{"type":"ScholarlyArticle","title":"PiShield: A PyTorch Package for Learning with Requirements","authors":[{"name":"Mihaela C. Stoian","slug":"mihaela-c-stoian","given":"Mihaela C.","family":"Stoian","affiliation":"Department of Computer Science , University of Oxford , UK"},{"name":"Alex Tatomir","slug":"alex-tatomir","given":"Alex","family":"Tatomir","affiliation":"Department of Computer Science , University of Oxford , UK"},{"name":"Thomas Lukasiewicz","slug":"thomas-lukasiewicz","given":"Thomas","family":"Lukasiewicz","affiliation":"Institute of Logic and Computation , Vienna University of Technology , Austria; Department of Computer Science , University of Oxford , UK"},{"name":"Eleonora Giunchiglia","slug":"eleonora-giunchiglia","given":"Eleonora","family":"Giunchiglia","affiliation":"Institute of Logic and Computation , Vienna University of Technology , Austria"}],"abstract":"Deep learning models have shown their strengths in various application domains, however, they often struggle to meet safety requirements for their outputs. In this paper, we introduce PiShield, the first package ever allowing for the integration of the requirements into the neural networks' topology. PiShield guarantees compliance with these requirements, regardless of input. Additionally, it allows for integrating requirements both at inference and/or training time, depending on the practitioners' needs. Given the widespread application of deep learning, there is a growing need for frameworks allowing for the integration of the requirements across various domains. Here, we explore three application scenarios: functional genomics, autonomous driving, and tabular data generation.","doi":"10.24963/ijcai.2024/1037","url":"https://ijcai.org/proceedings/2024/1037","pdf":"https://ijcai.org/proceedings/2024/1037.pdf","markdown":"https://ijcai.org/proceedings/2024/1037.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/1037","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Demo Track","track":"Demo Track","number":1037,"pages":{"first":8805,"last":8809},"keywords":["AI Ethics, Trust, Fairness: ETF: Safety and robustness","Machine Learning: ML: Neuro-symbolic methods","Machine Learning: ML: Knowledge-aided learning","Machine Learning: ML: Structured prediction"],"videos":[],"references":[{"position":1,"raw":"[Ahmed et al., 2022a] Kareem Ahmed, Tao Li, Thy Ton, Quan Guo, Kai-Wei Chang, Parisa Kordjamshidi, Vivek Srikumar, Guy Van den Broeck, and Sameer Singh. Py- lon: A PyTorch Framework for Learning with Constraints. In Proceedings of Neural Information Processing Systems 2021 Competitions and Demonstrations Track. PMLR, 2022.","title":"Pylon: A PyTorch Framework for Learning with Constraints","authors":"Ahmed","year":"2022","venue":"Proceedings of Neural Information Processing Systems 2021 Competitions and Demonstrations Track","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Ahmed et al., 2022b] Kareem Ahmed, Stefano Teso, Kai- Wei Chang, Guy Van den Broeck, and Antonio Vergari. Semantic probabilistic layers for neuro-symbolic learning. In Proceedings of Neural Information Processing Systems, 2022.","title":"Semantic probabilistic layers for neuro-symbolic learning","authors":"Ahmed","year":"2022","venue":"Proceedings of Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Ahmed et al., 2022c] Kareem Ahmed, Eric Wang, Kai-Wei Chang, and Guy Van den Broeck. Neuro-symbolic entropy regularization. In Proceedings of the Conference on Un- certainty in Artificial Intelligence, 2022.","title":"Neuro-symbolic entropy regularization","authors":"Ahmed","year":"2022","venue":"Proceedings of the Conference on Uncertainty in Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Badreddine et al., 2022] Samy Badreddine, Artur d'Avila Garcez, Luciano Serafini, and Michael Spranger. Logic tensor networks. Artificial Intelligence, 303, 2022.","title":"Logic tensor networks","authors":"Samy Badreddine, Artur D'avila, Luciano Garcez, Michael Serafini, Spranger","year":"2022","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Carraro, 2022] Tommaso Carraro. LTNtorch: PyTorch im- plementation of Logic Tensor Networks, 2022.","title":"LTNtorch: