Search Results for author:
Found 5 papers, 4 papers with code
TensorCodec: Compact Lossy Compression of Tensors without Strong Data Assumptions
While many tensor compression algorithms are available, many of them rely on strong data assumptions regarding its order, sparsity, rank, and smoothness.
NeuKron: Constant-Size Lossy Compression of Sparse Reorderable Matrices and Tensors
The updates take time linear in the number of non-zeros in the input matrix, and the approximation of each entry can be retrieved in logarithmic time.
BeGin: Extensive Benchmark Scenarios and An Easy-to-use Framework for Graph Continual Learning
Compared to them, however, CL methods for graph data (graph CL) are relatively underexplored because of (a) the lack of standard experimental settings, especially regarding how to deal with the dependency between instances, (b) the lack of benchmark datasets and scenarios, and (c) high complexity in implementation and evaluation due to the dependency.
Learning to Pool in Graph Neural Networks for Extrapolation
However, according to a recent study, a careful choice of pooling functions, which are used for the aggregation and readout operations in GNNs, is crucial for enabling GNNs to extrapolate.
SliceNStitch: Continuous CP Decomposition of Sparse Tensor Streams
SLICENSTITCH changes the starting point of each period adaptively, based on the current time, and updates factor matrices (i. e., outputs of CP decomposition) instantly as new data arrives.
