Timezone: »
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.
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
-
2022 : Trustworthy Robots for Human-Robot Interaction »
Harold Soh -
2022 Poster: On Scalable Testing of Samplers »
Yash Pote · Kuldeep S Meel -
2022 Poster: Don't Pour Cereal into Coffee: Differentiable Temporal Logic for Temporal Action Segmentation »
Ziwei Xu · Yogesh Rawat · Yongkang Wong · Mohan Kankanhalli · Mubarak Shah -
2021 Poster: Learning to Predict Trustworthiness with Steep Slope Loss »
Yan Luo · Yongkang Wong · Mohan Kankanhalli · Qi Zhao -
2021 Poster: Deep Explicit Duration Switching Models for Time Series »
Abdul Fatir Ansari · Konstantinos Benidis · Richard Kurle · Ali Caner Turkmen · Harold Soh · Alexander Smola · Bernie Wang · Tim Januschowski -
2021 Poster: Unsupervised Motion Representation Learning with Capsule Autoencoders »
Ziwei Xu · Xudong Shen · Yongkang Wong · Mohan Kankanhalli -
2021 Poster: Testing Probabilistic Circuits »
Yash Pote · Kuldeep S Meel -
2020 Poster: On Testing of Samplers »
Kuldeep S Meel · Yash Pote · Sourav Chakraborty -
2020 Poster: Taming Discrete Integration via the Boon of Dimensionality »
Jeffrey Dudek · Dror Fried · Kuldeep S Meel -
2020 Poster: Efficient Distance Approximation for Structured High-Dimensional Distributions via Learning »
Arnab Bhattacharyya · Sutanu Gayen · Kuldeep S Meel · N. V. Vinodchandran -
2018 Poster: Unsupervised Learning of View-invariant Action Representations »
Junnan Li · Yongkang Wong · Qi Zhao · Mohan Kankanhalli