Abstract

Neural Structured Learning (NSL) is a new learning paradigm to train neural networks by leveraging structured signals in addition to feature inputs. Structure can be explicit as represented by a graph or implicit as induced by adversarial perturbation. Structured signals are commonly used to represent relations or similarity among samples that may be labeled or unlabeled. Therefore, leveraging these signals during neural network training harnesses both labeled and unlabeled data, which can improve model accuracy, particularly when the amount of labeled data is relatively small. Additionally, models trained with samples that are generated by adding adversarial perturbation have been shown to be robust against malicious attacks. NSL has been open sourced as part of TF ecosystem, and we will also introduce its industrial applications on both NLP and machine perception.

All faculties and students are welcome to join.