4 Search Results for "Passerini, Andrea"

Document
DOI: 10.4230/LIPIcs.TIME.2022.12
A Neuro-Symbolic Approach for Real-World Event Recognition from Weak Supervision

Authors: Gianluca Apriceno, Andrea Passerini, and Luciano Serafini

Published in: LIPIcs, Volume 247, 29th International Symposium on Temporal Representation and Reasoning (TIME 2022)

Abstract
Events are structured entities involving different components (e.g, the participants, their roles etc.) and their relations. Structured events are typically defined in terms of (a subset of) simpler, atomic events and a set of temporal relation between them. Temporal Event Detection (TED) is the task of detecting structured and atomic events within data streams, most often text or video sequences, and has numerous applications, from video surveillance to sports analytics. Existing deep learning approaches solve TED task by implicitly learning the temporal correlations among events from data. As consequence, these approaches often fail in ensuring a consistent prediction in terms of the relationship between structured and atomic events. On the other hand, neuro-symbolic approaches have shown their capability to constrain the output of the neural networks to be consistent with respect to the background knowledge of the domain. In this paper, we propose a neuro-symbolic approach for TED in a real world scenario involving sports activities. We show how by incorporating simple knowledge involving the relative order of atomic events and constraints on their duration, the approach substantially outperforms a fully neural solution in terms of recognition accuracy, when little or even no supervision is available on the atomic events.
Cite as

Gianluca Apriceno, Andrea Passerini, and Luciano Serafini. A Neuro-Symbolic Approach for Real-World Event Recognition from Weak Supervision. In 29th International Symposium on Temporal Representation and Reasoning (TIME 2022). Leibniz International Proceedings in Informatics (LIPIcs), Volume 247, pp. 12:1-12:19, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)

Copy BibTex To Clipboard

@InProceedings{apriceno_et_al:LIPIcs.TIME.2022.12,
  author =	{Apriceno, Gianluca and Passerini, Andrea and Serafini, Luciano},
  title =	{{A Neuro-Symbolic Approach for Real-World Event Recognition from Weak Supervision}},
  booktitle =	{29th International Symposium on Temporal Representation and Reasoning (TIME 2022)},
  pages =	{12:1--12:19},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-262-4},
  ISSN =	{1868-8969},
  year =	{2022},
  volume =	{247},
  editor =	{Artikis, Alexander and Posenato, Roberto and Tonetta, Stefano},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.TIME.2022.12},
  URN =		{urn:nbn:de:0030-drops-172594},
  doi =		{10.4230/LIPIcs.TIME.2022.12},
  annote =	{Keywords: structured events, temporal event detection, neuro-symbolic integration}
}
Document
DOI: 10.4230/LIPIcs.TIME.2021.11
A Neuro-Symbolic Approach to Structured Event Recognition

Authors: Gianluca Apriceno, Andrea Passerini, and Luciano Serafini

Published in: LIPIcs, Volume 206, 28th International Symposium on Temporal Representation and Reasoning (TIME 2021)

Abstract
Events are structured entities with multiple components: the event type, the participants with their roles, the outcome, the sub-events etc. A fully end-to-end approach for event recognition from raw data sequence, therefore, should also solve a number of simpler tasks like recognizing the objects involved in the events and their roles, the outcome of the events as well as the sub-events. Ontological knowledge about event structure, specified in logic languages, could be very useful to solve the aforementioned challenges. However, the majority of successful approaches in event recognition from raw data are based on purely neural approaches (mainly recurrent neural networks), with limited, if any, support for background knowledge. These approaches typically require large training sets with detailed annotations at the different levels in which recognition can be decomposed (e.g., video annotated with object bounding boxes, object roles, events and sub-events). In this paper, we propose a neuro-symbolic approach for structured event recognition from raw data that uses "shallow" annotation on the high-level events and exploits background knowledge to propagate this supervision to simpler tasks such as object classification. We develop a prototype of the approach and compare it with a purely neural solution based on recurrent neural networks, showing the higher capability of solving both the event recognition task and the simpler task of object classification, as well as the ability to generalize to events with unseen outcomes.
Cite as

Gianluca Apriceno, Andrea Passerini, and Luciano Serafini. A Neuro-Symbolic Approach to Structured Event Recognition. In 28th International Symposium on Temporal Representation and Reasoning (TIME 2021). Leibniz International Proceedings in Informatics (LIPIcs), Volume 206, pp. 11:1-11:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2021)

Copy BibTex To Clipboard

@InProceedings{apriceno_et_al:LIPIcs.TIME.2021.11,
  author =	{Apriceno, Gianluca and Passerini, Andrea and Serafini, Luciano},
  title =	{{A Neuro-Symbolic Approach to Structured Event Recognition}},
  booktitle =	{28th International Symposium on Temporal Representation and Reasoning (TIME 2021)},
  pages =	{11:1--11:14},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-206-8},
  ISSN =	{1868-8969},
  year =	{2021},
  volume =	{206},
  editor =	{Combi, Carlo and Eder, Johann and Reynolds, Mark},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.TIME.2021.11},
  URN =		{urn:nbn:de:0030-drops-147876},
  doi =		{10.4230/LIPIcs.TIME.2021.11},
  annote =	{Keywords: Event recognition, learning and reasoning, neuro-symbolic integration}
}
Document
DOI: 10.4230/OASIcs.Gabbrielli.11
Derivation of Constraints from Machine Learning Models and Applications to Security and Privacy

