4 accepted papers
Unsupervised contrastive learning has shown significant performance improvements in recent years, often approaching or even rivaling supervised learning in various tasks. However, its learning mechanism is fundamentally different from supervised learning. Previous works have shown that difficult exa…
Graph Attention Networks (GATs) that compute node representation by its lower-order neighbors, are state-of-the-art architecture for representation learning with graphs. In practice, however, the high-order neighbors that turn out to be useful, remain largely unemployed in GATs. Efforts on this issu…
Graph-based consistency principle has been successfully applied to many semi-supervised problems in machine learning. Its performance largely depends on the quality of augmented graphs, which has been recently proven that revealing graph properties and maintaining the invariance of graphs are crucia…
Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data. Existing SSL typically requires all classes have labels. However, in many real-world applications, there may exist some classes that are difficult to label or newly occurred classes that cannot be labeled in…