Timezone: »
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.
Author Information
Konstantin Schürholt (University of St. Gallen)
Diyar Taskiran (Universität St. Gallen)
Boris Knyazev (University of Guelph)
Xavier Giró-i-Nieto (UPC Barcelona)
Damian Borth (University of St.Gallen (HSG))
More from the Same Authors
-
2022 : Federated Continual Learning to Detect Accounting Anomalies in Financial Auditing »
Marco Schreyer · Hamed Hemati · Damian Borth · Miklos Vasarhelyi -
2022 : Towards dynamical stability analysis of sustainable power grids using Graph Neural Networks »
Christian Nauck · Michael Lindner · Ulrich Schürholt · Frank Hellmann -
2023 Poster: Adversarial Learning for Feature Shift Detection and Correction »
Míriam Barrabés · Daniel Mas Montserrat · Margarita Geleta · Xavier Giró-i-Nieto · Alexander Ioannidis -
2022 Spotlight: Lightning Talks 2A-3 »
David Buterez · Chengan He · Xuan Kan · Yutong Lin · Konstantin Schürholt · Yu Yang · Louis Annabi · Wei Dai · Xiaotian Cheng · Alexandre Pitti · Ze Liu · Jon Paul Janet · Jun Saito · Boris Knyazev · Mathias Quoy · Zheng Zhang · James Zachary · Steven J Kiddle · Xavier Giro-i-Nieto · Chang Liu · Hejie Cui · Zilong Zhang · Hakan Bilen · Damian Borth · Dino Oglic · Holly Rushmeier · Han Hu · Xiangyang Ji · Yi Zhou · Nanning Zheng · Ying Guo · Pietro Liò · Stephen Lin · Carl Yang · Yue Cao -
2022 Spotlight: Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights »
Konstantin Schürholt · Boris Knyazev · Xavier Giro-i-Nieto · Damian Borth -
2022 Poster: Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights »
Konstantin Schürholt · Boris Knyazev · Xavier Giró-i-Nieto · Damian Borth -
2021 Poster: Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction »
Konstantin Schürholt · Dimche Kostadinov · Damian Borth -
2019 : Speech in Pixels: Automatic Detection of Offensive Memes for Moderation »
Xavier Giro-i-Nieto -
2018 : Contributed Work »
Thaer Moustafa Dieb · Aditya Balu · Amir H. Khasahmadi · Viraj Shah · Boris Knyazev · Payel Das · Garrett Goh · Georgy Derevyanko · Gianni De Fabritiis · Reiko Hagawa · John Ingraham · David Belanger · Jialin Song · Kim Nicoli · Miha Skalic · Michelle Wu · Niklas Gebauer · Peter Bjørn Jørgensen · Ryan-Rhys Griffiths · Shengchao Liu · Sheshera Mysore · Hai Leong Chieu · Philippe Schwaller · Bart Olsthoorn · Bianca-Cristina Cristescu · Wei-Cheng Tseng · Seongok Ryu · Iddo Drori · Kevin Yang · Soumya Sanyal · Zois Boukouvalas · Rishi Bedi · Arindam Paul · Sambuddha Ghosal · Daniil Bash · Clyde Fare · Zekun Ren · Ali Oskooei · Minn Xuan Wong · Paul Sinz · Théophile Gaudin · Wengong Jin · Paul Leu -
2017 : Coffee break and Poster Session I »
Nishith Khandwala · Steve Gallant · Gregory Way · Aniruddh Raghu · Li Shen · Aydan Gasimova · Alican Bozkurt · William Boag · Daniel Lopez-Martinez · Ulrich Bodenhofer · Samaneh Nasiri GhoshehBolagh · Michelle Guo · Christoph Kurz · Kirubin Pillay · Kimis Perros · George H Chen · Alexandre Yahi · Madhumita Sushil · Sanjay Purushotham · Elena Tutubalina · Tejpal Virdi · Marc-Andre Schulz · Samuel Weisenthal · Bharat Srikishan · Petar Veličković · Kartik Ahuja · Andrew Miller · Erin Craig · Disi Ji · Filip Dabek · Chloé Pou-Prom · Hejia Zhang · Janani Kalyanam · Wei-Hung Weng · Harish Bhat · Hugh Chen · Simon Kohl · Mingwu Gao · Tingting Zhu · Ming-Zher Poh · Iñigo Urteaga · Antoine Honoré · Alessandro De Palma · Maruan Al-Shedivat · Pranav Rajpurkar · Matthew McDermott · Vincent Chen · Yanan Sui · Yun-Geun Lee · Li-Fang Cheng · Chen Fang · Sibt ul Hussain · Cesare Furlanello · Zeev Waks · Hiba Chougrad · Hedvig Kjellstrom · Finale Doshi-Velez · Wolfgang Fruehwirt · Yanqing Zhang · Lily Hu · Junfang Chen · Sunho Park · Gatis Mikelsons · Jumana Dakka · Stephanie Hyland · yann chevaleyre · Hyunwoo Lee · Xavier Giro-i-Nieto · David Kale · Michael Hughes · Gabriel Erion · Rishab Mehra · William Zame · Stojan Trajanovski · Prithwish Chakraborty · Kelly Peterson · Muktabh Mayank Srivastava · Amy Jin · Heliodoro Tejeda Lemus · Priyadip Ray · Tamas Madl · Joseph Futoma · Enhao Gong · Syed Rameel Ahmad · Eric Lei · Ferdinand Legros