How deeply does Graph Neural Networks in Action cover teacher forcing?

Explains the input-switching behavior and shows its decoder implementation, but does not discuss scheduling strategies or quantitative trade-offs.

Teacher forcing

As explained in Graph Neural Networks in Action

Teacher forcing is a sequential-model training technique that supplies the ground-truth previous output as input when predicting the next step.

Teacher forcing trains a sequential decoder by supplying the ground-truth previous output when predicting the next timestep. With it enabled, a graph decoder uses the real graph; when disabled, it feeds back its own previous prediction. section 6.4.2

A decoder uses the technique as a controlled prediction pipeline:

Pass observed graph frames and sampled edges into the decoder. section 6.4.2
During teacher-forced steps, use the real next graph as the next input rather than the model’s previous output. section 6.4.2
For autonomous forecasting, set teacher_forcing=False and repeatedly use decoder predictions for future timesteps. section 6.4.2

How Graph Neural Networks in Action covers it

Cover of Graph Neural Networks in Action

liveBook manning.com

Read Graph Neural Networks in Action on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Inside Deep Learning: Math, Algorithms, ModelsA training approach for sequence decoders that feeds the true previous token as the next input instead of the model's own prediction.

Compare how 2 books explain teacher forcing →

Related concepts

recurrent neural networkuses · A recurrent neural network is a neural network that processes sequences by updating an internal state across successive inputs, allowing earlier inputs to influence later computations.
labeluses · A label is a value or annotation associated with an item that identifies its target category, outcome, or reference answer for learning or evaluation.
tokenuses · A token is a discrete unit of text, such as a word, word fragment, character, or symbol, represented and processed as an element by a language model.

This explainer was generated by Manning's knowledge graph from the text of Graph Neural Networks in Action. The section links point to the parts of the book it draws on.