Intrinsic dimension of data representations in deep neural networks

29 May 2019

Jakob H. Macke

Papers citing "Intrinsic dimension of data representations in deep neural networks"

50 / 64 papers shown

Title
Informed Mixing -- Improving Open Set Recognition via Attribution-based Augmentation Jiawen Xu O. Kao Margret Keuper 27 0 0 19 May 2025
FedDuA: Doubly Adaptive Federated Learning Shokichi Takakura Seng Pei Liew Satoshi Hasegawa FedML 30 0 0 16 May 2025
Register and CLS tokens yield a decoupling of local and global features in large ViTs Alexander Lappe M. Giese 29 0 0 09 May 2025
High-entropy Advantage in Neural Networks' Generalizability Entao Yang Xuzhi Zhang Yue Shang Ge Zhang AI4CE 71 0 0 17 Mar 2025
A Geometric Perspective for High-Dimensional Multiplex Graphs K. Abdous Nairouz Mrabah Mohamed Bouguessa 80 0 0 29 Jan 2025
The Geometry of Tokens in Internal Representations of Large Language Models Karthik Viswanathan Yuri Gardinazzi Giada Panerai Alberto Cazzaniga Matteo Biagetti AIFin 102 4 0 17 Jan 2025
Unsupervised detection of semantic correlations in big data Santiago Acevedo Alex Rodriguez Alessandro Laio 70 2 0 04 Nov 2024
ResiDual Transformer Alignment with Spectral Decomposition Lorenzo Basile Valentino Maiorca Luca Bortolussi Emanuele Rodolà Francesco Locatello 66 1 0 31 Oct 2024
The Geometry of Concepts: Sparse Autoencoder Feature Structure Yuxiao Li Eric J. Michaud David D. Baek Joshua Engels Xiaoqing Sun Max Tegmark 58 9 0 10 Oct 2024
Geometric Signatures of Compositionality Across a Language Model's Lifetime Jin Hwa Lee Thomas Jiralerspong Lei Yu Yoshua Bengio Emily Cheng CoGe 87 1 0 02 Oct 2024
Intrinsic Dimension Correlation: uncovering nonlinear connections in multimodal representations Lorenzo Basile Santiago Acevedo Luca Bortolussi Fabio Anselmi Alex Rodriguez 53 4 0 22 Jun 2024
Exploiting the Layered Intrinsic Dimensionality of Deep Models for Practical Adversarial Training Enes Altinisik Safa Messaoud Husrev Taha Sencar Hassan Sajjad Sanjay Chawla AAML 53 0 0 27 May 2024
Emergence of a High-Dimensional Abstraction Phase in Language Transformers Emily Cheng Diego Doimo Corentin Kervadec Iuri Macocco Jade Yu Alessandro Laio Marco Baroni 112 11 0 24 May 2024
Quantifying Manifolds: Do the manifolds learned by Generative Adversarial Networks converge to the real data manifold Anupam Chaudhuri Anj Simmons Mohamed Abdelrazek 33 0 0 08 Mar 2024
LDReg: Local Dimensionality Regularized Self-Supervised Learning Hanxun Huang R. Campello S. Erfani Xingjun Ma Michael E. Houle James Bailey 46 5 0 19 Jan 2024
Bridging Information-Theoretic and Geometric Compression in Language Models Emily Cheng Corentin Kervadec Marco Baroni 36 17 0 20 Oct 2023
Systematic Architectural Design of Scale Transformed Attention Condenser DNNs via Multi-Scale Class Representational Response Similarity Analysis Andrew Hryniowski Alexander Wong 23 0 0 16 Jun 2023
Deep neural networks architectures from the perspective of manifold learning German Magai AAML AI4CE 35 6 0 06 Jun 2023
The Tunnel Effect: Building Data Representations in Deep Neural Networks Wojciech Masarczyk M. Ostaszewski Ehsan Imani Razvan Pascanu Piotr Milo's Tomasz Trzciñski 41 19 0 31 May 2023
Data Representations' Study of Latent Image Manifolds Ilya Kaufman Omri Azencot 14 7 0 31 May 2023
Emergent representations in networks trained with the Forward-Forward algorithm Niccolo Tosato Lorenzo Basile Emanuele Ballarin Giuseppe de Alteriis Alberto Cazzaniga A. Ansuini 31 9 0 26 May 2023
Similarity of Neural Network Models: A Survey of Functional and Representational Measures Max Klabunde Tobias Schumacher M. Strohmaier Florian Lemmerich 63 66 0 10 May 2023
Probing the Purview of Neural Networks via Gradient Analysis Jinsol Lee Charles Lehman Mohit Prabhushankar Ghassan AlRegib 37 7 0 06 Apr 2023
Local Intrinsic Dimensional Entropy Rohan Ghosh Mehul Motani 31 2 0 05 Apr 2023
Mathematical Challenges in Deep Learning V. Nia Guojun Zhang I. Kobyzev Michael R. Metel Xinlin Li ... S. Hemati M. Asgharian Linglong Kong Wulong Liu Boxing Chen AI4CE VLM 37 1 0 24 Mar 2023
