Embedding Symbolic Knowledge into Deep Networks
This work addresses the challenge of combining symbolic reasoning with neural networks for researchers in AI and machine learning, representing an incremental advancement in hybrid AI methods.
The paper tackles the problem of integrating symbolic knowledge into deep networks to enhance model performance, achieving improvements in entailment checking and visual relation prediction tasks.
In this work, we aim to leverage prior symbolic knowledge to improve the performance of deep models. We propose a graph embedding network that projects propositional formulae (and assignments) onto a manifold via an augmented Graph Convolutional Network (GCN). To generate semantically-faithful embeddings, we develop techniques to recognize node heterogeneity, and semantic regularization that incorporate structural constraints into the embedding. Experiments show that our approach improves the performance of models trained to perform entailment checking and visual relation prediction. Interestingly, we observe a connection between the tractability of the propositional theory representation and the ease of embedding. Future exploration of this connection may elucidate the relationship between knowledge compilation and vector representation learning.