English

Doubly Sparse: Sparse Mixture of Sparse Experts for Efficient Softmax Inference

Machine Learning 2019-07-04 v2 Machine Learning

Abstract

Computations for the softmax function are significantly expensive when the number of output classes is large. In this paper, we present a novel softmax inference speedup method, Doubly Sparse Softmax (DS-Softmax), that leverages sparse mixture of sparse experts to efficiently retrieve top-k classes. Different from most existing methods that require and approximate a fixed softmax, our method is learning-based and can adapt softmax weights for a better inference speedup. In particular, our method learns a two-level hierarchy which divides entire output class space into several partially overlapping experts. Each expert is sparse and only contains a subset of output classes. To find top-k classes, a sparse mixture enables us to find the most probable expert quickly, and the sparse expert enables us to search within a small-scale softmax. We empirically conduct evaluation on several real-world tasks, including neural machine translation, language modeling and image classification, and demonstrate that significant computation reductions can be achieved at no performance loss.

Keywords

Cite

@article{arxiv.1901.10668,
  title  = {Doubly Sparse: Sparse Mixture of Sparse Experts for Efficient Softmax Inference},
  author = {Shun Liao and Ting Chen and Tian Lin and Denny Zhou and Chong Wang},
  journal= {arXiv preprint arXiv:1901.10668},
  year   = {2019}
}
R2 v1 2026-06-23T07:26:36.704Z