Open mounchiliu opened 7 months ago
Hi there, The code performs conduct DFT on NT dimension and then conducts matrix multiplication on d dimension. Why this kind of matrix multiplication in d dimension is equivalent to matrix multiplication AXW in the time domain?
The graph convolution operation AXW is also conducted on d dimension
Hi there, The code performs conduct DFT on NT dimension and then conducts matrix multiplication on d dimension. Why this kind of matrix multiplication in d dimension is equivalent to matrix multiplication AXW in the time domain?