Graph Neural Networks (GNNs) have received significant attention for demonstrating their
capability to handle graph data. However, they are difficult to be deployed in resource …

Large language models (LLMs) have exploded a new heatwave of AI for their ability to
engage end-users in human-level conversations with detailed and articulate answers across …

Speculative decoding is a pivotal technique to accelerate the inference of large language
models (LLMs) by employing a smaller draft model to predict the target model's outputs …

Abstract Generative Adversarial Networks (GANs) have been widely used to recover vivid
textures in image super-resolution (SR) tasks. In particular one discriminator is utilized to …

Federated Distillation (FD) has recently attracted increasing attention for its efficiency in
aggregating multiple diverse local models trained from statistically heterogeneous data of …

Existing methods for asymmetric image retrieval employ a rigid pairwise similarity constraint
between the query network and the larger gallery network. However these one-to-one …

Previous Knowledge Distillation based efficient image retrieval methods employ a
lightweight network as the stu-dent model for fast inference. However, the lightweight stu …

Knowledge distillation is a deep learning method that mimics the way that humans teach, ie,
a teacher network is used to guide the training of a student one. Knowledge distillation can …

Existing studies on knowledge distillation typically focus on teacher-centered methods, in
which the teacher network is trained according to its own standards before transferring the …

Graph Neural Networks (GNNs) have demonstrated effectiveness in various graph-based
tasks. However, their inefficiency in training and inference presents challenges for scaling …