Journal article · 2026 · Open access
Less Is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection
IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–18 · Published 1 January 2026 · DOI 10.1109/tpami.2026.3746930
In brief
“Less Is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection” is a 2026 journal article by Ruoyu Chen and 6 co-authors, published in IEEE Transactions on Pattern Analysis and Machine Intelligence. OpenAlex counts 10 citations as of 16 November 2026, which puts it in the top 5% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 10
- Most cited in
- 2026 (7)
- Field-weighted impact
- 9.77
- References
- 8
- Authors
- 7
Abstract
To develop a trustworthy AI system, it is essential to understand its behavior using attribution methods, which aim to identify the input regions that most influence the model's decisions. For discrete inputs such as images, however, accurately identifying input prediction interactions is particularly challenging because of combinatorial explosion. We formulate black-box attribution as an ordered interpretable subset-selection problem. Inspired by the marginal-gain principle of submodular optimization, the formulation permits redundancy, positive complementarity, and negative interference among input sub-regions. We propose LIMA (Less input is More faithful for Attribution), which ranks sub-regions by their contributions along a sequence of selected subsets. LIMA employs a composite objective that evaluates subsets through semantic consistency, collaboration, prediction confidence, and semantic effectiveness. We further design a bidirectional greedy search to efficiently identify important and non-critical sub-regions. Experiments on eight foundation models (CLIP, ImageBind, LanguageBind, QuiltNet, etc.) and six datasets (ImageNet, VGG-Sound, CUB-200-2011, etc.) demonstrate strong generalization and faithful interpretations with fewer sub-regions. LIMA achieves state-of-the-art Insertion, Deletion, and average highest confidence, with average improvements of 36.3% in Insertion and 39.6% in Deletion; it is also 1.6 times faster than naive greedy search. For failure attribution on incorrect predictions, LIMA improves average highest confidence by 86.1% over state-of-the-art methods.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Chen, R., Liang, S., Li, J., Liu, S., Liu, L., Zhang, H., & Cao, X. (2026). Less Is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–18. https://doi.org/10.1109/tpami.2026.3746930
MLA 9
Chen, Ruoyu, et al. “Less Is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, 2026, pp. 1–18. https://doi.org/10.1109/tpami.2026.3746930.
Chicago
Chen, Ruoyu, Siyuan Liang, Jingzhi Li, Shiming Liu, Li Liu, Hua Zhang, and Xiaochun Cao. 2026. “Less Is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection.” IEEE Transactions on Pattern Analysis and Machine Intelligence PP: 1–18. https://doi.org/10.1109/tpami.2026.3746930.
Harvard
Chen, R. et al. (2026) ‘Less Is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection’, IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, pp. 1–18. doi:10.1109/tpami.2026.3746930.
IEEE
R. Chen et al., “Less Is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, pp. 1–18, 2026, doi: 10.1109/tpami.2026.3746930.
BibTeX
@article{chen2026less,
title = {{Less Is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection}},
author = {Chen, Ruoyu and Liang, Siyuan and Li, Jingzhi and Liu, Shiming and Liu, Li and Zhang, Hua and Cao, Xiaochun},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {PP},
pages = {1--18},
doi = {10.1109/tpami.2026.3746930},
url = {https://doi.org/10.1109/tpami.2026.3746930}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- submodular optimization
- greedy search
- image interpretability
- foundation models
- failure attribution
- trustworthy AI
- Lima
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Chen, R., Liang, S., Li, J., Liu, S., Liu, L., Zhang, H., & Cao, X. (2026). Less Is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–18. https://doi.org/10.1109/tpami.2026.3746930
How many times has this paper been cited?
10 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Ruoyu Chen, Siyuan Liang, Jingzhi Li, Shiming Liu, Li Liu, Hua Zhang, Xiaochun Cao.
What is the DOI of this paper?
10.1109/tpami.2026.3746930, permanently at https://doi.org/10.1109/tpami.2026.3746930. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.