DBScholar

Back to papers

P-Shapley: Shapley Values on Probabilistic Classifiers

Summary: Introduces P-Shapley, a Shapley-value formulation for classification that uses model-predicted probabilities (with convex calibration functions) as utility instead of binary accuracy. Theoretically and empirically yields more stable, more discriminative data valuations. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
13600
Venue
VLDB
Year
2024
Pagerank
5.4574671e-05
Overall Rank
8,250 | 43.40%
DOI
10.14778/3654621.3654638

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@article{xia_vldb24,
        title = {{P-Shapley: Shapley Values on Probabilistic Classifiers}},
        author = {Xia, Haocheng and Li, Xiang and Pang, Junyuan and Liu, Jinfei and Ren, Kui and Xiong, Li},
        journal = {PVLDB},
        series = {{VLDB} '24},
        volume = {17},
        number = {7},
        pages = {1737--1750},
        doi = {10.14778/3654621.3654638},
        url = {https://doi.org/10.14778/3654621.3654638},
        year = {2024}
}

Incoming Citations (Sorted by Pagerank)

Showing 3 of 3 citing papers.

Rank Citing Paper Year Venue Pagerank
9,541 Shapley Value Estimation Based on Differential Matrix 2025 SIGMOD 5.2528121e-05
10,198 ASSS: Adaptive Stratified Sampling for Shapley-like Values 2026 SIGMOD 5.093636e-05
10,906 A Comprehensive Study of Shapley Value in Data Analytics 2025 VLDB 5.093636e-05
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 14 of 14 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Previous Page 1 / 1 Next

Semantically Similar Papers