Shahin: Faster Algorithms for Generating Explanations for Multiple Predictions
Summary: Shahin batch-processes explanations for multiple predictions, identifying and reusing overlapping perturbation computations. Generalizable to LIME, Anchor, SHAP, it delivers large speedups with minimal overhead and few modifications. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Sona Hasani (Google)
- 2. Saravanan Thirumuruganathan (Hamad Bin Khalifa University; Qatar Computing Research Institute)
- 3. Nick Koudas (University of Toronto)
- 4. Gautam Das (University of Texas)
BibTeX Citation
@inproceedings{hasani_sigmod21,
title = {{Shahin: Faster Algorithms for Generating Explanations for Multiple Predictions}},
author = {Hasani, Sona and Thirumuruganathan, Saravanan and Koudas, Nick and Das, Gautam},
series = {{SIGMOD} '21},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3448016.3457332},
url = {https://dl.acm.org/doi/10.1145/3448016.3457332},
year = {2021}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 7 of 7 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 128 | Efficient and Extensible Algorithms for Multi Query Optimization | 2000 | SIGMOD | 0.0003072825 |
| 284 | NoScope: Optimizing Neural Network Queries over Video at Scale | 2017 | VLDB | 0.00022370521 |
| 2,987 | Incremental and Approximate Inference for Faster Occlusion-based Deep CNN Explanations | 2019 | SIGMOD | 7.8907997e-05 |
| 4,023 | Smurf: Self-Service String Matching Using Random Forests | 2019 | VLDB | 6.949387e-05 |
| 6,038 | Efficient Construction of Approximate Ad-Hoc ML models Through Materialization and Reuse | 2018 | VLDB | 5.9990929e-05 |
| 7,000 | A Cost-based Optimizer for Gradient Descent Optimization | 2017 | SIGMOD | 5.7287645e-05 |
| 9,076 | Leveraging Similarity Joins for Signal Reconstruction | 2018 | VLDB | 5.3251649e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,214 | CoShap: A Scalable Coalition Growth Approach to Shapley Value Approximation | 2026 | SIGMOD |
| 2 | 10,796 | Understanding the Black Box: A Deep Empirical Dive into Shapley Value Approximations for Tabular Data | 2025 | SIGMOD |
| 3 | 10,557 | Database Views as Explanations for Relational Deep Learning | 2026 | VLDB |
| 4 | 1,066 | Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms | 2019 | VLDB |
| 5 | 9,922 | View-based Explanations for Graph Neural Networks | 2024 | SIGMOD |
| 6 | 13,324 | ShaRP: Explaining Rankings and Preferences with Shapley Values | 2025 | VLDB |
| 7 | 11,157 | Relative Keys: Putting Feature Explanation into Context | 2024 | SIGMOD |
| 8 | 9,313 | Computing Rule-Based Explanations by Leveraging Counterfactuals | 2023 | VLDB |
| 9 | 13,292 | Scalable GNN Explanations with Distributed Shapley Values | 2026 | VLDB |
| 10 | 13,315 | ShapX Engine: A Demonstration of Shapley Value Approximations | 2025 | SIGMOD |