{"type":"ScholarlyArticle","title":"Teaching LTLf Satisfiability Checking to Neural Networks","authors":[{"name":"Weilin Luo","slug":"weilin-luo","given":"Weilin","family":"Luo","affiliation":"School of Computer Science and Engineering , Sun Yat-sen University , Guangzhou , China"},{"name":"Hai Wan","slug":"hai-wan","given":"Hai","family":"Wan","affiliation":"School of Computer Science and Engineering , Sun Yat-sen University , Guangzhou , China; Key Laboratory of Machine Intelligence and Advanced Computing (Sun Yat- sen University) , Ministry of Education , China"},{"name":"Jianfeng Du","slug":"jianfeng-du","given":"Jianfeng","family":"Du","affiliation":"Guangdong University of Foreign Studies , Guangzhou , China; Pazhou Lab , Guangzhou , China"},{"name":"Xiaoda Li","slug":"xiaoda-li","given":"Xiaoda","family":"Li","affiliation":"School of Computer Science and Engineering , Sun Yat-sen University , Guangzhou , China"},{"name":"Yuze Fu","slug":"yuze-fu","given":"Yuze","family":"Fu","affiliation":"School of Computer Science and Engineering , Sun Yat-sen University , Guangzhou , China"},{"name":"Rongzhen Ye","slug":"rongzhen-ye","given":"Rongzhen","family":"Ye","affiliation":"School of Computer Science and Engineering , Sun Yat-sen University , Guangzhou , China"},{"name":"Delong Zhang","slug":"delong-zhang","given":"Delong","family":"Zhang","affiliation":"School of Computer Science and Engineering , Sun Yat-sen University , Guangzhou , China"}],"abstract":"Linear temporal logic over finite traces (LTLf) satisfiability checking is a fundamental and hard (PSPACE-complete) problem in the artificial intelligence community. We explore teaching end-to-end neural networks to check satisfiability in polynomial time. It is a challenge to characterize the syntactic and semantic features of LTLf via neural networks. To tackle this challenge, we propose LTLfNet, a recursive neural network that captures syntactic features of LTLf by recursively combining the embeddings of sub-formulae. LTLfNet models permutation invariance and sequentiality in the semantics of LTLf through different aggregation mechanisms of sub-formulae. Experimental results demonstrate that LTLfNet achieves good performance in synthetic datasets and generalizes across large-scale datasets. They also show that LTLfNet is competitive with state-of-the-art symbolic approaches such as nuXmv and CDLSC.","doi":"10.24963/ijcai.2022/457","url":"https://ijcai.org/proceedings/2022/457","pdf":"https://ijcai.org/proceedings/2022/0457.pdf","markdown":"https://ijcai.org/proceedings/2022/457.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/457","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Machine Learning","track":"Main Track","number":457,"pages":{"first":3292,"last":3298},"keywords":["Machine Learning: Representation learning"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986850","length_sec":90,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984993","length_sec":338,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Allamanis et al., 2017] Miltiadis Allamanis, Pankajan Chanthirasegaran, Pushmeet Kohli, and Charles Sutton. Learning continuous semantic representations of symbolic expressions. In ICML, volume 70, pages 80-88, 2017.","title":"Learning continuous semantic representations of symbolic expressions","authors":"Allamanis","year":"2017","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Amizadeh et al., 2019] Saeed Amizadeh, Sergiy Matu- sevych, and Markus Weimer. Learning to solve circuit-sat: An unsupervised differentiable approach. In ICLR, 2019.","title":"Learning to solve circuit-sat: An unsupervised differentiable approach","authors":"Saeed Amizadeh, Sergiy Matusevych, Markus Weimer","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cameron et al., 2020] Chris Cameron, Rex Chen, Jason S. Hartford, and Kevin Leyton-Brown. Predicting proposi- tional satisfiability via end-to-end learning. In AAAI, pages 3324-3331, 2020.","title":"Predicting propositional satisfiability via end-to-end learning","authors":"Chris Cameron, Rex Chen, Jason S Hartford, Kevin Leyton-Brown","year":"2020","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cavada et al., 2014] Roberto Cavada, Alessandro Cimatti, Michele Dorigatti, Alberto Griggio, Alessandro Mariotti, Andrea Micheli, Sergio Mover, Marco Roveri, and Stefano Tonetta. The nuxmv symbolic model checker. In CAV, pages 334-342, 2014.","title":"The nuxmv symbolic model checker","authors":"Roberto Cavada, Alessandro Cimatti, Michele Dorigatti, Alberto Griggio, Alessandro Mariotti, Andrea Micheli, Sergio Mover, Marco Roveri, Stefano Tonetta","year":"2014","venue":"CAV","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Degiovanni et al., 2018] Renzo