Interpreting Neural Networks with Nearest Neighbors
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Local model interpretation methods explain individual predictions by assigning an importance value to each input feature.This value is often determined by measuring the change in confidence when a feature is removed.However, the confidence of neural networks is not a robust measure of model uncertainty.This issue makes reliably judging the importance of the input features difficult.We address this by changing the test-time behavior of neural networks using Deep k-Nearest Neighbors.Without harming text classification accuracy, this algorithm provides a more robust uncertainty metric which we use to generate feature importance values.The resulting interpretations better align with human perception than baseline methods.Finally, we use our interpretation method to analyze model predictions on dataset annotation artifacts.
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
On calibration of modern neural networks
Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017) · arXiv · doi:10.48550/arxiv.1706.04599 · Cited by 3,435
A large annotated corpus for learning natural language inference
Bowman, S. R., Angeli, G., Potts, C., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1075 · Cited by 3,377 · cited 1×
“Additionally, we consider natural language inference with SNLI (Bowman et al., 2015).”
MethodDeep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Nguyen, A., Yosinski, J., & Clune, J. (2014) · arXiv · doi:10.48550/arxiv.1412.1897 · Cited by 3,258
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
Nguyen, A., Yosinski, J., & Clune, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298640 · Cited by 3,258
Towards A Rigorous Science of Interpretable Machine Learning
Doshi-Velez, F., & Kim, B. (2017) · arXiv · doi:10.48550/arxiv.1702.08608 · Cited by 3,121
Supervised Learning of Universal Sentence Representations from Natural Language Inference Data
Conneau, A., Kiela, D., Schwenk, H., Barrault, L., & Bordes, A. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1070 · Cited by 2,049 · cited 1×
“Following Conneau et al. (2017), we use the same model to encode the two inputs, generating representations u for the premise and v for the hypothesis.”
MethodUnderstanding Black-box Predictions via Influence Functions
Koh, P. W., & Liang, P. (2017) · arXiv · doi:10.48550/arxiv.1703.04730 · Cited by 1,514 · cited 1×
“, 1999), an intuitive explanation for both machine learning experts and non-experts (Klein, 1989; Kim et al., 2014; Koh and Liang, 2017; Wallace and BoydGraber, 2018).”
BackgroundSmoothGrad: 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 · cited 3×
“Smilkov et al. (2017) and Sundararajan et al. (2017) both aggregate gradient values over multiple backpropagation passes to eliminate local noise or satisfy interpretation axioms.”
BackgroundMethodAnnotation Artifacts in Natural Language Inference Data
Gururangan, S., Swayamdipta, S., Levy, O., Schwartz, R., Bowman, S., & Smith, N. A. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) · doi:10.18653/v1/n18-2017 · Cited by 907
Interpretation of Neural Networks Is Fragile
Ghorbani, A., Abid, A., & Zou, J. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33013681 · Cited by 765
Cited by
On Interpretability of Artificial Neural Networks: A Survey
Fan, F.-L., Xiong, J., Li, M., & Wang, G. (2021) · IEEE Transactions on Radiation and Plasma Medical Sciences · doi:10.1109/trpms.2021.3066428 · Cited by 561
AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models
Wallace, E., Tuyls, J., Wang, J., Subramanian, S., Gardner, M., & Singh, S. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations · doi:10.18653/v1/d19-3002 · Cited by 116
“This is useful for aggregating interpretation results, e.g., as in Feng et al. (2018) and Wallace et al. (2018).”
MethodSelf-citationKeane, M. T., & Kenny, E. M. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-29249-2_11 · Cited by 84
“Another approach tries to map the layers of a DNN onto particular exemplar cases using Deep k-Nearest neighbors (DkNN) [71, 91, 92].”
MethodCecil, J., Lermer, E., Hudecek, M. F. C., Sauer, J., & Gaube, S. (2024) · Scientific Reports · doi:10.1038/s41598-024-60220-5 · Cited by 37
“Visualizations using salient heatmaps are also widely deployed to explain the results of AI algorithms relying on natural language processing (NLP), employed for the analysis of written or spoken language 27–31 .”
Metadata
- Authors
- Wallace, E., Feng, S., & Boyd-Graber, J.
- Venue
- Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
- Published
- 2018
- Pages
- 136-144
- OpenAlex
- W2891020797
- Cited by
- 64
- References
- 11
- FWCI
- 5.20
- Type
- conference paper
- Language
- en
- Open access
- gold
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: Interpreting Neural Networks with Nearest Neighbors. https://app.cochat.ai/papers/10.18653/v1/w18-5416
- The paper
- Wallace, E., Feng, S., & Boyd-Graber, J. (2018). Interpreting Neural Networks with Nearest Neighbors. Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP. https://doi.org/10.18653/v1/w18-5416
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.