Cascade Processes for Sparse Machine Learning

Informations projet

SPARSE-ML

N° de convention de subvention: 101116395

DOI

10.3030/101116395

Date de signature de la CE 25 Octobre 2023

Date de début 1 Decembre 2023

Date de fin 30 Novembre 2028

Financé au titre de

• European Research Council (ERC)

Coût total

€ 1 499 285,00

Contribution de l’UE

€ 1 499 285,00

Coordonné par

CISPA - HELMHOLTZ-ZENTRUM FUR INFORMATIONSSICHERHEIT GGMBH
Germany

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Publications

Conference proceedings (31)

Robustness of Mixtures of Experts to Feature Noise

Auteurs: Dong Sun; Rahul Nittala; Rebekka Burkholz
Publié dans: Forty-third International Conference on Machine Learning, 2026, Numéro 43, 2026
Éditeur: arXiv
DOI: 10.60882/CISPA.32771433

Pruning neural network models for gene regulatory dynamics using data and domain knowledge

Auteurs: Intekhab Hossain, Jonas Fischer, Rebekka Burkholz, John Quackenbush
Publié dans: Advances in Neural Information Processing Systems 37, 2024
Éditeur: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.60882/CISPA.31169941

Bridging Domains through Subspace-Aware Model Merging

Auteurs: Levy Chaves; Chao Zhou; Rebekka Burkholz; Eduardo Valle; Andra Avila
Publié dans: IEEE Conference on Computer Vision and Pattern Recognition, 2026, 2026
Éditeur: Computer Vision Foundation (CVF) / IEEE

Are GATs Out of Balance?

Auteurs: Nimrah Mustafa; Aleksandar Bojchevski; Rebekka Burkholz
Publié dans: Thirty-seventh Conference on Neural Information Processing Systems, 2023, Numéro 37, 2023, ISSN 1049-5258
Éditeur: NeurIPS
DOI: 10.60882/CISPA.25233052

Masks, Signs, And Learning Rate Rewinding.

Auteurs: Advait Gadhikar; Rebekka Burkholz
Publié dans: The Twelfth International Conference on Learning Representations, 2024, Numéro 12, 2024
Éditeur: ICLR
DOI: 10.60882/CISPA.26808280

Fixed Aggregation Features Can Rival GNNs

Auteurs: Celia Rubio-Madrigal; Rebekka Burkholz
Publié dans: Forty-third International Conference on Machine Learning, 2026, Numéro 43, 2026
Éditeur: PMLR
DOI: 10.60882/CISPA.32771526

When Shift Happens - Confounding Is to Blame

Auteurs: Abbavaram Gowtham Reddy; Celia Rubio-Madrigal; Rebekka Burkholz; Krikamol Muandet
Publié dans: The Fourteenth International Conference on Learning Representations, 2026, Numéro 14, 2026
Éditeur: International Conference on Learning Representations (ICLR)
DOI: 10.60882/CISPA.31150255

The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis

Auteurs: Hoang Pham; The-Anh Ta; Tom Jacobs; Rebekka Burkholz; Long Tran-Thanh
Publié dans: The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025, Numéro 39, 2025
Éditeur: eural Information Processing Systems Foundation
DOI: 10.60882/CISPA.31170061

Pruning neural network models for gene regulatory dynamics using data and domain knowledge

Auteurs: Rebekka Burkholz, Jonas Fischer, Intekhab Hossain, John Quackenbush
Publié dans: Advances in Neural Information Processing Systems 37, 2025
Éditeur: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.52202/079017-3732

Spectral Graph Pruning Against Over-Squashing and Over-Smoothing

Auteurs: Adarsh Jamadandi, Celia Rubio-Madrigal, Rebekka Burkholz
Publié dans: Advances in Neural Information Processing Systems 37, 2026
Éditeur: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.60882/CISPA.31169929

SparseOpt: Addressing Normalization-induced Gradient Skew in Sparse Training

Auteurs: Mohammed Adnan; Rohan Jain; Tom Jacobs; Ekansh Sharma; Rahul G Krishnan; Rebekka Burkholz; Yani Ioannou
Publié dans: Forty-third International Conference on Machine Learning, 2026, Numéro 43, 2026
Éditeur: OpenReview
DOI: 10.60882/CISPA.32771370

