Deep Learning
Improving Barely Supervised Learning by Discriminating Unlabeled Data with Super-Class
We compare our method with state-of-the-art SSL and BSL methods through extensive experiments on standard SSL benchmarks.
Identifying Mislabeled Data using the Area Under the Margin Ranking
Our goal is to automatically identify and subsequently remove mislabeled samples from training datasets. Discarding these harmful data will reduce memorization and improve generalization.
GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Games
Figure 1: Explanations on graphs with structure-aware values (like HN) offers advantages over non-structure-aware values (like Shapley).
SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connection
In this paper, we present a method for accelerating and structuring self-attentions: Sparse Adaptive Connection (SAC).
