← Search

Junyi Du

2 accepted papers

2021

Gradient-based Editing of Memory Examples for Online Task-free Continual Learning

NeurIPS 2021poster

We explore task-free continual learning (CL), in which a model is trained to avoid catastrophic forgetting in the absence of explicit task boundaries or identities. Among many efforts on task-free CL, a notable family of approaches are memory-based that store and replay a subset of training examples…

2020

Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models

ICLR 2020spotlight

The impressive performance of neural networks on natural language processing tasks attributes to their ability to model complicated word and phrase compositions. To explain how the model handles semantic compositions, we study hierarchical explanation of neural network predictions. We identify non-a…

Cited by 128SourceScholar