Addressing Some Limitations of Transformers with Feedback Memory

Angela Fan, Thibaut Lavril, Edouard Grave, Armand Joulin, Sainbayar Sukhbaatar

Keywords: Feedback, Memory, Transformers

Abstract: Transformers have been successfully applied to sequential tasks despite being feedforward networks. Unlike recurrent neural networks, Transformers use attention to capture temporal relations while processing input tokens in parallel. While this parallelization makes them computationally efficient, it restricts the model from fully exploiting the sequential nature of the input. The representation at a given layer can only access representations from lower layers, rather than the higher level representations already available. In this work, we propose the Feedback Transformer architecture that exposes all previous representations to all future representations, meaning the lowest representation of the current timestep is formed from the highest-level abstract representation of the past. We demonstrate on a variety of benchmarks in language modeling, machine translation, and reinforcement learning that the increased representation capacity can create small, shallow models with much stronger performance than comparable Transformers.

One-sentence Summary: Transformers have shortcomings - limited memory and limited state update - but Feedback Memory is a straightforward way to resolve these.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=5LFcpD4D3E