Abstract
In this paper, we consider the problem of learning Boolean formulae from examples obtained by actively querying an oracle that can label these examplesz as either positive or negative. This problem has received attention in both machine learning as well as formal methods communities, and it has been shown to have exponential worst-case complexity in the general case as well as for many restrictions. In this paper, we focus on learning sparse Boolean formulae which depend on only a small (but unknown) subset of the overall vocabulary of atomic propositions. We propose an efficient algorithm to learn these sparse Boolean formulae with a given confidence. This assumption of sparsity is motivated by the problem of mining explanations for decisions made by artificially intelligent (AI) algorithms, where the explanation of individual decisions may depend on a small but unknown subset of all the inputs to the algorithm. We demonstrate the use of our algorithm in automatically generating explanations of these decisions. These explanations will make intelligent systems more understandable and accountable to human users, facilitate easier audits and provide diagnostic information in the case of failure. The proposed approach treats the AI algorithm as a black-box oracle; hence, it is broadly applicable and agnostic to the specific AI algorithm. We illustrate the practical effectiveness of our approach on a diverse set of case studies.
S. Jha—The author is currently at SRI International.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abouzied, A., Angluin, D., Papadimitriou, C., Hellerstein, J.M., Silberschatz, A.: Learning and verifying quantified boolean queries by example. In: ACM Symposium on Principles of Database Systems, pp. 49–60. ACM (2013)
Angluin, D., Computational learning theory: survey and selected bibliography. In: ACM Symposium on Theory of Computing, pp. 351–369. ACM (1992)
Angluin, D., Kharitonov, M.: When won’t membership queries help? In: ACM Symposium on Theory of Computing, pp. 444–454. ACM (1991)
Bittner, B., Bozzano, M., Cimatti, A., Gario, M., Griggio, A.: Towards pareto-optimal parameter synthesis for monotonie cost functions. In: FMCAD, pp. 23–30, October 2014
Boigelot, B., Godefroid, P.: Automatic synthesis of specifications from the dynamic observation of reactive programs. In: Brinksma, E. (ed.) TACAS 1997. LNCS, vol. 1217, pp. 321–333. Springer, Heidelberg (1997). doi:10.1007/BFb0035397
Botinčan, M., Babić, D., Sigma*: Symbolic learning of input-output specifications. In: POPL, pp. 443–456 (2013)
Cook, B., Kroening, D., Rümmer, P., Wintersteiger, C.M.: Ranking function synthesis for bit-vector relations. FMSD 43(1), 93–120 (2013)
Ehrenfeucht, A., Haussler, D., Kearns, M., Valiant, L.: A general lower bound on the number of examples needed for learning. Inf. Comput. 82(3), 247–261 (1989)
Elizalde, F., Sucar, E., Noguez, J., Reyes, A.: Generating explanations based on Markov decision processes. In: Aguirre, A.H., Borja, R.M., Garciá, C.A.R. (eds.) MICAI 2009. LNCS (LNAI), vol. 5845, pp. 51–62. Springer, Heidelberg (2009). doi:10.1007/978-3-642-05258-3_5
Feng, C., Muggleton, S.: Towards inductive generalisation in higher order logic. In: 9th International Workshop on Machine learning, pp. 154–162 D (2014)
Godefroid, P., Taly, A.: Automated synthesis of symbolic instruction encodings from i/o samples. SIGPLAN Not. 47(6), 441–452 (2012)
Goldsmith, J., Sloan, R.H., Szörényi, B., Turán, G.: Theory revision with queries: Horn, read-once, and parity formulas. Artif. Intell. 156(2), 139–176 (2004)
Gurfinkel, A., Belov, A., Marques-Silva, J.: Synthesizing safe bit-precise invariants. In: Ábrahám, E., Havelund, K. (eds.) TACAS 2014. LNCS, vol. 8413, pp. 93–108. Springer, Heidelberg (2014). doi:10.1007/978-3-642-54862-8_7
