2 papers
cs.LG2023
TK-KNN: A Balanced Distance-Based Pseudo Labeling Approach for Semi-Supervised Intent Classification
Nicholas Botzer, David Vasquez, Tim Weninger +1
The ability to detect intent in dialogue systems has become increasingly important in modern technology. These systems often generate a large amount of unlabeled data, and manually…
cs.LG2022
Using Graph Algorithms to Pretrain Graph Completion Transformers
Jonathan Pilault, Michael Galkin, Bahare Fatemi +3
Recent work on Graph Neural Networks has demonstrated that self-supervised pretraining can further enhance performance on downstream graph, link, and node classification tasks. How…