Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
153 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

From Shapley Value to Model Counting and Back (2306.14211v1)

Published 25 Jun 2023 in cs.DB, cs.CC, and cs.LO

Abstract: In this paper we investigate the problem of quantifying the contribution of each variable to the satisfying assignments of a Boolean function based on the Shapley value. Our main result is a polynomial-time equivalence between computing Shapley values and model counting for any class of Boolean functions that are closed under substitutions of variables with disjunctions of fresh variables. This result settles an open problem raised in prior work, which sought to connect the Shapley value computation to probabilistic query evaluation. We show two applications of our result. First, the Shapley values can be computed in polynomial time over deterministic and decomposable circuits, since they are closed under OR-substitutions. Second, there is a polynomial-time equivalence between computing the Shapley value for the tuples contributing to the answer of a Boolean conjunctive query and counting the models in the lineage of the query. This equivalence allows us to immediately recover the dichotomy for Shapley value computation in case of self-join-free Boolean conjunctive queries; in particular, the hardness for non-hierarchical queries can now be shown using a simple reduction from the #P-hard problem of model counting for lineage in positive bipartite disjunctive normal form.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (34)
  1. The tractability of shap-score-based explanations for classification over deterministic and decomposable Boolean circuits. In AAAI, pages 6670–6678, 2021.
  2. On computing probabilistic explanations for decision trees. In NeurIPS, 2022.
  3. On the complexity of shap-score-based explanations: Tractability via knowledge compilation and non-approximability results, 2023.
  4. Conditional dichotomy of Boolean ordered promise CSPs. TheoretiCS, 2, 2023.
  5. Understanding model counting for beta-acyclic cnf-formulas. In STACS, volume 30 of LIPIcs, pages 143–156, 2015.
  6. N. N. Dalvi and D. Suciu. Efficient query evaluation on probabilistic databases. In VLDB, pages 864–875, 2004.
  7. N. N. Dalvi and D. Suciu. The dichotomy of probabilistic inference for unions of conjunctive queries. J. ACM, 59(6):30:1–30:87, 2012.
  8. A. Darwiche and P. Marquis. A knowledge compilation map. J. Artif. Intell. Res., 17:229–264, 2002.
  9. Recent trends in knowledge compilation (dagstuhl seminar 17381). Dagstuhl Reports, 7(9):62–85, 2017.
  10. Shapgraph: An holistic view of explanations through provenance graphs and Shapley values. In SIGMOD, pages 2373–2376, 2022.
  11. On the tractability of SHAP explanations. In AAAI, pages 6505–6513, 2021.
  12. On the tractability of SHAP explanations. J. Artif. Intell. Res., 74:851–886, 2022.
  13. Computing the Shapley value of facts in query answering. In SIGMOD, pages 1570–1583, 2022.
  14. Matrix Computations, Third Edition. Johns Hopkins University Press, 1996.
  15. Model counting. In Handbook of Satisfiability - Second Edition, volume 336, pages 993–1014. 2021.
  16. Provenance semirings. In L. Libkin, editor, SIGACT-SIGMOD-SIGART, pages 31–40, 2007.
  17. Evaluation, strength, and relevance of variables of Boolean functions. SIAM J. Discret. Math., 13(3):302–312, 2000.
  18. A unifying formal approach to importance values in Boolean functions. CoRR, abs/2305.08103, 2023.
  19. G. Kalai. Social indeterminacy. Econometrica, 72(5):1565–1581, 2004.
  20. Monte-Carlo approximation algorithms for enumeration problems. J. Algorithms, 10(3):429–448, 1989.
  21. The Shapley value of tuples in query answering. Log. Methods Comput. Sci., 17(3), 2021.
  22. Internet economics: The use of Shapley value for ISP settlement. IEEE/ACM Trans. Netw., 18(3):775–787, 2010.
  23. Interconnecting eyeballs to content: a Shapley value perspective on isp peering and settlement. In SIGCOMM, pages 61–66, 2008.
  24. Explainable artificial intelligence: A comprehensive review. Artif. Intell. Rev., 55(5):3503–3568, 2022.
  25. Using coalitional games on biological networks to measure centrality and power of genes. Bioinform., 26(21):2721–2730, 2010.
  26. R. Narayanam and Y. Narahari. A Shapley value-based approach to discover influential nodes in social networks. IEEE Trans Autom. Sci. Eng., 8(1):130–147, 2011.
  27. D. Olteanu and J. Huang. Using OBDDs for efficient query evaluation on probabilistic databases. In SUM, volume 5291, pages 326–340, 2008.
  28. The complexity of counting cuts and of computing the probability that a graph is connected. SIAM J. Comput., 12(4):777–788, 1983.
  29. The impact of negation on the complexity of the Shapley value in conjunctive queries. In D. Suciu, Y. Tao, and Z. Wei, editors, PODS, pages 285–297, 2020.
  30. A. E. Roth. The Shapley value: essays in honor of Lloyd S. Shapley. Cambridge University Press, 1988.
  31. The Shapley value in machine learning. In L. D. Raedt, editor, IJCAI, pages 5572–5579, 2022.
  32. L. S. Shapley. A Value for n-Person Games, pages 307–318. Princeton University Press, 1953.
  33. Probabilistic Databases. Synthesis Lectures on Data Management. Morgan & Claypool Publishers, 2011.
  34. A new approximation method for the Shapley value applied to the WTC 9/11 terrorist attack. Soc. Netw. Anal. Min., 8(1):3:1–3:12, 2018.
Citations (5)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now