CGSTAE learns correlation graphs with spatial self-attention, derives causal graphs via a three-step invariance algorithm, and uses GCLSTM encoder-decoder to monitor industrial processes on Tennessee Eastman and air separation data.
Process monitoring using recurrent kalman variational auto-encoder for general complex dynamic processes,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Graph Autoencoder for Process Monitoring
CGSTAE learns correlation graphs with spatial self-attention, derives causal graphs via a three-step invariance algorithm, and uses GCLSTM encoder-decoder to monitor industrial processes on Tennessee Eastman and air separation data.