Guolin Ke

gradient boosting (3) transformer architecture (2) graph neural network (2) decision tree (2) efficient computing (2) self-supervised learning (2) gradient boosting decision tree (2) representation learning (2) benchmark evaluation (1) attention mechanism (1) contrastive learning (1) knowledge distillation (1) multimodal learning (1) text representation (1) software engineering (1) curriculum learning (1) distributed training (1) self-attention mechanism (1) dense retrieval (1) semi-supervised learning (1)