PyTorch implementation of Logic Tensor Networks","authors":"Tommaso Carraro","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Clare, 2003] Amanda Clare. Machine Learning and Data Mining for Yeast Functional Genomics. PhD thesis, Uni- versity of Wales, 2003.","title":"Machine Learning and Data Mining for Yeast Functional Genomics","authors":"Amanda Clare","year":"2003","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"['Avila Garcez et al., 2019] Artur S. d'Avila Garcez, Marco Gori, Luís C. Lamb, Luciano Serafini, Michael Spranger, and Son N. Tran. Neural-symbolic computing: An effective methodology for principled integration of machine learning and reasoning. CoRR, abs/1905.06088, 2019.","title":"Neural-symbolic computing: An effective methodology for principled integration of machine learning and reasoning","authors":"Artur S Garcez, Marco Gori, Luís C Lamb, Luciano Serafini, Michael Spranger, Son N Tran","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Deng et al., 2009] Jia Deng, Wei Dong, Richard Socher, Li- Jia Li, Kai Li, and Fei-Fei Li. ImageNet: A large-scale hierarchical image database. In Proceedings of Conference on Computer Vision and Pattern Recognition, 2009.","title":"ImageNet: A large-scale hierarchical image database","authors":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Fei-Fei Li","year":"2009","venue":"Proceedings of Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Diligenti et al., 2012] Michelangelo Diligenti, Marco Gori, Marco Maggini, and Leonardo Rigutini. Bridging logic and kernel machines. Machine Learning, 2012.","title":"Bridging logic and kernel machines","authors":"Diligenti","year":"2012","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Diligenti et al., 2017] Michelangelo Diligenti, Soumali Roychowdhury, and Marco Gori. Integrating prior knowl- edge into deep learning. In Proceedings of International Conference on Machine Learning and Applications, 2017.","title":"Michelangelo Diligenti, Soumali Roychowdhury, and Marco Gori. Integrating prior knowledge into deep learning","authors":"Diligenti","year":"2017","venue":"Proceedings of International Conference on Machine Learning and Applications","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Dimitrovski et al., 2008] Ivica Dimitrovski, Dragi Kocev, Suzana Loskovska, and Sašo Džeroski. Hierchical anno- tation of medical images. In Proc. of IS. IJS Ljubljana, 2008.","title":"Hierchical annotation of medical images","authors":"Dimitrovski","year":"2008","venue":"Proc. of IS. IJS Ljubljana","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Donadello et al., 2017] Ivan Donadello, Luciano Serafini, and Artur d'Avila Garcez. Logic tensor networks for se- mantic image interpretation. In Proceedings of Interna- tional Joint Conference on Artificial Intelligence, 2017.","title":"Logic tensor networks for semantic image interpretation","authors":"Ivan Donadello, Luciano Serafini, Artur D'avila Garcez","year":"2017","venue":"Proceedings of International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2017/221"},{"position":13,"raw":"[Fischer et al., 2019] Marc Fischer, Mislav Balunovic, Dana Drachsler-Cohen, Timon Gehr, Ce Zhang, and Martin Vechev. DL2: Training and querying neural networks with logic. In Proceedings of International Conference on Ma- chine Learning, 2019.","title":"DL2: Training and querying neural networks with logic","authors":"Marc Fischer, Mislav Balunovic, Dana Drachsler-Cohen, Timon Gehr, Ce Zhang, Martin Vechev","year":"2019","venue":"Proceedings of International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Giunchiglia and Lukasiewicz, 2020] Eleonora Giunchiglia and Thomas Lukasiewicz. Coherent hierarchical multi- label classification networks. In Proceedings of Neural Information Processing Systems, 2020.","title":"Coherent hierarchical multilabel classification networks","authors":"Lukasiewicz Giunchiglia, Eleonora Giunchiglia, Thomas Lukasiewicz","year":"2020","venue":"Proceedings of Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Giunchiglia and Lukasiewicz, 2021] Eleonora Giunchiglia and Thomas Lukasiewicz. Multi-label classification neural