Abstract
Is intelligence realized by connectionist or classicist? While connectionist approaches have achieved superhuman performance, there has been growing evidence that such task-specific superiority is particularly fragile in systematic generalization. This observation lies in the central debate between connectionist and classicist, wherein the latter continually advocates an algebraic treatment in cognitive architectures. In this work, we follow the classicist’s call and propose a hybrid approach to improve systematic generalization in reasoning. Specifically, we showcase a prototype with algebraic representation for the abstract spatial-temporal reasoning task of Raven’s Progressive Matrices (RPM) and present the ALgebra-Aware Neuro-Semi-Symbolic (ALANS) learner. The ALANS learner is motivated by abstract algebra and the representation theory. It consists of a neural visual perception frontend and an algebraic abstract reasoning backend: the frontend summarizes the visual information from object-based representation, while the backend transforms it into an algebraic structure and induces the hidden operator on the fly. The induced operator is later executed to predict the answer’s representation, and the choice most similar to the prediction is selected as the solution. Extensive experiments show that by incorporating an algebraic treatment, the ALANS learner outperforms various pure connectionist models in domains requiring systematic generalization. We further show the generative nature of the learned algebraic representation; it can be decoded by isomorphism to generate an answer.
C. Zhang, S. Xie, B. Jia—Indicates equal contribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Augustine, S.: The confessions. Clark (1876)
Bahdanau, D., et al.: Systematic generalization: what is required and can it be learned? In: International Conference on Learning Representations (ICLR) (2019)
Bard, J.F.: Practical Bilevel Optimization: Algorithms and Applications, vol. 30. Springer, Dordrecht (2013)
Carpenter, P.A., Just, M.A., Shell, P.: What one intelligence test measures: a theoretical account of the processing in the raven progressive matrices test. Psychol. Rev. 97(3), 404 (1990)
Chen, X., Liang, C., Yu, A.W., Song, D., Zhou, D.: Compositional generalization via neural-symbolic stack machines. In: Advances in Neural Information Processing Systems (2020)
Chen, Z., Mao, J., Wu, J., Wong, K.Y.K., Tenenbaum, J.B., Gan, C.: Grounding physical concepts of objects and events through dynamic visual reasoning. In: International Conference on Learning Representations (ICLR) (2020)
Chollet, F.: The measure of intelligence. arXiv preprint arXiv:1911.01547 (2019)
Colson, B., Marcotte, P., Savard, G.: An overview of bilevel optimization. Ann. Oper. Res. 153(1), 235–256 (2007)
Dong, H., Mao, J., Lin, T., Wang, C., Li, L., Zhou, D.: Neural logic machines. In: International Conference on Learning Representations (ICLR) (2018)
Evans, R., Grefenstette, E.: Learning explanatory rules from noisy data. J. Artif. Intell. Res. (JAIR) 61, 1–64 (2018)
Fodor, J.A.: The Language of Thought, vol. 5. Harvard University Press, Cambridge (1975)
Fodor, J.A., Pylyshyn, Z.W., et al.: Connectionism and cognitive architecture: a critical analysis. Cognition 28(1–2), 3–71 (1988)
d’Avila Garcez, A.S. Broda, K.B., Gabbay, D.M.: Neural-Symbolic Learning Systems: Foundations and Applications. Springer, London (2012)
Han, C., Mao, J., Gan, C., Tenenbaum, J., Wu, J.: Visual concept-metaconcept learning. In: Advances in Neural Information Processing Systems (NeurIPS) (2019)
Hausmann, B.A., Ore, O.: Theory of quasi-groups. Am. J. Math. 59(4), 983–1004 (1937)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Heath, T.L., et al.: The Thirteen Books of Euclid’s Elements. Courier Corporation (1956)
Hill, F., Santoro, A., Barrett, D.G., Morcos, A.S., Lillicrap, T.: Learning to make analogies by contrasting abstract relational structure. In: International Conference on Learning Representations (ICLR) (2019)
Hofstadter, D.R.: Fluid concepts and Creative Analogies: Computer Models of the Fundamental Mechanisms of Thought. Basic Books, New York (1995)
Holyoak, K.J., Ichien, N., Lu, H.: From semantic vectors to analogical mapping. Curr. Dir. Psychol. Sci. 31, 09637214221098054 (2022)
