Search Results for author:
Found 4 papers, 2 papers with code
Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model
While the model parameters do contribute to memory usage, the primary memory bottleneck during training arises from storing feature maps, also known as activations, as they are crucial for gradient calculation.
Editable Graph Neural Network for Node Classifications
However, model editing for graph neural networks (GNNs) is rarely explored, despite GNNs' widespread applicability.
Data-centric Artificial Intelligence: A Survey
Artificial Intelligence (AI) is making a profound impact in almost every domain.
Revisit Kernel Pruning with Lottery Regulated Grouped Convolutions
In this paper, we revisit the idea of kernel pruning (to only prune one or several $k \times k$ kernels out of a 3D-filter), a heavily overlooked approach under the context of structured pruning due to it will naturally introduce sparsity to filters within the same convolutional layer—thus, making the remaining network no longer dense.