networks with hard logical constraints. Journal of Artifi- cial Intelligence Research, 72, 2021.","title":"Multi-label classification neural networks with hard logical constraints","authors":"Lukasiewicz Giunchiglia, Eleonora Giunchiglia, Thomas Lukasiewicz","year":"2021","venue":"Journal of Artificial Intelligence Research","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Giunchiglia et al., 2022] Eleonora Giunchiglia, Mi- haela Catalina Stoian, and Thomas Lukasiewicz. Deep learning with logical constraints. In Proceedings of International Joint Conference on Artificial Intelligence, 2022.","title":"Deep learning with logical constraints","authors":"Eleonora Giunchiglia, Mihaela Catalina Stoian, Thomas Lukasiewicz","year":"2022","venue":"Proceedings of International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2022/767"},{"position":17,"raw":"[Giunchiglia et al., 2023a] Eleonora Giunchiglia, Fergus Imrie, Mihaela van der Schaar, and Thomas Lukasiewicz. Machine Learning with Requirements: a Manifesto. CoRR, abs/2304.03674, 2023.","title":"Machine Learning with Requirements: a Manifesto","authors":"Giunchiglia","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Giunchiglia et al., 2023b] Eleonora Giunchiglia, Mi- haela Cȃtȃlina Stoian, Salman Khan, Fabio Cuzzolin, and Thomas Lukasiewicz. ROAD-R: The autonomous driving dataset for learning with requirements. Machine Learning Journal, 2023.","title":"ROAD-R: The autonomous driving dataset for learning with requirements","authors":"Giunchiglia","year":"2023","venue":"Machine Learning Journal","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Giunchiglia et al., 2024] Eleonora Giunchiglia, Alex Tatomir, Mihaela Catalina Stoian, and Thomas Lukasiewicz. CCN+: A neuro-symbolic framework for deep learning with requirements. International Journal of Approximate Reasoning, 2024. In press.","title":"CCN+: A neuro-symbolic framework for deep learning with requirements","authors":"Eleonora Giunchiglia, Alex Tatomir, Mihaela Catalina Stoian, Thomas Lukasiewicz","year":"2024","venue":"International Journal of Approximate Reasoning","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Hoernle et al., 2022] Nicholas Hoernle, Rafael-Michael Karampatsis, Vaishak Belle, and Kobi Gal. MultiplexNet: Towards fully satisfied logical constraints in neural net- works. In Proceedings of Association for the Advancement of Artificial Intelligence, 2022.","title":"MultiplexNet: Towards fully satisfied logical constraints in neural networks","authors":"Nicholas Hoernle, Rafael-Michael Karampatsis, Vaishak Belle, Kobi Gal","year":"2022","venue":"Proceedings of Association for the Advancement of Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Klimt and Yang, 2004] Bryan Klimt and Yiming Yang. The Enron Corpus: A new dataset for email classification re- search. In Proceedings of European Conference on Ma- chine Learning, 2004.","title":"The Enron Corpus: A new dataset for email classification research","authors":"Bryan Klimt, Yiming Yang","year":"2004","venue":"Proceedings of European Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Lewis et al., 2004] David D. Lewis, Yiming Yang, Tony G. Rose, and Fan Li. RCV1: A new benchmark collection for text categorization research. J. Mach. Learn. Res., 5, 2004.","title":"RCV1: A new benchmark collection for text categorization research","authors":"David D Lewis, Yiming Yang, Tony G Rose, Fan Li","year":"2004","venue":"J. Mach. Learn. Res","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Li et al., 2023] Zenan Li, Zehua Liu, Yuan Yao, Jingwei Xu, Taolue Chen, Xiaoxing Ma, and Jian Lü. Learning with logical constraints but without shortcut satisfaction. In Proceedings of International Conference on Learning Representations, 2023.","title":"Learning with logical constraints but without shortcut satisfaction","authors":"Zenan Li, Zehua Liu, Yuan Yao, Jingwei Xu, Taolue Chen, Xiaoxing Ma, Jian Lü","year":"2023","venue":"Proceedings of International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Manhaeve et al., 2018] Robin Manhaeve, Sebastijan Du- mancic, Angelika Kimmig, Thomas Demeester, and Luc De Raedt. DeepProbLog: