Neural Networks for Approximate DNF Counting: An Abridged Report

Weighted model counting (WMC) has emerged as a prevalent approach for probabilistic inference. In its most general form, WMC is #P-hard. Weighted DNF counting (weighted #DNF) is a special case where approximations with probabilistic guarantees are obtained in O(nm), where n denotes the number of variables, and m the number of clauses of the input DNF, but this is not scalable in practice. In this paper, we propose a novel approach for weighted #DNF that combines approximate model counting with deep learning, and accurately approximates model counts in linear time when width is bounded. We conduct experiments to validate our method, and show that our model learns and generalizes very well to large-scale #DNF instances.

[1]  Thomas Lukasiewicz,et al.  Ontology-Mediated Queries for Probabilistic Databases , 2017, AAAI.

[2]  Prasoon Goyal,et al.  Probabilistic Databases , 2009, Encyclopedia of Database Systems.

[3]  Luc De Raedt,et al.  ProbLog: A Probabilistic Prolog and its Application in Link Discovery , 2007, IJCAI.

[4]  Geoffrey E. Hinton,et al.  Layer Normalization , 2016, ArXiv.

[5]  Jure Leskovec,et al.  How Powerful are Graph Neural Networks? , 2018, ICLR.

[6]  Larry J. Stockmeyer,et al.  The complexity of approximate counting , 1983, STOC.

[7]  Bart Selman,et al.  Taming the Curse of Dimensionality: Discrete Integration by Hashing and Optimization , 2013, ICML.

[8]  F. Scarselli,et al.  A new model for learning in graph domains , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[9]  Martin Grohe,et al.  Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks , 2018, AAAI.

[10]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[11]  Pierre Marquis,et al.  A Knowledge Compilation Map , 2002, J. Artif. Intell. Res..

[12]  Richard M. Karp,et al.  Monte-Carlo Approximation Algorithms for Enumeration Problems , 1989, J. Algorithms.

[13]  Supratik Chakraborty,et al.  A Scalable Approximate Model Counter , 2013, CP.

[14]  Bart Selman,et al.  Knowledge compilation and theory approximation , 1996, JACM.

[15]  J. Scott Provan,et al.  The Complexity of Counting Cuts and of Computing the Probability that a Graph is Connected , 1983, SIAM J. Comput..

[16]  Ah Chung Tsoi,et al.  The Graph Neural Network Model , 2009, IEEE Transactions on Neural Networks.

[17]  Bart Selman,et al.  Model Counting , 2021, Handbook of Satisfiability.

[18]  Richard S. Zemel,et al.  Gated Graph Sequence Neural Networks , 2015, ICLR.

[19]  Luís C. Lamb,et al.  Learning to Solve NP-Complete Problems - A Graph Neural Network for the Decision TSP , 2018, AAAI.

[20]  Leslie G. Valiant,et al.  The Complexity of Computing the Permanent , 1979, Theor. Comput. Sci..

[21]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[22]  Guy Van den Broeck,et al.  Open World Probabilistic Databases (Extended Abstract) , 2016, Description Logics.

[23]  Moshe Y. Vardi,et al.  On Hashing-Based Approaches to Approximate DNF-Counting , 2017, FSTTCS.

[24]  Thomas Lukasiewicz,et al.  Learning to Reason: Leveraging Neural Networks for Approximate DNF Counting , 2019, AAAI.

[25]  Supratik Chakraborty,et al.  Algorithmic Improvements in Approximate Counting for Probabilistic Inference: From Linear to Logarithmic SAT Calls , 2016, IJCAI.

[26]  Marco Cadoli,et al.  A Survey on Knowledge Compilation , 1997, AI Commun..

[27]  Carmel Domshlak,et al.  Probabilistic Planning via Heuristic Forward Search and Weighted Model Counting , 2007, J. Artif. Intell. Res..

[28]  David L. Dill,et al.  Learning a SAT Solver from Single-Bit Supervision , 2018, ICLR.