Flashback: Memory Mechanism for Enhancing Memory Efficiency and Speed in Deep Sequential Models

AbstractIn this study, we tackle three main challenges of deep sequential processing models in previous research: (1) memory degradation, (2) inaccurate gradient backpropagation, and (3) compatibility with next-token prediction. Specifically, to address (1-2), we define a Flashback property in which memory is preserved perfectly as an identity mapping of its stored value in a memory region until it is overwritten by a hidden state at a different time step. We propose a Flashback mechanism that satisfies this property in a fully differentiable, end-to-end manner. Further, to tackle (3), we propose architectures that incorporate the Flashback mechanism into Transformers and Mamba, enabling next-token prediction for language modeling tasks. In experiments, we trained on The Pile dataset, which includes diverse texts, to evaluate tradeoffs between commonsense reasoning accuracy, processing speed, and memory usage after introducing the Flashback mechanism into existing methods. The evaluations confirmed the effectiveness of the Flashback mechanism.