Neural probabilistic logic pro- gramming. In Proceedings of Neural Information Process- ing Systems, 2018.","title":"DeepProbLog: Neural probabilistic logic programming","authors":"Manhaeve","year":"2018","venue":"Proceedings of Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Nandwani et al., 2019] Yatin Nandwani, Abhishek Pathak, Mausam, and Parag Singla. A primal dual formulation for deep learning with constraints. In Proceedings of Neural Information Processing Systems, 2019.","title":"A primal dual formulation for deep learning with constraints","authors":"Yatin Nandwani, Abhishek Pathak, Mausam, Parag Singla","year":"2019","venue":"Proceedings of Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Singh et al., 2023] Gurkirt Singh, Stephen Akrigg, Manuele Di Maio, Valentina Fontana, Reza Javan- mard Alitappeh, Salman Khan, Suman Saha, Kossar Jeddi Saravi, Farzad Yousefi, Jacob Culley, Tom Nicholson, Jordan Omokeowa, Stanislao Grazioso, Andrew Bradley, Giuseppe Di Gironimo, and Fabio Cuzzolin. ROAD: The ROad event Awareness Dataset for autonomous driving. IEEE Trans. Pattern Anal. Mach. Intell., 2023.","title":"ROAD: The ROad event Awareness Dataset for autonomous driving","authors":"Singh","year":"2023","venue":"IEEE Trans. Pattern Anal. Mach. Intell","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Stoian et al., 2023] Mihaela C. Stoian, Eleonora Giunchiglia, and Thomas Lukasiewicz. Exploiting T-norms for Deep Learning in Autonomous Driving. In Proceedings of International Workshop on Neural- Symbolic Learning and Reasoning, 2023.","title":"Exploiting T-norms for Deep Learning in Autonomous Driving","authors":"C Mihaela, Eleonora Stoian, Thomas Giunchiglia, Lukasiewicz","year":"2023","venue":"Proceedings of International Workshop on Neural-Symbolic Learning and Reasoning","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Stoian et al., 2024] Mihaela C. Stoian, Salijona Dyrmishi, Maxime Cordy, Thomas Lukasiewicz, and Eleonora Giunchiglia. How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Data. In Proceedings of International Conference on Learning Representations, 2024.","title":"How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Data","authors":"C Mihaela, Salijona Stoian, Maxime Dyrmishi, Thomas Cordy, Eleonora Lukasiewicz, Giunchiglia","year":"2024","venue":"Proceedings of International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[van Krieken et al., 2023] Emile van Krieken, Thiviyan Thanapalasingam, Jakub M. Tomczak, Frank Van Harme- len, and Annette Ten Teije. A-neSI: A scalable approx- imate method for probabilistic neurosymbolic inference. In Proceedings of Neural Information Processing Systems, 2023.","title":"A-neSI: A scalable approximate method for probabilistic neurosymbolic inference","authors":"Van Krieken","year":"2023","venue":"Proceedings of Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Vens et al., 2008] Celine Vens, Jan Struyf, Leander Schiet- gat, Saso Dzeroski, and Hendrik Blockeel. Decision trees for hierarchical multi-label classification. Mach. Learn., 73(2), 2008.","title":"Decision trees for hierarchical multi-label classification","authors":"Vens","year":"2008","venue":"Mach. Learn","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Wehrmann et al., 2018] Jonatas Wehrmann, Ricardo Cerri, and Rodrigo Barros. Hierarchical multi-label classification networks. In Proceedings of International Conference on Machine Learning, 2018.","title":"Hierarchical multi-label classification networks","authors":"Wehrmann","year":"2018","venue":"Proceedings of International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Xu et al., 2018] Jingyi Xu, Zilu Zhang, Tal Friedman, Yitao Liang, and Guy Van den Broeck. A semantic loss func- tion for deep learning with symbolic knowledge. In Pro- ceedings of International Conference on Machine Learn- ing, 2018.","title":"A semantic loss function for deep learning with symbolic knowledge","authors":"Jingyi Xu, Zilu Zhang, Tal Friedman, Yitao Liang, Guy Van Den Broeck","year":"2018","venue":"Proceedings of International Conference on Machine Learning","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}