# Consistent Distributed Ranking of Generative Models via Kernel Distances

Source: [Consistent Distributed Ranking of Generative Models via Kernel Distances](<https://www.sota2.com/research/paper/68fa73991e209131cea5d7ed>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-27T05:00:04.726Z

Authors: Zixiao Wang, Farzan Farnia, Zhenghao Lin, Yunheng Shen, Bei Yu

Published: 2023-10-18T05:06:04.000Z

## Abstract

Ranking generative models based on the fidelity and diversity of their outputs is required to identify the best generator in a group of candidate generative AI models. To rank a group of models in a conventional centralized setting, a standard score is commonly evaluated for each involved model. The selection and design of reference-based evaluation scores have been extensively studied in centralized settings, where the reference samples are drawn from a single probability distribution. However, in practical scenarios including distributed learning contexts, reference samples are distributed across multiple clients, each potentially with a heterogeneous data distribution. In this work, we investigate the ranking of generative models in such distributed settings with heterogeneous data distributions across clients. We focus on the widely used family of kernel distance (KD) evaluation metrics. We prove that, for every kernel function, ranking models by the averaged KD scores of individual clients yields the same ordering as a centralized KD evaluation using the combined reference data from all the clients. We further extend our analysis to other popular metrics, including the Fr\\'echet Distance (FD), for which the individual client scores could be insufficient for accurate model ranking. We present the numerical results of several experiments on standard image datasets and generative models to validate our theoretical findings regarding distributed ranking using various evaluation scores.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Generation on ImageNet 256x256 (KD, FD, FLS Metrics)](<https://www.sota2.com/research/sota/image-generation-on-imagenet-256x256-kd-fd-fls-metrics.md>): Image Generation; ImageNet 256x256; KD (All): 0.25.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2310.11714>)

[PDF](<https://arxiv.org/pdf/2310.11714.pdf>)