Timezone: »

O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers
Chulhee Yun · Yin-Wen Chang · Srinadh Bhojanapalli · Ankit Singh Rawat · Sashank Reddi · Sanjiv Kumar

Tue Dec 08 09:00 PM -- 11:00 PM (PST) @ Poster Session 2 #701
Recently, Transformer networks have redefined the state of the art in many NLP tasks. However, these models suffer from quadratic computational cost in the input sequence length $n$ to compute pairwise attention in each layer. This has prompted recent research into sparse Transformers that sparsify the connections in the attention layers. While empirically promising for long sequences, fundamental questions remain unanswered: Can sparse Transformers approximate any arbitrary sequence-to-sequence function, similar to their dense counterparts? How does the sparsity pattern and the sparsity level affect their performance? In this paper, we address these questions and provide a unifying framework that captures existing sparse attention models. We propose sufficient conditions under which we prove that a sparse attention model can universally approximate any sequence-to-sequence function. Surprisingly, our results show that sparse Transformers with only $O(n)$ connections per attention layer can approximate the same function class as the dense model with $n^2$ connections. Lastly, we present experiments comparing different patterns/levels of sparsity on standard NLP tasks.

Author Information

Charlie Yun (MIT)
Yin-Wen Chang (Google Inc.)
Srinadh Bhojanapalli (Google Research)
Ankit Singh Rawat (Google Research)
Sashank Reddi (Google)
Sanjiv Kumar (Google Research)

More from the Same Authors