Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time
This addresses the problem of encoding inductive biases effectively in neural networks for machine learning practitioners, offering a novel approach that is incremental in building on transductive and meta-learning ideas.
The paper tackles the generalization gap and objective mismatch of auxiliary losses by introducing tailoring, which fine-tunes models on unsupervised losses at prediction time, and meta-tailoring, which trains models to perform well after this adaptation, with empirical demonstrations across diverse examples.
From CNNs to attention mechanisms, encoding inductive biases into neural networks has been a fruitful source of improvement in machine learning. Adding auxiliary losses to the main objective function is a general way of encoding biases that can help networks learn better representations. However, since auxiliary losses are minimized only on training data, they suffer from the same generalization gap as regular task losses. Moreover, by adding a term to the loss function, the model optimizes a different objective than the one we care about. In this work we address both problems: first, we take inspiration from \textit{transductive learning} and note that after receiving an input but before making a prediction, we can fine-tune our networks on any unsupervised loss. We call this process {\em tailoring}, because we customize the model to each input to ensure our prediction satisfies the inductive bias. Second, we formulate {\em meta-tailoring}, a nested optimization similar to that in meta-learning, and train our models to perform well on the task objective after adapting them using an unsupervised loss. The advantages of tailoring and meta-tailoring are discussed theoretically and demonstrated empirically on a diverse set of examples.