Neurally-Guided Structure Inference

Most structure inference methods either rely on exhaustive search or are purely data-driven. Exhaustive search robustly infers the structure of arbitrarily complex data, but it is slow. Data-driven methods allow efficient inference, but do not generalize when test data have more complex structures than training data. In this paper, we propose a hybrid inference algorithm, the Neurally-Guided Structure Inference (NG-SI), keeping the advantages of both search-based and data-driven methods. The key idea of NG-SI is to use a neural network to guide the hierarchical, layer-wise search over the compositional space of structures. We evaluate our algorithm on two representative structure inference tasks: probabilistic matrix decomposition and symbolic program parsing. It outperforms data-driven and search-based alternatives on both tasks.

[1]  Hyeonwoo Noh,et al.  Neural Program Synthesis from Diverse Demonstration Videos , 2018, ICML.

[2]  Dawn Xiaodong Song,et al.  Making Neural Programming Architectures Generalize via Recursion , 2017, ICLR.

[3]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[4]  Joshua B. Tenenbaum,et al.  Automatic Construction and Natural-Language Description of Nonparametric Regression Models , 2014, AAAI.

[5]  William E. Byrd,et al.  Neural Guided Constraint Logic Programming for Program Synthesis , 2018, NeurIPS.

[6]  Sebastian Nowozin,et al.  DeepCoder: Learning to Write Programs , 2016, ICLR.

[7]  Lihong Li,et al.  Neuro-Symbolic Program Synthesis , 2016, ICLR.

[8]  Charles Kemp,et al.  The discovery of structural form , 2008, Proceedings of the National Academy of Sciences.

[9]  Geoffrey E. Hinton,et al.  Grammar as a Foreign Language , 2014, NIPS.

[10]  Michael S. Lewicki,et al.  Emergence of complex cell properties by learning to generalize in natural scenes , 2009, Nature.

[11]  Richard E. Turner,et al.  On Sparsity and Overcompleteness in Image Models , 2007, NIPS.

[12]  Butler W. Lampson,et al.  A Machine Learning Framework for Programming by Example , 2013, ICML.

[13]  Danqi Chen,et al.  A Fast and Accurate Dependency Parser using Neural Networks , 2014, EMNLP.

[14]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[15]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[16]  Christopher Meek,et al.  Semantic Parsing for Single-Relation Question Answering , 2014, ACL.

[17]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[18]  Pat Hanrahan,et al.  Neurally-Guided Procedural Models: Amortized Inference for Procedural Graphics Programs using Neural Networks , 2016, NIPS.

[19]  Ming Li,et al.  An Introduction to Kolmogorov Complexity and Its Applications , 2019, Texts in Computer Science.

[20]  Jiajun Wu,et al.  Learning to Infer and Execute 3D Shape Programs , 2019, ICLR.

[21]  Armando Solar-Lezama,et al.  Learning to Infer Graphics Programs from Hand-Drawn Images , 2017, NeurIPS.

[22]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[23]  Radomír Mech,et al.  Guided Procedural Modeling , 2011, Comput. Graph. Forum.

[24]  Dawn Xiaodong Song,et al.  Parametrized Hierarchical Procedures for Neural Programming , 2018, ICLR.

[25]  Joshua B. Tenenbaum,et al.  Exploiting compositionality to explore a large space of model structures , 2012, UAI.

[26]  Peter-Michael Osera,et al.  Type-and-example-directed program synthesis , 2015, PLDI.

[27]  Mirella Lapata,et al.  Language to Logical Form with Neural Attention , 2016, ACL.

[28]  Joshua B. Tenenbaum,et al.  Structure Discovery in Nonparametric Regression through Compositional Kernel Search , 2013, ICML.

[29]  Jovan Popovic,et al.  Style translation for human motion , 2005, ACM Trans. Graph..

[30]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[31]  Geoffrey E. Hinton,et al.  Modeling Human Motion Using Binary Latent Variables , 2006, NIPS.

[32]  Rishabh Singh,et al.  Robust Text-to-SQL Generation with Execution-Guided Decoding , 2018, 1807.03100.

[33]  Armando Solar-Lezama,et al.  Learning Libraries of Subroutines for Neurally-Guided Bayesian Program Induction , 2018, NeurIPS.

[34]  Dawn Song,et al.  Execution-Guided Neural Program Synthesis , 2018, ICLR.

[35]  Thomas L. Griffiths,et al.  Infinite latent feature models and the Indian buffet process , 2005, NIPS.

[36]  Eduard H. Hovy,et al.  End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF , 2016, ACL.

[37]  Lior Wolf,et al.  Automatic Program Synthesis of Long Programs with a Learned Garbage Collector , 2018, NeurIPS.

[38]  Dawn Xiaodong Song,et al.  Towards Synthesizing Complex Programs From Input-Output Examples , 2017, ICLR.

[39]  Ruslan Salakhutdinov,et al.  Probabilistic Matrix Factorization , 2007, NIPS.

[40]  Dawn Xiaodong Song,et al.  Tree-to-tree Neural Networks for Program Translation , 2018, NeurIPS.

[41]  Thomas L. Griffiths,et al.  Learning Systems of Concepts with an Infinite Relational Model , 2006, AAAI.

[42]  Pushmeet Kohli,et al.  RobustFill: Neural Program Learning under Noisy I/O , 2017, ICML.

[43]  Simon Haykin,et al.  GradientBased Learning Applied to Document Recognition , 2001 .

[44]  Armando Solar-Lezama,et al.  Program synthesis by sketching , 2008 .

[45]  Swarat Chaudhuri,et al.  Neural Sketch Learning for Conditional Program Generation , 2017, ICLR.

[46]  Sumit Gulwani,et al.  Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples , 2018, ICLR.

[47]  Samy Bengio,et al.  Show and tell: A neural image caption generator , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).