May 14, 2021
Attention mechanisms have shown promising results in sequence modeling tasks that require longterm memory. However, not all content in the past is equally important to remember. We propose Expire-Span, a method that learns to retain the most important information and expire the irrelevant information. This forgetting of memories enables Transformers to scale to attend over tens of thousands of previous timesteps efficiently, as not all states from previous timesteps are preserved. We demonstrate that Expire-Span can help models identify and retain critical information and show it can achieve strong performance on reinforcement learning tasks specifically designed to challenge this functionality. Next, we show that Expire-Span can scale to memories that are tens of thousands in size, setting a new state of the art on incredibly long context tasks such as character-level language modeling and a frame-by-frame moving objects task. Finally, we analyze the efficiency of Expire-Span compared to existing approaches and demonstrate that it trains faster and uses less memory.
Publisher
June 14, 2020
Ronghang Hu, Amanpreet Singh, Trevor Darrell, Marcus Rohrbach
June 14, 2020
April 25, 2020
Jonathan Gordon, David Lopez-Paz, Marco Baroni, Diane Bouchacourt
April 25, 2020
September 15, 2019
Tatiana Likhomanenko, Gabriel Synnaeve, Ronan Collobert
September 15, 2019
September 10, 2019
Jinfeng Rao, Linqing Liu, Yi Tay, Wei Yang, Peng Shi, Jimmy Lin
September 10, 2019
Who We Are
Our Actions
Newsletter