LYRICS: a General Interface Layer to Integrate Logic Inference and Deep Learning
This addresses the problem of combining low-level deep learning with high-level symbolic reasoning for AI agents in complex environments, representing a novel method for a known bottleneck rather than an incremental improvement.
The paper tackles the integration of symbolic logic inference with deep learning by introducing LYRICS, a general interface layer implemented in TensorFlow that converts First Order Logic knowledge into real-valued constraints for optimization, enabling learning under prior knowledge constraints. It demonstrates the approach's generality through use cases like model checking, supervised learning, and collective classification.
In spite of the amazing results obtained by deep learning in many applications, a real intelligent behavior of an agent acting in a complex environment is likely to require some kind of higher-level symbolic inference. Therefore, there is a clear need for the definition of a general and tight integration between low-level tasks, processing sensorial data that can be effectively elaborated using deep learning techniques, and the logic reasoning that allows humans to take decisions in complex environments. This paper presents LYRICS, a generic interface layer for AI, which is implemented in TersorFlow (TF). LYRICS provides an input language that allows to define arbitrary First Order Logic (FOL) background knowledge. The predicates and functions of the FOL knowledge can be bound to any TF computational graph, and the formulas are converted into a set of real-valued constraints, which participate to the overall optimization problem. This allows to learn the weights of the learners, under the constraints imposed by the prior knowledge. The framework is extremely general as it imposes no restrictions in terms of which models or knowledge can be integrated. In this paper, we show the generality of the approach showing some use cases of the presented language, including model checking, supervised learning and collective classification.