Xiaobing Sun

attention mechanism (2) federated learning (2) neural tangent kernel (1) contrastive learning (1) feature extraction (1) sentiment analysis (1) text classification (1) backdoor defense (1) self-supervised learning (1) knowledge distillation (1) language modeling (1) label noise (1) gradient descent (1) backdoor attack (1) gaussian mixture model (1) recurrent neural network (1) learning dynamics (1) activation function (1) attention weight (1) gradient analysis (1)