Degiovanni, Facundo Molina, Germán Regis, and Nazareno Aguirre. A genetic algorithm for goal-conflict identification. In ASE, pages 520-531, 2018.","title":"A genetic algorithm for goal-conflict identification","authors":"Renzo Degiovanni, Facundo Molina, Germán Regis, Nazareno Aguirre","year":"2018","venue":"ASE","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Evans et al., 2018] Richard Evans, David Saxton, David Amos, Pushmeet Kohli, and Edward Grefenstette. Can neural networks understand logical entailment? In ICLR, 2018.","title":"Can neural networks understand logical entailment?","authors":"Richard Evans, David Saxton, David Amos, Pushmeet Kohli, Edward Grefenstette","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Fionda and Greco, 2016] Valeria Fionda and Gianluigi Greco. The complexity of LTL on finite traces: Hard and easy fragments. In AAAI, pages 971-977, 2016.","title":"The complexity of LTL on finite traces: Hard and easy fragments","authors":"Greco Fionda, Valeria Fionda, Gianluigi Greco","year":"2016","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Giacomo and Vardi, 2013] Giuseppe De Giacomo and Moshe Y. Vardi. Linear temporal logic and linear dynamic logic on finite traces. In IJCAI, pages 854-860, 2013.","title":"Linear temporal logic and linear dynamic logic on finite traces","authors":"Giacomo, Vardi, Giuseppe De Giacomo, Moshe Y Vardi","year":"2013","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2013/132"},{"position":9,"raw":"[Hahn et al., 2021] Christopher Hahn, Frederik Schmitt, Jens U. Kreber, Markus Norman Rabe, and Bernd Finkbeiner. Teaching temporal logics to neural networks. In ICLR, 2021.","title":"Teaching temporal logics to neural networks","authors":"Christopher Hahn, Frederik Schmitt, Jens U Kreber, Markus Norman Rabe, Bernd Finkbeiner","year":"2021","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Hartford et al., 2018] Jason S. Hartford, Devon R. Graham, Kevin Leyton-Brown, and Siamak Ravanbakhsh. Deep models of interactions across sets. In ICML, volume 80, pages 1914-1923, 2018.","title":"Deep models of interactions across sets","authors":"Jason S Hartford, Devon R Graham, Kevin Leyton-Brown, Siamak Ravanbakhsh","year":"2018","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kim et al., 2019] Joseph Kim, Christian Muise, Ankit Shah, Shubham Agarwal, and Julie Shah. Bayesian inference of linear temporal logic specifications for contrastive expla- nations. In IJCAI, pages 5591-5598, 2019.","title":"Bayesian inference of linear temporal logic specifications for contrastive explanations","authors":"Joseph Kim, Christian Muise, Ankit Shah, Shubham Agarwal, Julie Shah","year":"2019","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2019/776"},{"position":12,"raw":"[Lee et al., 2019] Juho Lee, Yoonho Lee, Jungtaek Kim, Adam R. Kosiorek, Seungjin Choi, and Yee Whye Teh. Set transformer: A framework for attention-based permutation-invariant neural networks. In ICML, vol- ume 97, pages 3744-3753, 2019.","title":"Set transformer: A framework for attention-based permutation-invariant neural networks","authors":"Juho Lee, Yoonho Lee, Jungtaek Kim, Adam R Kosiorek, Seungjin Choi, Yee Whye Teh","year":"2019","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Li et al., 2014] Jianwen Li, Lijun Zhang, Geguang Pu, Moshe Y. Vardi, and Jifeng He. Ltlf satisfiability checking. In ECAI, volume 263, pages 513-518, 2014.","title":"Ltlf satisfiability checking","authors":"Jianwen Li, Lijun Zhang, Geguang Pu, Moshe Y Vardi, Jifeng He","year":"2014","venue":"ECAI","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Li et al., 2020] Jianwen Li, Geguang Pu, Yueling Zhang, Moshe Y. Vardi, and Kristin Y. Rozier. Sat-based explicit ltlf satisfiability checking. Artif. Intell., 289:103369, 2020.","title":"Sat-based explicit ltlf satisfiability checking","authors":"Jianwen Li, Geguang Pu, Yueling Zhang, Moshe Y Vardi, Kristin Y Rozier","year":"2020","venue":"Artif. Intell","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Luo et al., 2021] Weilin Luo, Hai Wan, Xiaotong Song, Binhao Yang, Hongzhen Zhong, and Yin Chen. How to identify boundary conditions with contrasty metric? In ICSE, pages 1473-1484, 2021.","title":"How to identify boundary conditions with contrasty metric?","authors":"Weilin Luo, Hai Wan, Xiaotong Song, Binhao Yang, Hongzhen Zhong, Yin Chen","year":"2021","venue":"ICSE","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Murphy et al., 2019] Ryan L. Murphy, Balasubramaniam Srinivasan, Vinayak A. Rao, and Bruno Ribeiro. Janossy pooling: Learning deep permutation-invariant functions for variable-size inputs. In ICLR, 2019.","title":"Janossy pooling: Learning deep permutation-invariant functions for variable-size