Integrating Learning and Reasoning with Deep Logic Models

By Giuseppe Marra, Francesco Giannini, Michelangelo Diligenti, Marco Gori. 2019

65 citations recorded by the source corpus.

Deep learning is very effective at jointly learning feature representations and classification models, especially when dealing with high dimensional input patterns. Probabilistic logic reasoning, on the other hand, is capable to take consistent and robust decisions in complex environments. The integration of deep learning and logic reasoning is still an open-research problem and it is considered to be the key for the development of real intelligent agents. This paper presents Deep Logic Models, which are deep graphical models integrating deep learning and logic reasoning both for learning and inference. Deep Logic Models create an end-to-end differentiable architecture, where deep learners are embedded into a network implementing a continuous relaxation of the logic knowledge. The learning process allows to jointly learn the weights of the deep learners and the meta-parameters controlling the high-level reasoning. The experimental results show that the proposed methodology overtakes the limitations of the other approaches that have been proposed to bridge deep learning and reasoning.

Subfields: Artificial Intelligence, Prompting & Reasoning, Knowledge Graphs & Representation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Prompting & Reasoning

In Knowledge Graphs & Representation

Citations in the corpus

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, positive): “Combining connectionist and symbolic paradigms seems a favourable way to address this challenge [169,299,312,352,353] .”
Conversational Neuro-Symbolic Commonsense Reasoning (2020, background): “They have shown promise in different areas of logical reasoning ranging from classical logic to propositional logic, probabilistic logic, abductive logic, and inductive logic (Mao et al. 2019; Manhaeve et al. 2018; Dong et al. 2019; Marra et al. 2019; Zhou 2019; Evans and Grefenstette 2018).”
Better Set Representations For Relational Reasoning (2020, background): “Proposals for moving towards System 2 reasoning in learning systems involve creating new abilities for composition, combinatorial generalization, and disentanglement [2, 13, 17].”
Set-Structured Latent Representations (2020, background): “Proposals for moving towards System 2 reasoning in learning systems involve creating new abilities for composition, combinatorial generalization, and disentanglement (Battaglia et al., 2018; van Steenkiste et al., 2019; Marra et al., 2019).”
Augmenting large language models with chemistry tools (2023, methodology): “Using a variety of chemistry-related packages and software, a set of tools is created.”
Logic Tensor Networks (2020, methodology): “Among the approaches that modify the predictions of the neural network using logical constraints are Deep Logic Models [46] and Knowledge Enhanced Neural Networks [15].”