# MGGAN: Solving Mode Collapse using Manifold Guided Training

arXiv: https://arxiv.org/abs/1804.04391 · HTML: https://mlsanity.com/paper/1804.04391/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Apr 2018.

## Built on by (most cited first, 22 of 22)

- [Mildly Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2206.04745/) (2022)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values](https://mlsanity.com/paper/2203.01993/) (2022)
- [Guiding Energy-based Models via Contrastive Latent Variables](https://mlsanity.com/paper/2303.03023/) (2023)
- [A survey on GANs for computer vision: Recent research, analysis and taxonomy](https://mlsanity.com/paper/2203.11242/) (2022)
- [Inexpensive High Fidelity Melt Pool Models in Additive Manufacturing Using Generative Deep Diffusion](https://mlsanity.com/paper/2311.16168/) (2023)
- [MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation](https://mlsanity.com/paper/2403.19144/) (2024)
- [DiverGAN: An Efficient and Effective Single-Stage Framework for Diverse Text-to-Image Generation](https://mlsanity.com/paper/2111.09267/) (2021)
- [AdvNF: Reducing Mode Collapse in Conditional Normalising Flows using Adversarial Learning](https://mlsanity.com/paper/2401.15948/) (2024)
- [Single-level Adversarial Data Synthesis based on Neural Tangent Kernels](https://mlsanity.com/paper/2204.04090/) (2022)
- [CAS-GAN for Contrast-free Angiography Synthesis](https://mlsanity.com/paper/2410.08490/) (2024)
- [Uncovering Hidden Subspaces in Video Diffusion Models Using Re-Identification](https://mlsanity.com/paper/2411.04956/) (2024)
- [On the Fairness, Diversity and Reliability of Text-to-Image Generative Models](https://mlsanity.com/paper/2411.13981/) (2024)
- [FedBM: Stealing Knowledge from Pre-trained Language Models for Heterogeneous Federated Learning](https://mlsanity.com/paper/2502.16832/) (2025)
- [Text-to-3D Generation using Jensen-Shannon Score Distillation](https://mlsanity.com/paper/2503.10660/) (2025)
- [IID-GAN: an IID Sampling Perspective for Regularizing Mode Collapse](https://mlsanity.com/paper/2106.00563/) (2021)
- [HGAN: Hybrid Generative Adversarial Network](https://mlsanity.com/paper/2102.03710/) (2021)
- [SVMax: A Feature Embedding Regularizer](https://mlsanity.com/paper/2103.02770/) (2021)
- [VARGAN: Variance Enforcing Network Enhanced GAN](https://mlsanity.com/paper/2109.02117/) (2021)
- [Hierarchical Vectorization for Portrait Images](https://mlsanity.com/paper/2205.11880/) (2022)
- [Distribution Fitting for Combating Mode Collapse in Generative Adversarial Networks](https://mlsanity.com/paper/2212.01521/) (2022)
- [Geodesic-informed Generative Diffusion Model For Topology-preserved Image Video Generation](https://mlsanity.com/paper/2609.08153/) (2026)

## Abstract (arXiv)

Mode collapse is a critical problem in training generative adversarial networks. To alleviate mode collapse, several recent studies introduce new objective functions, network architectures or alternative training schemes. However, their achievement is often the result of sacrificing the image quality. In this paper, we propose a new algorithm, namely a manifold guided generative adversarial network (MGGAN), which leverages a guidance network on existing GAN architecture to induce generator learning all modes of data distribution. Based on extensive evaluations, we show that our algorithm resolves mode collapse without losing image quality. In particular, we demonstrate that our algorithm is easily extendable to various existing GANs. Experimental analysis justifies that the proposed algorithm is an effective and efficient tool for training GANs.