From Sparse to Soft Mixtures of Experts

TL;DR

This paper introduces Soft MoE, a differentiable sparse Transformer that improves upon traditional MoEs by enabling implicit soft token assignment, leading to better scalability, stability, and performance in visual recognition tasks.

Contribution

The paper proposes Soft MoE, a fully-differentiable sparse Transformer that addresses key MoE challenges while maintaining scalability and performance benefits.

Findings

Soft MoE outperforms dense Transformers and other MoEs in visual recognition.

Soft MoE scales efficiently with over 40x more parameters at minimal inference cost.

Soft MoE demonstrates significant performance improvements in large-scale models.

Abstract

Sparse mixture of expert architectures (MoEs) scale model capacity without significant increases in training or inference costs. Despite their success, MoEs suffer from a number of issues: training instability, token dropping, inability to scale the number of experts, or ineffective finetuning. In this work, we propose Soft MoE, a fully-differentiable sparse Transformer that addresses these challenges, while maintaining the benefits of MoEs. Soft MoE performs an implicit soft assignment by passing different weighted combinations of all input tokens to each expert. As in other MoEs, experts in Soft MoE only process a subset of the (combined) tokens, enabling larger model capacity (and performance) at lower inference cost. In the context of visual recognition, Soft MoE greatly outperforms dense Transformers (ViTs) and popular MoEs (Tokens Choice and Experts Choice). Furthermore, Soft MoE scales well: Soft MoE Huge/14 with 128 experts in 16 MoE layers has over 40x more parameters than ViT Huge/14, with only 2% increased inference time, and substantially better quality.