Timezone: »

 
Poster
Embedding Symbolic Knowledge into Deep Networks
Yaqi Xie · Ziwei Xu · Kuldeep S Meel · Mohan Kankanhalli · Harold Soh

Thu Dec 12 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #188
in Deep Learning -- Embedding Approaches »

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.

Keywords: Representation Learning · Embedding Approaches · Algorithms · Deep Learning
[ Paper]  [ Poster] 

Author Information

Yaqi Xie (National University of Singapore)
Ziwei Xu (National University of Singapore)
Kuldeep S Meel (National University of Singapore)
Mohan Kankanhalli (National University of Singapore,)
Harold Soh (National University of Singapore (NUS))

More from the Same Authors