Evaluating Mixture-of-Experts Architectures for Network Aggregation
Svetlana Pavlitskaya, Christian Hubschneider, Michael Weber · 2022
Abstract The mixture-of-experts (MoE) architecture is an approach to aggregate several expert components via an additional gating module, which learns to predict the most suitable distribution of the expert’s outputs for each input. An MoE thus not only relies on redundancy for increased robustness—we also demonstrate how this architecture can provide additional interpretability, while retaining performance similar to a standalone network. As an example, we train expert networks to perform semantic segmentation of the traffic scenes and combine them into an MoE with an additional gating network. Our experiments with two different expert model architectures ( and ) reveal that the MoE is able to reach, and for certain data subsets even surpass, the baseline performance and also outperforms a simple aggregation via ensembling. A further advantage of an MoE is the increased interpretability—a comparison of pixel-wise predictions of the whole MoE model and the participating experts’ help to identify regions of high uncertainty in an input.