# GDPP: Learning Diverse Generations Using Determinantal Point Process

arXiv: https://arxiv.org/abs/1812.00068 · HTML: https://mlsanity.com/paper/1812.00068/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2018.

## Built on by (most cited first, 26 of 26)

- [VkD: Improving Knowledge Distillation using Orthogonal Projections](https://mlsanity.com/paper/2403.06213/) (2024)
- [Black-Box Testing of Deep Neural Networks Through Test Case Diversity](https://mlsanity.com/paper/2112.12591/) (2021)
- [Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games](https://mlsanity.com/paper/2106.04958/) (2021)
- [Improved Financial Forecasting via Quantum Machine Learning](https://mlsanity.com/paper/2306.12965/) (2023)
- [Diverse Sample Generation: Pushing the Limit of Generative Data-free Quantization](https://mlsanity.com/paper/2109.00212/) (2021)
- [Constraining Generative Models for Engineering Design with Negative Data](https://mlsanity.com/paper/2306.15166/) (2023)
- [It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models](https://mlsanity.com/paper/2601.00090/) (2025)
- [Deep Time Series Forecasting with Shape and Temporal Criteria](https://mlsanity.com/paper/2104.04610/) (2021)
- [Multiple-criteria Based Active Learning with Fixed-size Determinantal Point Processes](https://mlsanity.com/paper/2107.01622/) (2021)
- [A Unified Algorithm Framework for Unsupervised Discovery of Skills based on Determinantal Point Process](https://mlsanity.com/paper/2212.00211/) (2022)
- [From Sampling to Optimization on Discrete Domains with Applications to Determinant Maximization](https://mlsanity.com/paper/2102.05347/) (2021)
- [Generating Diverse 3D Reconstructions from a Single Occluded Face Image](https://mlsanity.com/paper/2112.00879/) (2021)
- [Loss function based second-order Jensen inequality and its application to particle variational inference](https://mlsanity.com/paper/2106.05010/) (2021)
- [Diverse Probabilistic Trajectory Forecasting with Admissibility Constraints](https://mlsanity.com/paper/2302.03462/) (2023)
- [Quantum latent distributions in deep generative models](https://mlsanity.com/paper/2508.19857/) (2025)
- [Variational Inference, Entropy, and Orthogonality: A Unified Theory of Mixture-of-Experts](https://mlsanity.com/paper/2601.03577/) (2026)
- [Scalable Sampling for Nonsymmetric Determinantal Point Processes](https://mlsanity.com/paper/2201.08417/) (2022)
- [Continual Zero-Shot Learning through Semantically Guided Generative Random Walks](https://mlsanity.com/paper/2308.12366/) (2023)
- [MUSS: Multilevel Subset Selection for Relevance and Diversity](https://mlsanity.com/paper/2503.11126/) (2025)
- [Scaling DPPs for RAG: Density Meets Diversity](https://mlsanity.com/paper/2604.03240/) (2026)
- [IID-GAN: an IID Sampling Perspective for Regularizing Mode Collapse](https://mlsanity.com/paper/2106.00563/) (2021)
- [VARGAN: Variance Enforcing Network Enhanced GAN](https://mlsanity.com/paper/2109.02117/) (2021)
- [Unified Simulation, Perception, and Generation of Human Behavior](https://mlsanity.com/paper/2204.13678/) (2022)
- [GLUE: Coordinating Pre-Trained Generative Models for System-Level Design](https://mlsanity.com/paper/2512.19469/) (2025)
- [AgForce Enables Antigen-conditioned Generative Antibody Design](https://mlsanity.com/paper/2605.21610/) (2026)
- [Adaptive Determinantal Client Scheduling in Federated Learning](https://mlsanity.com/paper/2609.23843/) (2026)

## Abstract (arXiv)

Generative models have proven to be an outstanding tool for representing high-dimensional probability distributions and generating realistic-looking images. An essential characteristic of generative models is their ability to produce multi-modal outputs. However, while training, they are often susceptible to mode collapse, that is models are limited in mapping input noise to only a few modes of the true data distribution. In this work, we draw inspiration from Determinantal Point Process (DPP) to propose an unsupervised penalty loss that alleviates mode collapse while producing higher quality samples. DPP is an elegant probabilistic measure used to model negative correlations within a subset and hence quantify its diversity. We use DPP kernel to model the diversity in real data as well as in synthetic data. Then, we devise an objective term that encourages generators to synthesize data with similar diversity to real data. In contrast to previous state-of-the-art generative models that tend to use additional trainable parameters or complex training paradigms, our method does not change the original training scheme. Embedded in an adversarial training and variational autoencoder, our Generative DPP approach shows a consistent resistance to mode-collapse on a wide variety of synthetic data and natural image datasets including MNIST, CIFAR10, and CelebA, while outperforming state-of-the-art methods for data-efficiency, generation quality, and convergence-time whereas being 5.8x faster than its closest competitor.