# Double-Stage Feature-Level Clustering-Based Mixture of Experts Framework

arXiv: https://arxiv.org/abs/2503.09504 · HTML: https://mlsanity.com/paper/2503.09504/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts.
- Builds on 8 of its 30 references that are in the map.
- First posted on arXiv 12 Mar 2025.

## Placed in

- Mixture-of-experts / [Vision mixture-of-experts](https://mlsanity.com/moe/vision-mixture-of-experts/)

## Builds on (most cited first, 8 of 8)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Learning Factored Representations in a Deep Mixture of Experts](https://mlsanity.com/paper/1312.4314/) (2013)
- [Learning from positive and unlabeled data: a survey](https://mlsanity.com/paper/1811.04820/) (2018)
- [DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learning](https://mlsanity.com/paper/2106.03760/) (2021)
- [Toward Scalable Generative AI via Mixture of Experts in Mobile Edge Networks](https://mlsanity.com/paper/2402.06942/) (2024)

## Built on by (most cited first, 2 of 2)

- [Spectral Manifold Regularization for Stable and Modular Routing in Deep MoE Architectures](https://mlsanity.com/paper/2601.03889/) (2026)
- [Sparse Mixture-of-Experts Reward Models Learn Interpretable and Specialized Experts for Personalized Preference Modeling](https://mlsanity.com/paper/2606.04284/) (2026)

## Abstract (arXiv)

The Mixture-of-Experts (MoE) model has succeeded in deep learning (DL). However, its complex architecture and advantages over dense models in image classification remain unclear. In previous studies, MoE performance has often been affected by noise and outliers in the input space. Some approaches incorporate input clustering for training MoE models, but most clustering algorithms lack access to labeled data, limiting their effectiveness. This paper introduces the Double-stage Feature-level Clustering and Pseudo-labeling-based Mixture of Experts (DFCP-MoE) framework, which consists of input feature extraction, feature-level clustering, and a computationally efficient pseudo-labeling strategy. This approach reduces the impact of noise and outliers while leveraging a small subset of labeled data to label a large portion of unlabeled inputs. We propose a conditional end-to-end joint training method that improves expert specialization by training the MoE model on well-labeled, clustered inputs. Unlike traditional MoE and dense models, the DFCP-MoE framework effectively captures input space diversity, leading to competitive inference results. We validate our approach on three benchmark datasets for multi-class classification tasks.