2000 character limit reached
PiShield: A PyTorch Package for Learning with Requirements
Published 28 Feb 2024 in cs.LG, cs.AI, and cs.LO | (2402.18285v2)
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.
- Pylon: A PyTorch Framework for Learning with Constraints. In Proceedings of Neural Information Processing Systems 2021 Competitions and Demonstrations Track. PMLR, 2022.
- Semantic probabilistic layers for neuro-symbolic learning. In Proceedings of Neural Information Processing Systems, 2022.
- Neuro-symbolic entropy regularization. In Proceedings of the Conference on Uncertainty in Artificial Intelligence, 2022.
- Logic tensor networks. Artificial Intelligence, 303, 2022.
- Tommaso Carraro. LTNtorch: PyTorch implementation of Logic Tensor Networks, 2022.
- Amanda Clare. Machine Learning and Data Mining for Yeast Functional Genomics. PhD thesis, University of Wales, 2003.
- Neural-symbolic computing: An effective methodology for principled integration of machine learning and reasoning. CoRR, abs/1905.06088, 2019.
- ImageNet: A large-scale hierarchical image database. In Proceedings of Conference on Computer Vision and Pattern Recognition, 2009.
- Bridging logic and kernel machines. Machine Learning, 2012.
- Integrating prior knowledge into deep learning. In Proceedings of International Conference on Machine Learning and Applications, 2017.
- Hierchical annotation of medical images. In Proc. of IS. IJS Ljubljana, 2008.
- Logic tensor networks for semantic image interpretation. In Proceedings of International Joint Conference on Artificial Intelligence, 2017.
- DL2: Training and querying neural networks with logic. In Proceedings of International Conference on Machine Learning, 2019.
- Coherent hierarchical multi-label classification networks. In Proceedings of Neural Information Processing Systems, 2020.
- Multi-label classification neural networks with hard logical constraints. Journal of Artificial Intelligence Research, 72, 2021.
- Deep learning with logical constraints. In Proceedings of International Joint Conference on Artificial Intelligence, 2022.
- ROAD-R: The autonomous driving dataset for learning with requirements. Machine Learning Journal, 2023.
- CCN+: A neuro-symbolic framework for deep learning with requirements. International Journal of Approximate Reasoning, 2024. In press.
- MultiplexNet: Towards fully satisfied logical constraints in neural networks. In Proceedings of Association for the Advancement of Artificial Intelligence, 2022.
- The Enron Corpus: A new dataset for email classification research. In Proceedings of European Conference on Machine Learning, 2004.
- RCV1: A new benchmark collection for text categorization research. J. Mach. Learn. Res., 5, 2004.
- Learning with logical constraints but without shortcut satisfaction. In Proceedings of International Conference on Learning Representations, 2023.
- DeepProbLog: Neural probabilistic logic programming. In Proceedings of Neural Information Processing Systems, 2018.
- A primal dual formulation for deep learning with constraints. In Proceedings of Neural Information Processing Systems, 2019.
- ROAD: The ROad event Awareness Dataset for autonomous driving. IEEE Trans. Pattern Anal. Mach. Intell., 2023.
- Exploiting T-norms for Deep Learning in Autonomous Driving. In Proceedings of International Workshop on Neural-Symbolic Learning and Reasoning, 2023.
- How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Data. In Proceedings of International Conference on Learning Representations, 2024.
- A-neSI: A scalable approximate method for probabilistic neurosymbolic inference. In Proceedings of Neural Information Processing Systems, 2023.
- Decision trees for hierarchical multi-label classification. Mach. Learn., 73(2), 2008.
- Hierarchical multi-label classification networks. In Proceedings of International Conference on Machine Learning, 2018.
- A semantic loss function for deep learning with symbolic knowledge. In Proceedings of International Conference on Machine Learning, 2018.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
