paper-with-me

홈 › Papers

Model Zoos: A Dataset of Diverse Populations of Neural Network Models

2022-09-29 · Konstantin Schürholt, Diyar Taskiran, Boris Knyazev, Xavier Giró-i-Nieto, Damian Borth

In the last years, neural networks (NN) have evolved from laboratory environments to the state-of-the-art for many real-world problems. It was shown that NN models (i.e., their weights and biases) evolve on unique trajectories in weight space during training. Following, a population of such neural network models (referred to as model zoo) would form structures in weight space. We think that the geometry, curvature and smoothness of these structures contain information about the state of training and can reveal latent properties of individual models. With such model zoos, one could investigate novel approaches for (i) model analysis, (ii) discover unknown learning dynamics, (iii) learn rich representations of such populations, or (iv) exploit the model zoos for generative modelling of NN weights and biases. Unfortunately, the lack of standardized model zoos and available benchmarks significantly increases the friction for further research about populations of NNs. With this work, we publish a novel dataset of model zoos containing systematically generated and diverse populations of NN models for further research. In total the proposed model zoo dataset is based on eight image datasets, consists of 27 model zoos trained with varying hyperparameter combinations and includes 50'360 unique NN models as well as their sparsified twins, resulting in over 3'844'360 collected model states. Additionally, to the model zoo data we provide an in-depth analysis of the zoos and provide benchmarks for multiple downstream tasks. The dataset can be found at www.modelzoos.cc.

📄 PDF Abstract BibTeX arXiv:2209.14764

Code (1)

ModelZoos/ModelZooDataset 공식 구현 pytorch

Tasks

ClassificationFriction

Similar Papers 제목 키워드 기반

Sparsified Model Zoo Twins: Investigating Populations of Sparsified Neural Network Models

2023-04-26 · Dominik Honegger, Konstantin Schürholt, Damian Borth

With growing size of Neural Networks (NNs), model sparsification to reduce the computational cost and memory demand for model inference has become of vital interest for both research and production. While many sparsifica…

Learning Model Representations Using Publicly Available Model Hubs

2025-10-02 · Damian Falk, Konstantin Schürholt, Konstantinos Tzevelekakis, Léo Meynent 외 arxiv

The weights of neural networks have emerged as a novel data modality, giving rise to the field of weight space learning. A central challenge in this area is that learning meaningful representations of weights typically r…

A Model Zoo of Vision Transformers

2025-04-14 · Damian Falk, Léo Meynent, Florence Pfammatter, Konstantin Schürholt 외

The availability of large, structured populations of neural networks - called 'model zoos' - has led to the development of a multitude of downstream tasks ranging from model analysis, to representation learning on model …

modelRepresentation Learning

The Impact of Model Zoo Size and Composition on Weight Space Learning

2025-04-14 · Damian Falk, Konstantin Schürholt, Damian Borth

Re-using trained neural network models is a common strategy to reduce training cost and transfer knowledge. Weight space learning - using the weights of trained models as data modality - is a promising new field to re-us…

DiversityTransfer LearningWeight Space Learning

Discrepancies among Pre-trained Deep Neural Networks: A New Threat to Model Zoo Reliability

2023-03-05 · Diego Montes, Pongpatapee Peerapatanapokin, Jeff Schultz, Chengjun Gun 외

Training deep neural networks (DNNs) takes signifcant time and resources. A practice for expedited deployment is to use pre-trained deep neural networks (PTNNs), often from model zoos -- collections of PTNNs; yet, the re…