A Semantic Loss Function for Deep Learning with Symbolic Knowledge
This work addresses the challenge of incorporating symbolic knowledge into deep learning, particularly for tasks involving structured output prediction, which is difficult for traditional neural networks.
This paper introduces a semantic loss function that integrates symbolic knowledge into deep learning by measuring how close a neural network's output is to satisfying logical constraints. This approach achieves near-state-of-the-art results in semi-supervised multi-class classification and significantly improves the prediction of structured objects like rankings and paths.
This paper develops a novel methodology for using symbolic knowledge in deep learning. From first principles, we derive a semantic loss function that bridges between neural output vectors and logical constraints. This loss function captures how close the neural network is to satisfying the constraints on its output. An experimental evaluation shows that it effectively guides the learner to achieve (near-)state-of-the-art results on semi-supervised multi-class classification. Moreover, it significantly increases the ability of the neural network to predict structured objects, such as rankings and paths. These discrete concepts are tremendously difficult to learn, and benefit from a tight integration of deep learning and symbolic reasoning methods.