{"type":"ScholarlyArticle","title":"Neural Belief Reasoner","authors":[{"name":"Haifeng Qian","slug":"haifeng-qian","given":"Haifeng","family":"Qian","affiliation":"IBM Research , Yorktown Heights , NY , USA"}],"abstract":"This paper proposes a new generative model called neural belief reasoner (NBR). It differs from previous models in that it specifies a belief function rather than a probability distribution. Its implementation consists of neural networks, fuzzy-set operations and belief-function operations, and query-answering, sample-generation and training algorithms are presented. This paper studies NBR in two tasks. The first is a synthetic unsupervised-learning task, which demonstrates NBR's ability to perform multi-hop reasoning, reasoning with uncertainty and reasoning about conflicting information. The second is supervised learning: a robust MNIST classifier for 4 and 9, which is the most challenging pair of digits. This classifier needs no adversarial training, and it substantially exceeds the state of the art in adversarial robustness as measured by the L2 metric, while at the same time maintains 99.1% accuracy on natural images.","doi":"10.24963/ijcai.2020/590","url":"https://ijcai.org/proceedings/2020/590","pdf":"https://ijcai.org/proceedings/2020/0590.pdf","markdown":"https://ijcai.org/proceedings/2020/590.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/590","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Uncertainty in AI","track":"Main track","number":590,"pages":{"first":4275,"last":4282},"keywords":["Machine Learning: Neuro-Symbolic Methods","Machine Learning: Unsupervised Learning","Uncertainty in AI: Uncertainty Representations","Machine Learning: Adversarial Machine Learning"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24855/file_24855.m3u8","length_sec":281,"provider":"hls"}],"references":[{"position":1,"raw":"[Athalye et al., 2018] Anish Athalye, Nicholas Carlini, and David Wagner. Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples. In International Conference on Machine Learning, 2018.","title":"Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples","authors":"Anish Athalye, Nicholas Carlini, David Wagner","year":"2018","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Baldwin, 1986] James F. Baldwin. Support logic program- ming. In Fuzzy sets theory and applications, pages 133- 170. Springer, 1986.","title":"Support logic programming","authors":"James F Baldwin","year":"1986","venue":"Fuzzy sets theory and applications","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Brendel et al., 2018] Wieland Brendel, Jonas Rauber, and Matthias Bethge. Decision-based adversarial attacks: Re- liable attacks against black-box machine learning models. In International Conference on Learning Representations, 2018.","title":"Decision-based adversarial attacks: Reliable attacks against black-box machine learning models","authors":"Wieland Brendel, Jonas Rauber, Matthias Bethge","year":"2018","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Carlini and Wagner, 2017a] Nicholas Carlini and David Wagner. Adversarial examples are not easily detected: By- passing ten detection methods. In Proceedings of the ACM Workshop on Artificial Intelligence and Security, pages 3- 14. ACM, 2017.","title":"Adversarial examples are not easily detected: Bypassing ten detection methods","authors":"Wagner Carlini, Nicholas Carlini, David Wagner","year":"2017","venue":"Proceedings of the ACM Workshop on Artificial Intelligence and Security","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Carlini and Wagner, 2017b] Nicholas Carlini and David Wagner. Towards evaluating the robustness of neural net- works. In Proceedings of the IEEE Symposium on Security and Privacy, pages 39-57, 2017.","title":"Towards evaluating the robustness of neural networks","authors":"Wagner Carlini, Nicholas Carlini, David Wagner","year":"2017","venue":"Proceedings of the IEEE Symposium on Security and Privacy","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[D'Ambrosio, 1988] Bruce D'Ambrosio. A hybrid approach to reasoning under uncertainty. International Journal of Approximate Reasoning, 2(1):29-45, 1988.","title":"A hybrid approach to reasoning under uncertainty","authors":"D' Bruce, Ambrosio","year":"1988","venue":"International Journal of Approximate Reasoning","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[De Raedt and Kersting, 2008] Luc De Raedt and Kristian Kersting. Probabilistic inductive logic programming. In Probabilistic Inductive Logic Programming: Theory and Applications, pages 1-27. Springer, 2008.","title":"Probabilistic inductive logic programming","authors":"De Raedt, Kersting ; Luc De, Raedt, Kristian Kersting","year":"2008","venue":"Probabilistic Inductive Logic Programming: Theory and Applications","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Denœux, 2000] Thierry Denœux. Modeling vague beliefs using fuzzy-valued belief structures. Fuzzy Sets