Harbers, M., Meyer, J.-J., van den Bosch, K.: Explaining simulations through self explaining agents. J. Artif. Soc. Soc. Simul. 13, 10 (2010)
Hellerstein, L., Servedio, R.A.: On PAC learning algorithms for rich boolean function classes. Theoret. Comput. Sci. 384(1), 66–76 (2007)
Jha, S., Seshia, S.A.: A theory of formal synthesis via inductive learning. Acta Informatica, pp. 1–34 (2017)
Jha, S., A. Seshia, and A. Tiwari. Synthesis of optimal switching logic for hybrid systems. In: EMSOFT, pp. 107–116. ACM (2011)
Kearns, M., Li, M., Valiant, L.: Learning boolean formulas. J. ACM 41(6), 1298–1328 (1994)
Kearns, M., Valiant, L.: Cryptographic limitations on learning boolean formulae and finite automata. Journal of the ACM (JACM) 41(1), 67–95 (1994)
LaValle, S.M.: Planning Algorithms. Cambridge University Press, Cambridge (2006)
Lecun, Y., Cortes, C.: The MNIST database of handwritten digits. http://yann.lecun.com/exdb/mnist/
Lee, J., Moray, N.: Trust, control strategies and allocation of function in human-machine systems. Ergonomics 35(10), 1243–1270 (1992)
Mansour, Y.: Learning boolean functions via the fourier transform. In: Theoretical Advances in Neural Computation and Learning, pp. 391–424 (1994)
Nau, D., Ghallab, M., Traverso, P.: Automated Planning: Theory and Practice. Morgan Kaufmann Publishers Inc., San Francisco (2004)
Pitt, L., Valiant, L.G.: Computational limitations on learning from examples. J. ACM (JACM) 35(4), 965–984 (1988)
Raman, V.: Reactive switching protocols for multi-robot high-level tasks. In: IEEE/RSJ, pp. 336–341 (2014)
Raman, V., Lignos, C., Finucane, C., Lee, K.C.T., Marcus, M.P., Kress-Gazit, H.: Sorry Dave, I’m afraid i can’t do that: explaining unachievable robot tasks using natural language. In: Robotics: Science and Systems (2013)
Reynolds, A., Deters, M., Kuncak, V., Tinelli, C., Barrett, C.: Counterexample-guided quantifier instantiation for synthesis in SMT. In: Kroening, D., Păsăreanu, C.S. (eds.) CAV 2015. LNCS, vol. 9207, pp. 198–216. Springer, Cham (2015). doi:10.1007/978-3-319-21668-3_12
Ribeiro, M.T., Singh, S., Guestrin, C.: Why Should I Trust You?: Explaining the predictions of any classifier. In: KDD, pp. 1135–1144 (2016)
Russell, J., Cohn, R.: OODA Loop. Book on Demand, Norderstedt (2012)
Sankaranarayanan, S.: Automatic invariant generation for hybrid systems using ideal fixed points. In: HSCC, pp. 221–230 (2010)
Sankaranarayanan, S., Miller, C., Raghunathan, R., Ravanbakhsh, H., Fainekos, G.: A model-based approach to synthesizing insulin infusion pump usage parameters for diabetic patients. In: Annual Allerton Conference on Communication, Control, and Computing, pp. 1610–1617, October 2012
Sankaranarayanan, S., Sipma, H.B., Manna, Z.: Constructing invariants for hybrid systems. FMSD 32(1), 25–55 (2008)
Štrumbelj, E., Kononenko, I.: Explaining prediction models and individual predictions with feature contributions. KIS 41(3), 647–665 (2014)
Urban, C., Gurfinkel, A., Kahsai, T.: Synthesizing ranking functions from bits and pieces. In: Chechik, M., Raskin, J.-F. (eds.) TACAS 2016. LNCS, vol. 9636, pp. 54–70. Springer, Heidelberg (2016). doi:10.1007/978-3-662-49674-9_4
Yuan, C., Lim, H., Lu, T.-C.: Most relevant explanation in bayesian networks. J. Artif. Intell. Res. (JAIR) 42, 309–352 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Jha, S., Raman, V., Pinto, A., Sahai, T., Francis, M. (2017). On Learning Sparse Boolean Formulae for Explaining AI Decisions. In: Barrett, C., Davies, M., Kahsai, T. (eds) NASA Formal Methods. NFM 2017. Lecture Notes in Computer Science(), vol 10227. Springer, Cham. https://doi.org/10.1007/978-3-319-57288-8_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-57288-8_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-57287-1
Online ISBN: 978-3-319-57288-8
eBook Packages: Computer ScienceComputer Science (R0)