Hu, S., Ma, Y., Liu, X., Wei, Y., Bai, S.: Hierarchical rule induction network for abstract visual reasoning. arXiv preprint arXiv:2002.06838 (2020)
Hudson, D., Manning, C.D.: Learning by abstraction: The neural state machine. In: Advances in Neural Information Processing Systems (2019)
Humphreys, J.E.: Introduction to Lie Algebras and Representation Theory, vol. 9. Springer, New York (2012)
Jaeggi, S.M., Buschkuehl, M., Jonides, J., Perrig, W.J.: Improving fluid intelligence with training on working memory. Proc. Natl. Acad. Sci. (PNAS) 105(19), 6829–6833 (2008)
James, W.: The Principles of Psychology. Henry Holt and Company, New York (1891)
Kansky, K., et al.: Schema networks: zero-shot transfer with a generative causal model of intuitive physics. In: International Conference on Machine Learning (ICML) (2017)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (ICLR) (2014)
Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2013)
Lake, B., Baroni, M.: Generalization without systematicity: On the compositional skills of sequence-to-sequence recurrent networks. In: International Conference on Machine Learning (ICML) (2018)
Little, D.R., Lewandowsky, S., Griffiths, T.L.: A Bayesian model of rule induction in raven’s progressive matrices. In: Annual Meeting of the Cognitive Science Society (CogSci) (2012)
Lovett, A., Forbus, K.: Modeling visual problem solving as analogical reasoning. Psychol. Rev. 124(1), 60 (2017)
Lovett, A., Forbus, K., Usher, J.: A structure-mapping model of Raven’s progressive matrices. In: Annual Meeting of the Cognitive Science Society (CogSci) (2010)
Lovett, A., Tomai, E., Forbus, K., Usher, J.: Solving geometric analogy problems through two-stage analogical mapping. Cogn. Sci. 33(7), 1192–1231 (2009)
Maddy, P.: Believing the axioms. I. J. Symb. Logic 53(2), 481–511 (1988)
Manhaeve, R., Dumancic, S., Kimmig, A., Demeester, T., De Raedt, L.: DeepProbLog: neural probabilistic logic programming. In: Advances in Neural Information Processing Systems (NeurIPS) (2018)
Mao, J., Gan, C., Kohli, P., Tenenbaum, J.B., Wu, J.: The neuro-symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision. In: International Conference on Learning Representations (ICLR) (2019)
Marcus, G.: The Algebraic Mind. MIT Press, Cambridge (2001)
Marcus, G.: The next decade in AI: four steps towards robust artificial intelligence. arXiv preprint arXiv:2002.06177 (2020)
Marcus, G.F., Vijayan, S., Rao, S.B., Vishton, P.M.: Rule learning by seven-month-old infants. Science 283(5398), 77–80 (1999)
McCarthy, J.: Programs with common sense. RLE and MIT Computation Center (1960)
McGreggor, K., Goel, A.: Confident reasoning on raven’s progressive matrices tests. In: AAAI Conference on Artificial Intelligence (AAAI) (2014)
McGreggor, K., Kunda, M., Goel, A.: Fractals and Ravens. Artif. Intell. 215, 1–23 (2014)
Mekik, C.S., Sun, R., Dai, D.Y.: Similarity-based reasoning, Raven’s matrices, and general intelligence. In: International Joint Conference on Artificial Intelligence (IJCAI) (2018)
Newell, A.: Physical symbol systems. Cogn. Sci. 4(2), 135–183 (1980)
Paszke, A., et al.: Automatic differentiation in PyTorch. In: NIPS Autodiff Workshop (2017)
Peano, G.: Arithmetices principia: Nova methodo exposita. Fratres Bocca (1889)
Rahaman, N., et al.: Dynamic inference with neural interpreters. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)
Raven, J.C.: Mental tests used in genetic studies: the performance of related individuals on tests mainly educative and mainly reproductive. Master’s thesis, University of London (1936)
Raven, J.C., Court, J.H.: Raven’s Progressive Matrices and Vocabulary Scales. Oxford Pyschologists Press, Oxford (1998)
Rocktäschel, T., Riedel, S.: End-to-end differentiable proving. In: Advances in Neural Information Processing Systems (NeurIPS) (2017)
Santoro, A., Hill, F., Barrett, D., Morcos, A., Lillicrap, T.: Measuring abstract reasoning in neural networks. In: International Conference on Machine Learning (ICML) (2018)
Santoro, A., et al.: A simple neural network module for relational reasoning. In: Advances in Neural Information Processing Systems (NeurIPS) (2017)