inputs","authors":"Ryan L Murphy, Balasubramaniam Srinivasan, A Vinayak, Bruno Rao, Ribeiro","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Paliwal et al., 2020] Aditya Paliwal, Sarah M. Loos, Markus N. Rabe, Kshitij Bansal, and Christian Szegedy. Graph representations for higher-order logic and theorem proving. In AAAI, pages 2967-2974, 2020.","title":"Graph representations for higher-order logic and theorem proving","authors":"Aditya Paliwal, Sarah M Loos, Markus N Rabe, Kshitij Bansal, Christian Szegedy","year":"2020","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Pnueli, 1977] Amir Pnueli. The temporal logic of programs. In FOCS, pages 46-57, 1977.","title":"The temporal logic of programs","authors":"Amir Pnueli, Pnueli","year":"1977","venue":"FOCS","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Schlichtkrull et al., 2018] Michael Sejr Schlichtkrull, Thomas N. Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, and Max Welling. Modeling relational data with graph convolutional networks. In ESWC, volume 10843, pages 593-607, 2018.","title":"Modeling relational data with graph convolutional networks","authors":"Sejr Michael, Thomas N Schlichtkrull, Peter Kipf, Rianne Bloem, Van Den, Ivan Berg, Max Titov, Welling","year":"2018","venue":"ESWC","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Selsam et al., 2019] Daniel Selsam, Matthew Lamm, Benedikt Bünz, Percy Liang, Leonardo de Moura, and David L. Dill. Learning a SAT solver from single-bit supervision. In ICLR, pages 1-11, 2019.","title":"Learning a SAT solver from single-bit supervision","authors":"Daniel Selsam, Matthew Lamm, Benedikt Bünz, Percy Liang, Leonardo De Moura, David L Dill","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Socher et al., 2011] Richard Socher, Jeffrey Pennington, Eric H. Huang, Andrew Y. Ng, and Christopher D. Man- ning. Semi-supervised recursive autoencoders for predict- ing sentiment distributions. In EMNLP, pages 151-161, 2011.","title":"Manning. Semi-supervised recursive autoencoders for predicting sentiment distributions","authors":"Richard Socher, Jeffrey Pennington, Eric H Huang, Andrew Y Ng, Christopher D","year":"2011","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Socher et al., 2013] Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D. Manning, Andrew Y. Ng, and Christopher Potts. Recursive deep models for semantic compositionality over a sentiment treebank. In EMNLP, pages 1631-1642, 2013.","title":"Recursive deep models for semantic compositionality over a sentiment treebank","authors":"Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D Manning, Andrew Y Ng, Christopher Potts","year":"2013","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Vaezipoor et al., 2021] Pashootan Vaezipoor, Andrew C. Li, Rodrigo Toro Icarte, and Sheila A. McIlraith. Ltl2action: Generalizing LTL instructions for multi-task RL. In ICML, volume 139, pages 10497-10508, 2021.","title":"Ltl2action: Generalizing LTL instructions for multi-task RL","authors":"Vaezipoor","year":"2021","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In NeurIPS, pages 5998-6008, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, Illia Polosukhin","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Xiao et al., 2021] Shengping Xiao, Jianwen Li, Shufang Zhu, Yingying Shi, Geguang Pu, and Moshe Y. Vardi. On- the-fly synthesis for LTL over finite traces. In AAAI, pages 6530-6537, 2021.","title":"Onthe-fly synthesis for LTL over finite traces","authors":"Shengping Xiao, Jianwen Li, Shufang Zhu, Yingying Shi, Geguang Pu, Moshe Y Vardi","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Xie et al., 2021] Yaqi Xie, Fan Zhou, and Harold Soh. Em- bedding symbolic temporal knowledge into deep sequen- tial models. In ICRA, pages 4267-4273, 2021.","title":"Embedding symbolic temporal knowledge into deep sequential models","authors":"Yaqi Xie, Fan Zhou, Harold Soh","year":"2021","venue":"ICRA","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zaheer et al., 2017] Manzil Zaheer, Satwik Kottur, Siamak Ravanbakhsh, Barnabás Póczos, Ruslan Salakhutdinov, and Alexander J. Smola. Deep sets. In NeurIPS, pages 3391-3401, 2017.","title":"Deep sets","authors":"Manzil Zaheer, Satwik Kottur, Siamak Ravanbakhsh, Barnabás Póczos, Ruslan Salakhutdinov, Alexander J Smola","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhang et al., 2020] Yan Zhang, Jonathon S. Hare, and Adam Prügel-Bennett. Fspool: Learning set representa- tions with featurewise sort pooling. In ICLR, 2020.","title":"Fspool: Learning set representations with featurewise sort pooling","authors":"Yan Zhang, Jonathon S Hare, Adam Prügel-Bennett","year":"2020","venue":"ICLR","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}