It Is All About Data: A Survey on the Effects of Data on Adversarial Robustness Peiyu Xiong Michael W. Tegegn Jaskeerat Singh Sarin Shubhraneel Pal Julia Rubin SILM AAML 37 8 0 17 Mar 2023
Inversion dynamics of class manifolds in deep learning reveals tradeoffs underlying generalisation Simone Ciceri Lorenzo Cassani Matteo Osella P. Rotondo P. Pizzochero M. Gherardi 44 7 0 09 Mar 2023
BrainBERT: Self-supervised representation learning for intracranial recordings Christopher Wang Vighnesh Subramaniam A. Yaari Gabriel Kreiman Boris Katz Ignacio Cases Andrei Barbu MedIm SSL 32 31 0 28 Feb 2023
The geometry of hidden representations of large transformer models L. Valeriani Diego Doimo F. Cuturello Alessandro Laio A. Ansuini Alberto Cazzaniga MILM 34 50 0 01 Feb 2023
On the Geometry of Reinforcement Learning in Continuous State and Action Spaces Saket Tiwari Omer Gottesman George Konidaris 29 0 0 29 Dec 2022
Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning Xiaoyue Duan Guoliang Kang Runqi Wang Shumin Han Shenjun Xue Tian Wang Baochang Zhang 34 2 0 28 Nov 2022
Linear Classification of Neural Manifolds with Correlated Variability Albert J. Wakhloo Tamara J. Sussman SueYeon Chung 29 10 0 27 Nov 2022
NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimension Xin He Jiangchao Yao Yuxin Wang Zhenheng Tang Ka Chu Cheung Simon See Bo Han Xiaowen Chu 24 9 0 23 Nov 2022
Internal Representations of Vision Models Through the Lens of Frames on Data Manifolds Henry Kvinge Grayson Jorgenson Davis Brown Charles Godfrey Tegan H. Emerson 59 2 0 19 Nov 2022
Dimensionality of datasets in object detection networks Ajay Chawda A. Vierling Karsten Berns 3DPC 18 0 0 13 Oct 2022
Verifying the Union of Manifolds Hypothesis for Image Data Bradley Brown Anthony L. Caterini Brendan Leigh Ross Jesse C. Cresswell Gabriel Loaiza-Ganem 44 39 0 06 Jul 2022
LIDL: Local Intrinsic Dimension Estimation Using Approximate Likelihood Piotr Tempczyk Rafał Michaluk Łukasz Garncarek Przemysław Spurek Jacek Tabor Adam Goliñski 35 26 0 29 Jun 2022
Learning sparse features can lead to overfitting in neural networks Leonardo Petrini Francesco Cagnetta Eric Vanden-Eijnden Matthieu Wyart MLT 47 23 0 24 Jun 2022
A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning Da-Wei Zhou Qiwen Wang Han-Jia Ye De-Chuan Zhan 36 125 0 26 May 2022
Toward a Geometrical Understanding of Self-supervised Contrastive Learning Romain Cosentino Anirvan M. Sengupta Salman Avestimehr Mahdi Soltanolkotabi Antonio Ortega Ted Willke Mariano Tepper SSL 50 17 0 13 May 2022
Low Dimensional Invariant Embeddings for Universal Geometric Learning Nadav Dym S. Gortler 34 39 0 05 May 2022
One Picture is Worth a Thousand Words: A New Wallet Recovery Process H. Chabanne Vincent Despiegel Linda Guiga 22 0 0 05 May 2022
DADApy: Distance-based Analysis of DAta-manifolds in Python Aldo Glielmo Iuri Macocco Diego Doimo Matteo Carli C. Zeni Romina Wild M. d’Errico Alex Rodriguez Alessandro Laio 11 37 0 04 May 2022
Topology and geometry of data manifold in deep learning German Magai A. Ayzenberg AAML 28 11 0 19 Apr 2022
Deep Layer-wise Networks Have Closed-Form Weights Chieh-Tsai Wu A. Masoomi Arthur Gretton Jennifer Dy 34 3 0 01 Feb 2022
Quantifying Relevance in Learning and Inference M. Marsili Y. Roudi 22 18 0 01 Feb 2022
Eigenvalues of Autoencoders in Training and at Initialization Ben Dees S. Agarwala Corey Lowman 29 0 0 27 Jan 2022
Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks Tolga Birdal Aaron Lou Leonidas J. Guibas Umut cSimcsekli 35 61 0 25 Nov 2021
Neural Population Geometry Reveals the Role of Stochasticity in Robust Perception Joel Dapello J. Feather Hang Le Tiago Marques David D. Cox Josh H. McDermott J. DiCarlo SueYeon Chung AAML OOD 19 25 0 12 Nov 2021
Channel redundancy and overlap in convolutional neural networks with channel-wise NNK graphs David Bonet Antonio Ortega Javier Ruiz-Hidalgo Sarath Shekkizhar GNN 33 7 0 18 Oct 2021