$\infty$-former: Infinite Memory Transformer

Abstract

Transformers are unable to model long-term memories effectively, since the amount of computation they need to perform grows with the context length. While variations of efficient transformers have been proposed, they all have a finite memory capacity and are forced to drop old information. In this paper, we propose the $\infty$-former, which extends the vanilla transformer with an unbounded long-term memory. By making use of a continuous-space attention mechanism to attend over the long-term memory, the $\infty$-former's attention complexity becomes independent of the context length, trading off memory length with precision. In order to control where precision is more important, $\infty$-former maintains "sticky memories" being able to model arbitrarily long contexts while keeping the computation budget fixed. Experiments on a synthetic sorting task, language modeling, and document grounded dialogue generation demonstrate the $\infty$-former's ability to retain information from long sequences.

ACL 2022

References in corpus (10)

• Longformer: The Long-Document Transformer
• Generating Long Sequences with Sparse Transformers
• Reformer: The Efficient Transformer
• Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
• Big Bird: Transformers for Longer Sequences
• Perceiver: General Perception with Iterative Attention
• Random Feature Attention
• Improving Neural Language Models with a Continuous Cache
• Sparse Sinkhorn Attention
• Sparse and Continuous Attention Mechanisms