Authors: Moreno Falaschi, Catuscia Palamidessi, and Marco Romanelli

Published in: OASIcs, Volume 86, Recent Developments in the Design and Implementation of Programming Languages (2020)

Abstract
This paper shows how we can combine the power of machine learning with the flexibility of constraints. More specifically, we show how machine learning models can be represented by first-order logic theories, and how to derive these theories. The advantage of this representation is that it can be augmented with additional formulae, representing constraints of some kind on the data domain. For instance, new knowledge, or potential attackers, or fairness desiderata. We consider various kinds of learning algorithms (neural networks, k-nearest-neighbours, decision trees, support vector machines) and for each of them we show how to infer the FOL formulae. Then we focus on one particular application domain, namely the field of security and privacy. The idea is to represent the potentialities and goals of the attacker as a set of constraints, then use a constraint solver (more precisely, a solver modulo theories) to verify the satisfiability. If a solution exists, then it means that an attack is possible, otherwise, the system is safe. We show various examples from different areas of security and privacy; specifically, we consider a side-channel attack on a password checker, a malware attack on smart health systems, and a model-inversion attack on a neural network.
Cite as

Moreno Falaschi, Catuscia Palamidessi, and Marco Romanelli. Derivation of Constraints from Machine Learning Models and Applications to Security and Privacy. In Recent Developments in the Design and Implementation of Programming Languages. Open Access Series in Informatics (OASIcs), Volume 86, pp. 11:1-11:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2020)

Copy BibTex To Clipboard

@InProceedings{falaschi_et_al:OASIcs.Gabbrielli.11,
  author =	{Falaschi, Moreno and Palamidessi, Catuscia and Romanelli, Marco},
  title =	{{Derivation of Constraints from Machine Learning Models and Applications to Security and Privacy}},
  booktitle =	{Recent Developments in the Design and Implementation of Programming Languages},
  pages =	{11:1--11:20},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-171-9},
  ISSN =	{2190-6807},
  year =	{2020},
  volume =	{86},
  editor =	{de Boer, Frank S. and Mauro, Jacopo},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.Gabbrielli.11},
  URN =		{urn:nbn:de:0030-drops-132338},
  doi =		{10.4230/OASIcs.Gabbrielli.11},
  annote =	{Keywords: Constraints, machine learning, privacy, security}
}
Document
DOI: 10.4230/DagSemProc.05051.8
Kernels on Prolog Proof Trees:Statistical Learning in the ILP Setting

Authors: Andrea Passerini, Paolo Frasconi, and Luc De Raedt

Published in: Dagstuhl Seminar Proceedings, Volume 5051, Probabilistic, Logical and Relational Learning - Towards a Synthesis (2006)

Abstract
An example-trace is a sequence of steps taken by a program on a given example input. Different approaches exist in order to exploit example-traces for learning, all explicitly inferring a target program from positive and negative traces. We generalize such idea by developing similarity measures betweeen traces in order to learn to discriminate between positive and negative ones. This allows to combine the expressiveness of inductive logic programming in representing knowledge to the statistical properties of kernel machines. Logic programs will be used to generate proofs of given visitor programs which exploit the available background knowledge, while kernel machines will be employed to learn from such proofs.
Cite as

Andrea Passerini, Paolo Frasconi, and Luc De Raedt. Kernels on Prolog Proof Trees:Statistical Learning in the ILP Setting. In Probabilistic, Logical and Relational Learning - Towards a Synthesis. Dagstuhl Seminar Proceedings, Volume 5051, pp. 1-20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2006)

Copy BibTex To Clipboard

@InProceedings{passerini_et_al:DagSemProc.05051.8,
  author =	{Passerini, Andrea and Frasconi, Paolo and De Raedt, Luc},
  title =	{{Kernels on Prolog Proof Trees:Statistical Learning in the ILP Setting}},
  booktitle =	{Probabilistic, Logical and Relational Learning - Towards a Synthesis},
  pages =	{1--20},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2006},
  volume =	{5051},
  editor =	{Luc De Raedt and Thomas Dietterich and Lise Getoor and Stephen H. Muggleton},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.05051.8},
  URN =		{urn:nbn:de:0030-drops-4171},
  doi =		{10.4230/DagSemProc.05051.8},
  annote =	{Keywords: Proof Trees, Logic Kernels, Learning from Traces}
}
  • Refine by Type
  • 4 Document/PDF

  • Refine by Publication Year
  • 1 2022
  • 1 2021
  • 1 2020
  • 1 2006

  • Refine by Author
  • 3 Passerini, Andrea
  • 2 Apriceno, Gianluca
  • 2 Serafini, Luciano
  • 1 De Raedt, Luc
  • 1 Falaschi, Moreno
  • Show More...

  • Refine by Series/Journal
  • 2 LIPIcs
  • 1 OASIcs
  • 1 DagSemProc

  • Refine by Classification
  • 2 Computing methodologies → Activity recognition and understanding
  • 2 Computing methodologies → Temporal reasoning
  • 1 Computing methodologies → Learning paradigms
  • 1 Computing methodologies → Symbolic and algebraic manipulation
  • 1 Security and privacy → Formal security models
  • Show More...

  • Refine by Keyword
  • 2 neuro-symbolic integration
  • 1 Constraints
  • 1 Event recognition
  • 1 Learning from Traces
  • 1 Logic Kernels
  • Show More...

Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2026 Schloss Dagstuhl – LZI GmbH Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact