1 code implementation • 19 Sep 2023 • Taehyung Kwon, Jihoon Ko, Jinhong Jung, Kijung Shin
While many tensor compression algorithms are available, many of them rely on strong data assumptions regarding its order, sparsity, rank, and smoothness.
1 code implementation • 9 Feb 2023 • Taehyung Kwon, Jihoon Ko, Jinhong Jung, Kijung Shin
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.
1 code implementation • 26 Nov 2022 • Jihoon Ko, Shinhwan Kang, Taehyung Kwon, Heechan Moon, Kijung Shin
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.
no code implementations • 11 Jun 2021 • Jihoon Ko, Taehyung Kwon, Kijung Shin, Juho Lee
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.
1 code implementation • 23 Feb 2021 • Taehyung Kwon, Inkyu Park, Dongjin Lee, Kijung Shin
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.