Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations
Open accessThe DOI matches its OpenAlex record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
A critical problem in the field of post hoc explainability is the lack of a common foundational goal among methods. For example, some methods are motivated by function approximation, some by game theoretic notions, and some by obtaining clean visualizations. This fragmentation of goals causes not only an inconsistent conceptual understanding of explanations but also the practical challenge of not knowing which method to use when. In this work, we begin to address these challenges by unifying eight popular post hoc explanation methods (LIME, C-LIME, KernelSHAP, Occlusion, Vanilla Gradients, Gradients x Input, SmoothGrad, and Integrated Gradients). We show that these methods all perform local function approximation of the black-box model, differing only in the neighbourhood and loss function used to perform the approximation. This unification enables us to (1) state a no free lunch theorem for explanation methods, demonstrating that no method can perform optimally across all neighbourhoods, and (2) provide a guiding principle to choose among methods based on faithfulness to the black-box model. We empirically validate these theoretical results using various real-world datasets, model classes, and prediction tasks. By bringing diverse explanation methods into a common framework, this work (1) advances the conceptual understanding of these methods, revealing their shared local function approximation objective, properties, and relation to one another, and (2) guides the use of these methods in practice, providing a principled approach to choose among methods and paving the way for the creation of new ones.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Learning Deconvolution Network for Semantic Segmentation
Noh, H., Hong, S., & Han, B. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.178 · Cited by 4,422
Axiomatic attribution for deep networks
Sundararajan, M., Taly, A., & Yan, Q. (2017) · arXiv · doi:10.48550/arxiv.1703.01365 · Cited by 4,087
Striving for Simplicity: The All Convolutional Net
Springenberg, J. T., Dosovitskiy, A., Brox, T., & Riedmiller, M. (2014) · arXiv · doi:10.48550/arxiv.1412.6806 · Cited by 3,447
Learning Important Features Through Propagating Activation Differences
Shrikumar, A., Greenside, P., & Kundaje, A. (2017) · arXiv · doi:10.48550/arxiv.1704.02685 · Cited by 2,761
SmoothGrad: removing noise by adding noise
Smilkov, D., Thorat, N., Kim, B., Viégas, F., & Wattenberg, M. (2017) · arXiv · doi:10.48550/arxiv.1706.03825 · Cited by 1,467
Sanity Checks for Saliency Maps
Adebayo, J., Gilmer, J., Muelly, M., Goodfellow, I., Hardt, M., & Kim, B. (2018) · arXiv · doi:10.48550/arxiv.1810.03292 · Cited by 1,294
Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods
Slack, D., Hilgard, S., Jia, E., Singh, S., & Lakkaraju, H. (2020) · Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3375627.3375830 · Cited by 900
Self-citationCaptum: A unified and generic model interpretability library for PyTorch
Kokhlikyan, N., Miglani, V., Martin, M., Wang, E., Alsallakh, B., Reynolds, J., Melnikov, A., Kliushkina, N., Araya, C., Yan, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2009.07896 · Cited by 658
Visualizing and Understanding Convolutional Networks
Zeiler, M. D., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1311.2901 · Cited by 522
On the Robustness of Interpretability Methods
Alvarez-Melis, D., & Jaakkola, T. S. (2018) · arXiv · doi:10.48550/arxiv.1806.08049 · Cited by 310
Cited by
Longo, L., Brcic, M., Cabitza, F., Choi, J., Confalonieri, R., Ser, J. D., Guidotti, R., Hayashi, Y., Herrera, F., Holzinger, A., et al. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102301 · Cited by 626
EXplainable Artificial Intelligence (XAI)—From Theory to Methods and Applications
Ortigossa, E. S., Gonçalves, T., & Nonato, L. G. (2024) · IEEE Access · doi:10.1109/access.2024.3409843 · Cited by 124
Toward a Theory of Causation for Interpreting Neural Code Models
Nader Palacio, D., Velasco, A., Cooper, N., Rodriguez, A., Moran, K., & Poshyvanyk, D. (2024) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2024.3379943 · Cited by 18
Gauge fixing for sequence-function relationships
Posfai, A., Zhou, J., McCandlish, D. M., & Kinney, J. B. (2024) · doi:10.1101/2024.05.12.593772 · Cited by 11
Gauge fixing for sequence-function relationships
(2025) · doi:10.1371/journal.pcbi.1012818 · Cited by 11
Metadata
- Authors
- Han, T., Srinivas, S., & Lakkaraju, H.
- Venue
- neural information processing systems
- Published
- 2022-01-01
- Pages
- 5256-5268
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W7133188536
- Cited by
- 38
- References
- 10
- FWCI
- 4.49
- Type
- conference paper
- Language
- en
- Open access
- green
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations. https://app.cochat.ai/papers/10.52202/068431-0380
- The paper
- Han, T., Srinivas, S., & Lakkaraju, H. (2022). Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations. neural information processing systems. https://doi.org/10.52202/068431-0380
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.