Code generation models have increasingly become integral to aiding software development.

Our understanding of learning input-output relationships with neural nets has improved rapidly in recent years, but little is known about the convergence of the underlying representations, even in the simple case of linear autoencoders (LAEs).

However,existingapproachesusually require alargesetofhuman annotated explanations fortraining while collecting a large set of explanations is not only time consuming but also expensive.

The left part is about some existing approaches, e.g., IRNet [