Publications
You can also find my articles on my Google Scholar profile.
Published in ICLR, 2024
In this paper, we show how deep generative models for tabular data can be constrained such that their generated samples are guaranteed to be compliant with given constraints. This is achieved by automatically parsing the constraints and transforming them into a Constraint Layer seamlessly integrated with the model.
Recommended citation: Mihaela C. Stoian, Salijona Dyrmishi, Maxime Cordy, Thomas Lukasiewicz, Eleonora Giunchiglia. How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Data. In Proceedings of ICLR 2024.
Published in International Journal of Approximate Reasoning, 2024
In this paper, we propose a novel neuro-symbolic framework able to make any neural network compliant by design to a given set of requirements over the output space expressed in full propositional logic. This framework, called CCN+, integrates the requirements into the output layer of the neural network by applying multiple inference rules that ensure compliance with the requirements and adapts the standard binary cross-entropy loss function to the requirement output layer.
Recommended citation: Eleonora Giunchiglia‚ Alex Tatomir‚ Mihaela C. Stoian, Thomas Lukasiewicz. CCN+: A neuro-symbolic framework for deep learning with requirements. International Journal of Approximate Reasoning, 2024. (In Press)
Published in IJCAI, 2024
In this paper, we introduce PiShield, the first package ever allowing for the integration of (propositional or linear) requirements into the neural networks’ topology. PiShield guarantees compliance with these requirements, regardless of input.
Recommended citation: Mihaela C. Stoian, Alex Tatomir, Thomas Lukasiewicz, Eleonora Giunchiglia. PiShield: A NeSy Framework for Learning with Requirements. arXiv preprint 2402.18285, 2024. Accepted at IJCAI 2024.
Published in NeSy, 2023
In this paper, we show how it is possible to define memory-efficient t-norm-based losses, allowing for exploiting t-norms for the task of event detection in autonomous driving.
Recommended citation: Mihaela C. Stoian, Eleonora Giunchiglia, Thomas Lukasiewicz. Exploiting T-norms for Deep Learning in Autonomous Driving. In Proceedings of the 17th International Workshop on Neural-Symbolic Learning and Reasoning (NeSy), 2023.
Published in Machine Learning, 2023
In this paper, we introduce the ROad event Awareness Dataset with logical Requirements (ROAD-R), the first publicly available dataset for autonomous driving with requirements expressed as logical constraints. The paper was presented at IJCLR 2022, where it received the Best Student Paper Prize, and at IJCAI 2022 Workshop on Artificial Intelligence for Autonomous Driving, where it received the Best Paper Award.
Recommended citation: Eleonora Giunchiglia, Mihaela C. Stoian, Salman Khan, Fabio Cuzzolin, Thomas Lukasiewicz. ROAD-R: The Autonomous Driving Dataset with Logical Requirements. Machine Learning, 112, 3261–3291 (2023).
Published in IJCAI, Survey Track, 2022
In this survey, we retrace works which exploit logically specified background knowledge in order to obtain neural models (i) with a better performance, (ii) able to learn from less data, and/or (iii) guaranteed to be compliant with the background knowledge itself, e.g., for safety-critical applications.
Recommended citation: Eleonora Giunchiglia, Mihaela C. Stoian, Thomas Lukasiewicz. Deep Learning with Logical Constraints. In Proceedings of International Joint Conference on Artificial Intelligence, 2022.
Published in CVPR 2021 Workshop on 3D Vision and Robotics, 2021
In this paper we present a novel method to estimate planar reflective symmetries that efficiently handles 3D inputs by slicing the data along the height dimension and passing it sequentially to a 2D convolutional recurrent regression scheme.
Recommended citation: Mihaela C. Stoian, Tommaso Cavallari. Recurrently Estimating Reflective Symmetry Planes from Partial Pointclouds. CVPR Workshop on 3D Vision and Robotics, 2021.
Published in ICASSP, 2020
In this paper we explore what factors help pretraining for low-resource automatic speech-to-text translation (AST). We show that the word error rate (WER) of the pre-trained automatic speech recognition (ASR) models is likely the best direct predictor of AST performance. Additionally, our analysis suggests that the models with better WER are transparently encoding more language-universal phonetic information in the later RNN layers, and this appears to help with AST.
Recommended citation: Mihaela C. Stoian, Sameer Bansal, Sharon Goldwater. Analyzing ASR pretraining for low-resource speech-to-text translation. In Proceedings of ICASSP, 2020.
