Logic List Mailing Archive

CfP: JAIR Special Track: Integration of Logical Constraints in Deep Learning

(apologies for cross-posting)

=========================
=========================
====================
Special Track on Integration of Logical Constraints in Deep Learning
----------------------------------------------------------------------
Journal of Artificial Intelligence Research (JAIR)
Deadline: May 31, 2025
Info: https://www.jair.org/index.php/jair/SpecialTrack-LogicDL
=========================
=========================
====================
Track Editors:
----------------------------------------------------------------------
Alessandro Abate, University of Oxford, U.K.
Eleonora Giunchiglia, Imperial College London, U.K.
Bettina Knighofer, Graz University of Technology, Austria
Luca Pasa, University of Padova, Italy
Matteo Zavatteri, University of Padova, Italy
=========================
=========================
====================

Overview:

Over the last few years, the integration of logical constraints in Deep Lea
rning models has gained significant attention from research communities for
 its potential to enhance the interpretability, robustness, safety, and gen
eralization capabilities of these models. This integration opens the possib
ility of incorporating prior knowledge, handling incomplete data, and combi
ning symbolic and subsymbolic reasoning. Moreover, the use of logical const
raints improves generalization, formal verification, and ethical decision-m
aking. The versatility of logical constraint integration spans diverse doma
ins, presenting both research challenges and opportunities. In recent times
, there has been a growing trend in incorporating logical constraints into 
deep learning models, especially in safety-critical applications. Looking a
head, challenges in this field extend to the development of Machine Learnin
g models that not only incorporate logical constraints but also provide rob
ust assurances. This involves ensuring that AI systems adhere to specific (
temporal) logical or ethical constraints, offering a level of guarantees in
 their behavior.

Thus, this special track seeks submissions on the integration of logical co
nstraints into deep learning approaches. We are particularly interested in 
the following broad content areas.

- Formal verification of neural networks is an active area of research that
 has been proposing methods, tools, specification languages (e.g., VNNLIB),
 and annual competitions (e.g., VNN-COMP) devoted to verify that a neural n
etwork satisfies a certain property typically given in (a fragment) of firs
t order logic.

- Synthesis aims at synthesizing neural networks that are compliant with so
me given constraint. Approaches to achieve this aim range from modifying th
e loss function in the training phase (i.e., soft constraint injection) to 
exploit counterexample guided inductive synthesis (CEGIS).

- Monitoring: Logical constraints can be used to mitigate and/or neutralize
 constraint violations of machine learning systems when formal verification
 and synthesis are not possible. Shielding techniques intervene by changing
 the output of the network when a constraint is being violated. Runtime mon
itoring can be used to anticipate failures of AI systems without modifying 
them.

- Explainability: Automated learning of formulae and logical constraints fr
om past executions of the system provides natural explanations for neural n
etwork predictions and poses another avenue for future research. Formulae a
nd constraints offer a high degree of explainability since they carry a pre
cise syntax and semantics, and thus they can be "read" by humans more easil
y than other explainability methods.

This special track aims to explore and showcase recent advancements in the 
integration of logical constraints within deep learning models, spanning th
e spectrum of verification, synthesis, monitoring and explainability, by co
nsidering exact and approximate solutions, online and offline approaches. T
he focus will also extend to encompass innovative approaches that address t
he challenges associated with handling logical constraints in neural networ
ks.

Submissions:

This special track seeks contributions that delve into various aspects of l
ogic constraint integration in deep learning, including, but not limited to:

- Learning with logical constraints
- Enhancing neural network expressiveness for logical constraints
- Formal verification (certification) of neural networks
- Automated synthesis of certified neural networks, or of AI systems with n
eural nets
- Decision making: Strategy/policy synthesis for AI systems with neural net
works
- Runtime monitoring of AI systems
- Learning of (temporal) logic formulae for explainable and interpretable AI
- Scalability challenges in neural networks with logical constraints
- Real-world applications of neural networks with logical constraints
- Enhancing model explainability via logical constraints
- Design of neural networks under temporal logical requirements

Pertinent review papers of exceptional quality may also be considered.
--
[LOGIC] mailing list, provided by DLMPST
More information (including information about subscription management) can
be found here: http://dlmpst.org/pages/logic-list.php