Could you provide (at a high level) the time complexity of AttentionXML for training and predicting?
You can use $C_L$ for the BiLSTM forward pass cost and abstract other complex terms.
Indeed, it will be excellent if the final formula depends mostly on terms of $N$ (number of texts instances) and $L$ (number o labels)
Hello?
Could you provide (at a high level) the time complexity of AttentionXML for training and predicting?
You can use $C_L$ for the BiLSTM forward pass cost and abstract other complex terms. Indeed, it will be excellent if the final formula depends mostly on terms of $N$ (number of texts instances) and $L$ (number o labels)
I appreciate any help you can provide.