Reversible Recurrent Neural Networks

TL;DR

Reversible RNNs can significantly reduce memory usage during training by enabling hidden state recomputation, but perfect reversibility limits forgetting; a new scheme balances reversibility and forgetting, maintaining performance.

Contribution

The paper introduces a scheme for reversible RNNs that allows controlled forgetting, reducing memory costs while preserving model performance.

Findings

Memory cost reduced by a factor of 10-15 in RNNs.

Performance comparable to traditional RNNs.

Extended technique to attention-based models with similar memory savings.

Abstract

Recurrent neural networks (RNNs) provide state-of-the-art performance in processing sequential data but are memory intensive to train, limiting the flexibility of RNN models which can be trained. Reversible RNNs---RNNs for which the hidden-to-hidden transition can be reversed---offer a path to reduce the memory requirements of training, as hidden states need not be stored and instead can be recomputed during backpropagation. We first show that perfectly reversible RNNs, which require no storage of the hidden activations, are fundamentally limited because they cannot forget information from their hidden state. We then provide a scheme for storing a small number of bits in order to allow perfect reversal with forgetting. Our method achieves comparable performance to traditional models while reducing the activation memory cost by a factor of 10--15. We extend our technique to attention-based sequence-to-sequence models, where it maintains performance while reducing activation memory cost by a factor of 5--10 in the encoder, and a factor of 10--15 in the decoder.