no code implementations • 17 Nov 2023 • Jingyun Feng, Lin Zhang, Lili Yang
Existing approaches often rely on Variational Auto-Encoder (VAE) or its causal structure learning-based refinement, which suffer from sub-optimality in VAEs due to the independence factor assumption and unavailability of concept labels, respectively.
no code implementations • 11 May 2023 • Wenwu Gong, Zhejun Huang, Lili Yang
Then, based on Tucker decomposition, the tensor is approximated by multiplying non-negative factor matrices with a sparse core tensor.