Transformers have become the dominant model class in the last few years for large data, but their quadratic complexity in terms of sequence length has plagued them until now. Fastformer claims to be the fastest and most performant linear attention variant, able to consume long contexts at once. This is achieved by a combination of additive attention and elementwise products. While initial results look promising, I have my reservations…
0:00 - Intro & Outline
2:15 - Fastformer description
5:20 - Baseline: Classic Attention
10:00 - Fastformer architecture
12:50 - Additive Attention
18:05 - Query-Key element-wise multiplication
21:35 - Redundant modules in Fastformer
25:00 - Problems with the architecture
27:30 - Is this even attention?
32:20 - Experimental Results
34:50 - Conclusion & Comments
Transformer is a powerful model for text understanding. However, it is inefficient due to its quadratic complexity to input sequence length. Although there are many methods on Transformer acceleration, they are still either inefficient on long sequences or not effective enough. In this paper, we propose Fastformer, which is an efficient Transformer model based on additive attention. In Fastformer, instead of modeling the pair-wise interactions between tokens, we first use additive attention mechanism to model global contexts, and then further transform each token representation based on its interaction with global context representations. In this way, Fastformer can achieve effective context modeling with linear complexity. Extensive experiments on five datasets show that Fastformer is much more efficient than many existing Transformer models and can meanwhile achieve comparable or even better long text modeling performance.
Authors: Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang