Timezone: »

A Semantic Loss Function for Deep Learning with Symbolic Knowledge
Jingyi Xu · Zilu Zhang · Tal Friedman · Yitao Liang · Guy Van den Broeck

Wed Jul 11 05:20 AM -- 05:30 AM (PDT) @ Victoria

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 captureshow 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.

Author Information

Jingyi Xu (University of California, Los Angeles)
Zilu Zhang (Peking University)
Tal Friedman (UCLA)
Yitao Liang (UCLA)
Guy Van den Broeck (University of California, Los Angeles)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors