Explaining k-Nearest Neighbors: Abductive and Counterfactual Explanations
Summary: Explores feature-level explanations for k-NN, introducing abductive minimum-sufficient-reason explanations and counterfactual explanations for classifications. Charts a complexity landscape across discrete vs continuous features and distance functions, and enables practical computation via Integer Quadratic Programming and SAT. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Pablo Barceló (Pontifical Catholic University of Chile)
- 2. Alexander Kozachinskiy (CENIA)
- 3. Miguel Romero (Pontifical Catholic University of Chile)
- 4. Bernardo Subercaseaux (Carnegie Mellon University)
- 5. José Verschae (Pontifical Catholic University of Chile)
BibTeX Citation
@inproceedings{barcelo_pods25,
address = {New York, NY, USA},
series = {{PODS} '25},
title = {{Explaining k-Nearest Neighbors: Abductive and Counterfactual Explanations}},
url = {https://dl.acm.org/doi/10.1145/3725234},
doi = {10.1145/3725234},
booktitle = {Proceedings of the {ACM} {SIGMOD} Symposium on {Principles} of {Database} {Systems}},
publisher = {Association for Computing Machinery},
author = {Barceló, Pablo and Kozachinskiy, Alexander and Romero, Miguel and Subercaseaux, Bernardo and Verschae, José},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,557 | Database Views as Explanations for Relational Deep Learning | 2026 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 6 of 6 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 28 | Nearest Neighbor Queries | 1995 | SIGMOD | 0.00052102434 |
| 581 | Quality and Efficiency in High Dimensional Nearest Neighbor Search | 2009 | SIGMOD | 0.00016153395 |
| 2,158 | What is the nearest neighbor in high dimensional spaces? | 2000 | VLDB | 9.0622995e-05 |
| 3,685 | Parallel Algorithms for Constructing Range and Nearest-Neighbor Searching Data Structures | 2016 | PODS | 7.2030591e-05 |
| 4,850 | Nearest-Neighbor Searching Under Uncertainty | 2012 | PODS | 6.480347e-05 |
| 7,025 | Nearest Neighbor Searching Under Uncertainty II | 2013 | PODS | 5.7234179e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 11,790 | Minimization of Classifier Construction Cost for Search Queries | 2020 | SIGMOD |
| 2 | 3,710 | Efficient Reverse k-Nearest Neighbor Search in Arbitrary Metric Spaces | 2006 | SIGMOD |
| 3 | 1,066 | Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms | 2019 | VLDB |
| 4 | 9,313 | Computing Rule-Based Explanations by Leveraging Counterfactuals | 2023 | VLDB |
| 5 | 12,422 | K-Nearest Neighbor Search for Fuzzy Objects | 2010 | SIGMOD |
| 6 | 11,751 | On the I/O Complexity of the k-Nearest Neighbors Problem | 2020 | PODS |
| 7 | 8,848 | A Generalized Approach for Reducing Expensive Distance Calls for A Broad Class of Proximity Problems | 2021 | SIGMOD |
| 8 | 1,605 | Efficient Search for the Top-k Probable Nearest Neighbors in Uncertain Databases | 2008 | VLDB |
| 9 | 11,157 | Relative Keys: Putting Feature Explanation into Context | 2024 | SIGMOD |
| 10 | 2,147 | Nearest Neighbor Classifiers over Incomplete Information: From Certain Answers to Certain Predictions | 2021 | VLDB |