and Sys- tems, 116(2):167-199, 2000.","title":"Modeling vague beliefs using fuzzy-valued belief structures","authors":"Thierry Denœux","year":"2000","venue":"Fuzzy Sets and Systems","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Evans and Grefenstette, 2018] Richard Evans and Edward Grefenstette. Learning explanatory rules from noisy data. Journal of Artificial Intelligence Research, 61:1-64, 2018.","title":"Learning explanatory rules from noisy data","authors":"Grefenstette Evans, Richard Evans, Edward Grefenstette","year":"2018","venue":"Journal of Artificial Intelligence Research","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Franc ¸a et al., 2014] Manoel VM Franc ¸a, Gerson Zaverucha, and Artur d'Avila Garcez. Fast relational learning us- ing bottom clause propositionalization with artificial neu- ral networks. Machine Learning, 94(1):81-104, 2014.","title":"Fast relational learning using bottom clause propositionalization with artificial neural networks","authors":"Franc ¸a","year":"2014","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Goodfellow et al., 2015] Ian Goodfellow, Jonathon Shlens, and Christian Szegedy. Explaining and harnessing adver- sarial examples. In International Conference on Learning Representations, 2015.","title":"Explaining and harnessing adversarial examples","authors":"Ian Goodfellow, Jonathon Shlens, Christian Szegedy","year":"2015","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Gordon and Shortliffe, 1985] Jean Gordon and Edward H. Shortliffe. A method for managing evidential reasoning in a hierarchical hypothesis space. Artificial Intelligence, 26(3):323-357, 1985.","title":"A method for managing evidential reasoning in a hierarchical hypothesis space","authors":"Gordon, Shortliffe, Jean Gordon, Edward H Shortliffe","year":"1985","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Hinton, 2002] Geoffrey E. Hinton. Training products of ex- perts by minimizing contrastive divergence. Neural Com- putation, 14(8):1771-1800, 2002.","title":"Training products of experts by minimizing contrastive divergence","authors":"Geoffrey E Hinton","year":"2002","venue":"Neural Computation","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kindermann and Snell, 1980] Ross Kindermann and J. Lau- rie Snell. Markov Random Fields and Their Applications. American Mathematical Society, 1980.","title":"Markov Random Fields and Their Applications","authors":"Ross Kindermann, J, Laurie Snell","year":"1980","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Laskey and Lehner, 1988] Kathryn B. Laskey and Paul E. Lehner. Belief maintenance: An integrated approach to uncertainty management. In AAAI Conference on Artificial Intelligence, pages 210-214, 1988.","title":"Belief maintenance: An integrated approach to uncertainty management","authors":"Kathryn B Laskey, Paul E Lehner","year":"1988","venue":"AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lowrance et al., 1986] John D. Lowrance, Thomas D. Gar- vey, and Thomas M. Strat. A framework for evidential- reasoning systems. In AAAI Conference on Artificial Intel- ligence, pages 896-901, 1986.","title":"A framework for evidentialreasoning systems","authors":"John D Lowrance, Thomas D Garvey, Thomas M Strat","year":"1986","venue":"AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Madry et al., 2018] Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. Towards deep learning models resistant to adversarial attacks. In International Conference on Learning Representations, 2018.","title":"Towards deep learning models resistant to adversarial attacks","authors":"Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, Adrian Vladu","year":"2018","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Muggleton and De Raedt, 1994] Stephen Muggleton and Luc De Raedt. Inductive logic programming: Theory and methods. The Journal of Logic Programming, 19:629- 679, 1994.","title":"Inductive logic programming: Theory and methods","authors":"De Muggleton, ; Raedt, Luc Stephen Muggleton, Raedt De","year":"1994","venue":"The Journal of Logic Programming","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Pearl, 1988] Judea Pearl. Probabilistic Reasoning in Intel- ligent Systems: Networks of Plausible Inference. Morgan Kaufmann, 1988.","title":"Judea Pearl. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference","authors":"Pearl","year":"1988","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Qian and Wegman, 2019] Haifeng Qian and Mark N. Weg- man. L2-nonexpansive neural networks. In International Conference on Learning Representations, 2019.","title":"L2-nonexpansive neural networks","authors":"Haifeng Qian, Mark N Wegman","year":"2019","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Raghunathan et al., 2018] Aditi Raghunathan, Jacob Stein- hardt, and Percy Liang. Certified defenses against adver- sarial examples. In International Conference on Learning Representations, 2018.","title":"Certified defenses against adversarial examples","authors":"Aditi Raghunathan, Jacob Steinhardt, Percy Liang","year":"2018","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Rauber et al., 2017] Jonas Rauber, Wieland Brendel, and Matthias Bethge. Foolbox: A python toolbox to bench- mark the robustness of machine learning models. arXiv preprint arXiv:1707.04131, 2017.","title":"Foolbox: A python toolbox to benchmark the robustness of machine learning models","authors":"Rauber","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Richardson and Domingos, 2006] Matthew Richardson and Pedro Domingos. Markov logic networks. Machine Learn- ing, 62(1-2):107-136, 2006.","title":"Matthew Richardson and Pedro Domingos. Markov logic networks","authors":"Domingos Richardson","year":"2006","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Salakhutdinov and Hinton, 2009] Ruslan Salakhutdinov and Geoffrey E. Hinton. Deep Boltzmann machines. In International Conference on Artificial Intelligence and Statistics, 2009.","title":"Deep Boltzmann machines","authors":"Ruslan Salakhutdinov, Geoffrey E Hinton","year":"2009","venue":"International Conference on Artificial Intelligence and Statistics","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Schott et al., 2019] Lukas Schott, Jonas Rauber, Matthias Bethge, and Wieland Brendel. Towards the first adversar- ially robust neural network model on MNIST. In Interna- tional Conference on Learning Representations, 2019.","title":"Towards the first adversarially robust neural network model on MNIST","authors":"Lukas Schott, Jonas Rauber, Matthias Bethge, Wieland Brendel","year":"2019","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Serafini and Garcez, 2016] Luciano Serafini and Ar- tur d'Avila Garcez. Logic tensor networks: Deep learning and logical reasoning from data and knowledge. arXiv preprint arXiv:1606.04422, 2016.","title":"Luciano Serafini and Artur d","authors":"Garcez ; 'avila Serafini, Garcez","year":"2016","venue":"Logic tensor networks: Deep learning and logical reasoning from data and knowledge","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Shafer, 1976] Glenn Shafer. A Mathematical Theory of Ev- idence. Princeton University Press, 1976.","title":"A Mathematical Theory of Evidence","authors":"Glenn Shafer","year":"1976","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Szegedy et al., 2014] Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus. Intriguing properties of neural networks. In International Conference on Learning Representations, 2014.","title":"Intriguing properties of neural networks","authors":"Szegedy","year":"2014","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Tsipras et al., 2019] Dimitris Tsipras, Shibani Santurkar, Logan Engstrom, Alexander Turner, and Aleksander Madry. Robustness may be at odds with accuracy. In Inter- national Conference on Learning Representations, 2019.","title":"Robustness may be at odds with accuracy","authors":"Dimitris Tsipras, Shibani Santurkar, Logan Engstrom, Alexander Turner, Aleksander Madry","year":"2019","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Wan and Kifer, 2009] Hui Wan and Michael Kifer. Be- lief logic programming: uncertainty reasoning with cor- relation of evidence. In Logic Programming and Non- monotonic Reasoning, Lecture Notes in Computer Science, pages 316-328, 2009.","title":"Belief logic programming: uncertainty reasoning with correlation of evidence","authors":"Wan, Kifer ; ] Hui, Wan, Michael Kifer","year":"2009","venue":"Logic Programming and Nonmonotonic Reasoning","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Wong and Kolter, 2018] Eric Wong and Zico Kolter. Prov- able defenses against adversarial examples via the convex outer adversarial polytope. In International Conference on Machine Learning, 2018.","title":"Provable defenses against adversarial examples via the convex outer adversarial polytope","authors":"Kolter Wong, Eric Wong, Zico Kolter","year":"2018","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Yen, 1990] John Yen. Generalizing the Dempster-Shafer theory to fuzzy sets. IEEE Transactions on Systems, Man, and Cybernetics, 20(3):559-570, 1990.","title":"Generalizing the Dempster-Shafer theory to fuzzy sets","authors":"John Yen","year":"1990","venue":"IEEE Transactions on Systems, Man, and Cybernetics","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Zadeh, 1965] Lotfi A. Zadeh. Fuzzy sets. Information and Control, 8(3):338-353, 1965.","title":"Fuzzy sets","authors":"A Lotfi, Zadeh","year":"1965","venue":"Information and Control","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Zadeh, 1979] Lotfi A. Zadeh. Fuzzy sets and information granularity. Advances in Fuzzy Set Theory and Applica- tions, 11:3-18, 1979.","title":"Fuzzy sets and information granularity","authors":"A Lotfi, Zadeh","year":"1979","venue":"Advances in Fuzzy Set Theory and Applications","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}