Serafini, L., d’Garcez, A.: Logic tensor networks: deep learning and logical reasoning from data and knowledge. arXiv preprint arXiv:1606.04422 (2016)
Shegheva, S., Goel, A.: The structural affinity method for solving the Raven’s progressive matrices test for intelligence. In: AAAI Conference on Artificial Intelligence (AAAI) (2018)
Spearman, C.: The Nature of “Intelligence’’ and the Principles of Cognition. Macmillan, New York (1923)
Spearman, C.: The Abilities of Man, vol. 6. Macmillan, New York (1927)
Steenbrugge, X., Leroux, S., Verbelen, T., Dhoedt, B.: Improving generalization for abstract reasoning tasks using disentangled feature representations. arXiv preprint arXiv:1811.04784 (2018)
Wang, D., Jamnik, M., Lio, P.: Abstract diagrammatic reasoning with multiplex graph networks. In: International Conference on Learning Representations (ICLR) (2020)
Wang, K., Su, Z.: Automatic generation of Raven’s progressive matrices. In: International Joint Conference on Artificial Intelligence (IJCAI) (2015)
Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3–4), 229–256 (1992)
Winograd, T.: Procedures as a representation for data in a computer program for understanding natural language. Technical report, MIT Center for Space Research (1971)
Wittgenstein, L.: Philosophical Investigations. Philosophische Untersuchungen. Macmillan, New York (1953)
Wu, J., Tenenbaum, J.B., Kohli, P.: Neural scene de-rendering. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Wu, Y., Dong, H., Grosse, R., Ba, J.: The scattering compositional learner: discovering objects, attributes, relationships in analogical reasoning. arXiv preprint arXiv:2007.04212 (2020)
Xu, M., Jiang, G., Zhang, C., Zhu, S.C., Zhu, Y.: EST: evaluating scientific thinking in artificial agents. arXiv preprint arXiv:2206.09203 (2022)
Yi, K., Gan, C., Li, Y., Kohli, P., Wu, J., Torralba, A., Tenenbaum, J.: CLEVRER: collision events for video representation and reasoning. In: International Conference on Learning Representations (ICLR) (2020)
Yi, K., Wu, J., Gan, C., Torralba, A., Kohli, P., Tenenbaum, J.: Neural-symbolic VQA: disentangling reasoning from vision and language understanding. In: Advances in Neural Information Processing Systems (NeurIPS) (2018)
Zhang, C., Gao, F., Jia, B., Zhu, Y., Zhu, S.C.: Raven: A dataset for relational and analogical visual reasoning. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Zhang, C., Jia, B., Edmonds, M., Zhu, S.C., Zhu, Y.: ACRE: abstract causal reasoning beyond covariation. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2021)
Zhang, C., Jia, B., Gao, F., Zhu, Y., Lu, H., Zhu, S.C.: Learning perceptual inference by contrasting. In: Advances in Neural Information Processing Systems (NeurIPS) (2019)
Zhang, C., Jia, B., Zhu, S.C., Zhu, Y.: Abstract spatial-temporal reasoning via probabilistic abduction and execution. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2021)
Zhang, C., Zhu, Y., Zhu, S.C.: MetaStyle: three-way trade-off among speed, flexibility, and quality in neural style transfer. In: AAAI Conference on Artificial Intelligence (AAAI) (2019)
Zhang, W., Zhang, C., Zhu, Y., Zhu, S.C.: Machine number sense: a dataset of visual arithmetic problems for abstract and relational reasoning. In: AAAI Conference on Artificial Intelligence (AAAI) (2020)
Zheng, K., Zha, Z.J., Wei, W.: Abstract reasoning with distracting features. In: Advances in Neural Information Processing Systems (NeurIPS) (2019)
Zhu, S.C., Mumford, D., et al.: A stochastic grammar of images. Found. Trends® Comput. Graph. Vis. 2(4), 259–362 (2007)
Zhu, Y., et al.: Dark, beyond deep: a paradigm shift to cognitive AI with humanlike common sense. Engineering 6(3), 310–345 (2020)
Acknowledgement
We thank Prof. Hongjing Lu and colleagues from UCLA for fruitful discussions. We would also like to thank anonymous reviewers for constructive feedback.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, C., Xie, S., Jia, B., Wu, Y.N., Zhu, SC., Zhu, Y. (2022). Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13699. Springer, Cham. https://doi.org/10.1007/978-3-031-19842-7_40
Download citation
DOI: https://doi.org/10.1007/978-3-031-19842-7_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19841-0
Online ISBN: 978-3-031-19842-7
eBook Packages: Computer ScienceComputer Science (R0)