# MD-Face: MoE-Enhanced Label-Free Disentangled Representation for Interactive Facial Attribute Editing

arXiv: https://arxiv.org/abs/2604.20317 · HTML: https://mlsanity.com/paper/2604.20317/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts.
- Builds on 28 of its 31 references that are in the map.
- First posted on arXiv 22 Apr 2026.

## Placed in

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

## Builds on (most cited first, 28 of 28)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [GANSpace: Discovering Interpretable GAN Controls](https://mlsanity.com/paper/2004.02546/) (2020)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs](https://mlsanity.com/paper/2005.09635/) (2020)
- [StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows](https://mlsanity.com/paper/2008.02401/) (2020)
- [AttGAN: Facial Attribute Editing by Only Changing What You Want](https://mlsanity.com/paper/1711.10678/) (2017)
- [Delta Denoising Score](https://mlsanity.com/paper/2304.07090/) (2023)
- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation](https://mlsanity.com/paper/2102.01187/) (2021)
- [Contrastive Denoising Score for Text-guided Latent Diffusion Image Editing](https://mlsanity.com/paper/2311.18608/) (2023)
- [UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation](https://mlsanity.com/paper/2203.02557/) (2022)
- [TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing](https://mlsanity.com/paper/2203.17266/) (2022)
- [NeRFFaceEditing: Disentangled Face Editing in Neural Radiance Fields](https://mlsanity.com/paper/2211.07968/) (2022)
- [Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANs](https://mlsanity.com/paper/2106.06959/) (2021)
- [Diff-Privacy: Diffusion-based Face Privacy Protection](https://mlsanity.com/paper/2309.05330/) (2023)
- [High Resolution Face Editing with Masked GAN Latent Code Optimization](https://mlsanity.com/paper/2103.11135/) (2021)
- [Adaptive Nonlinear Latent Transformation for Conditional Face Editing](https://mlsanity.com/paper/2307.07790/) (2023)
- [FDA-GAN: Flow-based Dual Attention GAN for Human Pose Transfer](https://mlsanity.com/paper/2112.00281/) (2021)
- [Semantic Latent Decomposition with Normalizing Flows for Face Editing](https://mlsanity.com/paper/2309.05314/) (2023)
- [Multi-Directional Subspace Editing in Style-Space](https://mlsanity.com/paper/2211.11825/) (2022)
- [WEM-GAN: Wavelet transform based facial expression manipulation](https://mlsanity.com/paper/2412.02530/) (2024)

## Abstract (arXiv)

GAN-based facial attribute editing is widely used in virtual avatars and social media but often suffers from attribute entanglement, where modifying one face attribute unintentionally alters others. While supervised disentangled representation learning can address this, it relies heavily on labeled data, incurring high annotation costs. To address these challenges, we propose MD-Face, a label-free disentangled representation learning framework based on Mixture of Experts (MoE). MD-Face utilizes a MoE backbone with a gating mechanism that dynamically allocates experts, enabling the model to learn semantic vectors with greater independence. To further enhance attribute entanglement, we introduce a geometry-aware loss, which aligns each semantic vector with its corresponding Semantic Boundary Vector (SBV) through a Jacobian-based pushforward method. Experiments with ProGAN and StyleGAN show that MD-Face outperforms unsupervised baselines and competes with supervised ones. Compared to diffusion-based methods, it offers better image quality and lower inference latency, making it ideal for interactive editing.