augustin, T., & Zeileis, A. (2008) · BMC Bioinformatics · doi:10.1186/1471-2105-9-307 · Cited by 3,254
Definitions, methods, and applications in interpretable machine learning
Murdoch, W. J., Singh, C., Kumbier, K., Abbasi-Asl, R., & Yu, B. (2019) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1900654116 · Cited by 2,167 · cited 1×
“A common approach is the post-hoc analysis of black-box models for dataset-level interpretation (Murdoch et al. 2019) using model-agnostic techniques such as the permutation-based variable importance, and graphical displays such as partial dependence plots that visualize main effects while…”
MethodVisualizing the effects of predictor variables in black box supervised learning models
Apley, D. W., & Zhu, J. (2020) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/rssb.12377 · Cited by 1,535
pdp: An R Package for Constructing Partial Dependence Plots
Greenwell, B. (2017) · The R Journal · doi:10.32614/rj-2017-016 · Cited by 1,189
Hyperspectral image data analysis
Landgrebe, D. (2002) · IEEE Signal Processing Magazine · doi:10.1109/79.974718 · Cited by 1,152
iml: An R package for Interpretable Machine Learning
Molnar, C. (2018) · Journal of Open Source Software · doi:10.21105/joss.00786 · Cited by 718
Interpretable Machine Learning – A Brief History, State-of-the-Art and Challenges
Molnar, C., Casalicchio, G., & Bischl, B. (2020) · Communications in Computer and Information Science · doi:10.1007/978-3-030-65965-3_28 · Cited by 677
Sakar, C. O., Serbes, G., Gunduz, A., Tunc, H. C., Nizam, H., Sakar, B. E., Tutuncu, M., Aydin, T., Isenkul, M. E., & Apaydin, H. (2019) · Applied Soft Computing · doi:10.1016/j.asoc.2018.10.022 · Cited by 550
Linear Dimensionality Reduction: Survey, Insights, and Generalizations
Cunningham, J. P., & Ghahramani, Z. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1406.0873 · Cited by 357
Designing Gabor filters for optimal texture separability
Clausi, D. A., & Ed Jernigan, M. (2000) · Pattern Recognition · doi:10.1016/s0031-3203(99)00181-8 · Cited by 348
Linear Dimensionality Reduction: Survey, Insights, and Generalizations
Cunningham, J., Ghahramani, Z., et al. (2015) · Cambridge University Engineering Department Publications Database · Cited by 326
Special issue on feature engineering editorial
Verdonck, T., Baesens, B., Óskarsdóttir, M., & Broucke, S. V. (2021) · Machine Learning · doi:10.1007/s10994-021-06042-2 · Cited by 279
Brenning, A. (2012) · 2012 IEEE International Geoscience and Remote Sensing Symposium · doi:10.1109/igarss.2012.6352393 · Cited by 266
Self-citationHooker, G., Mentch, L., & Zhou, S. (2021) · Statistics and Computing · doi:10.1007/s11222-021-10057-z · Cited by 264
General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models
Molnar, C., König, G., Herbinger, J., Freiesleben, T., Dandl, S., Scholbeck, C. A., Casalicchio, G., Grosse-Wentrup, M., & Bischl, B. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-04083-2_4 · Cited by 211
Basille, M., Calenge, C., Marboutin, É., Andersen, R., & Gaillard, J. (2008) · Ecological Modelling · doi:10.1016/j.ecolmodel.2007.09.006 · Cited by 185
Molnar, C., König, G., Bischl, B., & Casalicchio, G. (2023) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-022-00901-9 · Cited by 164
Assessing fruit-tree crop classification from Landsat-8 time series for the Maipo Valley, Chile
Peña, M. A., & Brenning, A. (2015) · Remote Sensing of Environment · doi:10.1016/j.rse.2015.10.029 · Cited by 134
Self-citationGrouped feature importance and combined features effect plot
Au, Q., Herbinger, J., Stachl, C., Bischl, B., & Casalicchio, G. (2022) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-022-00840-5 · Cited by 99
Please Stop Permuting Features: An Explanation and Alternatives.Preprint
Hooker, G., & Mentch, L. (2019) · arXiv (Cornell University) · Cited by 86
Guo, S., Rösch, P., Popp, J., & Bocklitz, T. W. (2019) · Journal of Chemometrics · doi:10.1002/cem.3202 · Cited by 81
Rousson, V., & Gasser, T. (2004) · Journal of the Royal Statistical Society Series C (Applied Statistics) · doi:10.1111/j.1467-9876.2004.05359.x · Cited by 64
Iterative Orthogonal Feature Projection for Diagnosing Bias in Black-Box ModelsPreprint
Adebayo, J., & Kagal, L. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.04967 · Cited by 62
Using spectrotemporal indices to improve the fruit-tree crop classification accuracy
Peña, M. A., Liao, R., & Brenning, A. (2017) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2017.03.019 · Cited by 61
Self-citationDetecting rock glacier flow structures using Gabor filters and IKONOS imagery
Brenning, A., Long, S., & Fieguth, P. (2012) · Remote Sensing of Environment · doi:10.1016/j.rse.2012.07.005 · Cited by 54
Self-citationSpatial machine-learning model diagnostics: a model-agnostic distance-based approach
Brenning, A. (2023) · International Journal of Geographical Information Science · doi:10.1080/13658816.2022.2131789 · Cited by 33
Self-citationPitfalls to Avoid when Interpreting Machine Learning ModelsPreprint
Molnar, C., König, G., Herbinger, J., Freiesleben, T., Dandl, S., Scholbeck, C. A., Casalicchio, G., Grosse‐Wentrup, M., & Bischl, B. (2020) · arXiv (Cornell University) · Cited by 32
modelStudio: Interactive Studio with Explanations for ML Predictive Models
Baniecki, H., & Biecek, P. (2019) · The Journal of Open Source Software · doi:10.21105/joss.01798 · Cited by 21
Feature Extraction in Remote Sensing High-Dimensional Image Data
Zortea, M., Haertel, V., & Clarke, R. T. (2007) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2006.886429 · Cited by 16
Improving projection-based data analysis by feature space transformations
Schaefer, M., Zhang, L., Schreck, T., Tatu, A., Lee, J. A., Verleysen, M., & Keim, D. A. (2013) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2000701 · Cited by 15
totalvis: A Principal Components Approach to Visualizing Total Effects in Black Box Models
Seedorff, N., & Brown, G. (2021) · SN Computer Science · doi:10.1007/s42979-021-00560-5 · Cited by 8
Research works printed but not linked: 2
- Biecek, P. (2018). DALEX: Explainers for complex predictive models in R. Journal of Machine Learning Research, 19(84), 1–5.
- Somers, B., Tits, L., Roberts, D., et al. (2016). Chapter 17 - Endmember library approaches to resolve spectral mixing problems in remotely sensed data: Potential, challenges, and applications. In C. Ruckebusch (Ed.), Resolving spectral mixtures, data handling in science and technology. Amsterdam: Elsevier.
Cited by
General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models
Molnar, C., König, G., Herbinger, J., Freiesleben, T., Dandl, S., Scholbeck, C. A., Casalicchio, G., Grosse-Wentrup, M., & Bischl, B. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-04083-2_4 · Cited by 211
Metadata
- Authors
- Brenning, A.
- Venue
- Machine Learning
- Published
- 2023-04-11
- Volume
- 112
- Issue
- 9
- Pages
- 3455-3471
- ISSN
- 0885-6125
- 1573-0565
- Cited by
- 26
- References
- 33
- Language
- en
- Licence
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Funders
- Friedrich-Schiller-Universität Jena
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.