Linear GCNs Need Better Bias, Not More Expressive Power

Auteurs: Celia Rubio-Madrigal; Rebekka Burkhol
Publié dans: Workshop on Graph Foundation Models: A New Era for Graph Machine Learning (GFM) @ ICML, 2026, 2026
Éditeur: OpenReview
DOI: 10.60882/CISPA.32771808

HAM: A Hyperbolic Step to Regulate Implicit Bias

Auteurs: Tom Jacobs et al
Publié dans: 2026
Éditeur: International Con-ference on Learning Representations (ICLR)
DOI: 10.48550/ARXIV.2506.02630

Hyperbolic Aware Minimization: Implicit Bias for Sparsity

Auteurs: Tom Jacobs; Advait Gadhikar; Celia Rubio-Madrigal; Rebekka Burkholz
Publié dans: The Fourteenth International Conference on Learning Representations, 2026, Numéro 41, 2026
Éditeur: arXiv
DOI: 10.60882/CISPA.31229218

Multi-Agent Systems are Mixtures of Experts: Who Becomes an Influencer?

Auteurs: Franka Bause; Jonas Niederle; Martin Pawelczyk; Rebekka Burkholz
Publié dans: Workshop on Compositional Learning: Safety, Interpretability, and Agents (CompLearn) @ ICML, 2026, 2026
Éditeur: arXiv
DOI: 10.60882/CISPA.32771649

HORST: Composing Optimizer Geometries for Sparse Transformer Training

Auteurs: Tom Jacobs; Rohan Jain; Rebekka Burkholz
Publié dans: Workshop on High-dimensional Learning Dynamics (HiLD) @ ICML, 2026, 2026
Éditeur: arXiv
DOI: 10.60882/CISPA.32771553

Batch normalization is sufficient for universal function approximation in CNNs

Auteurs: Rebekka Burkholz
Publié dans: The Twelfth International Conference on Learning Representations, 2024, Numéro 12, 2024
Éditeur: International Conference on Learning Representations (ICLR)
DOI: 10.60882/CISPA.26892709

GATE: How to Keep Out Intrusive Neighbors

Auteurs: Nimrah Mustafa; Rebekka Burkholz
Publié dans: Forty-first International Conference on Machine Learning, 2024, Numéro 41, 2024
Éditeur: PMLR
DOI: 10.60882/CISPA.27195786

Continuous Sparsification via Minimizing Movement

Auteurs: Hoang Pham; Tom Jacobs; Binh Nguyen; Rebekka Burkholz; Long Tran-Thanh
Publié dans: Workshop on High-dimensional Learning Dynamics (HiLD) @ ICML, 2026, 2026
Éditeur: PMLR
DOI: 10.60882/CISPA.32771496

Prune to Protect: Faster Training and Enhanced Privacy by Dynamic Data Pruning

Auteurs: Chinmay Joshi; Advait Gadhikar; Celia Rubio-Madrigal; Aneet Kumar Dutta; Mridula Singh; Rebekka Burkholz
Publié dans: Workshop on The Impact of Memorization on Trustworthy Foundation Models (MemFM) @ ICML, 2026, 2026
Éditeur: OpenReview
DOI: 10.60882/CISPA.32771721

Boosting for Predictive Sufficiency

Auteurs: Abbavaram Gowtham Reddy; Rajeev Verma; Celia Rubio-Madrigal; Krikamol Muandet; Rebekka Burkholz
Publié dans: The Fourteenth International Conference on Learning Representations, 2026, Numéro 14, 2026
Éditeur: International Con-ference on Learning Representations (ICLR)
DOI: 10.60882/CISPA.31150249

Spectral Graph Pruning Against Over-Squashing and Over-Smoothing

Auteurs: Rebekka Burkholz, Adarsh Jamadandi, Celia Rubio-Madrigal
Publié dans: Advances in Neural Information Processing Systems 37, 2024
Éditeur: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.52202/079017-0331

Edge-LLMs: Edge-Device Large Language Model Competition

Auteurs: Shiwei Liu; Kai Han; Adriana Fernandez-Lopez; Ajay Kumar Jaiswal; Zahra Atashgahi; Boqian Wu; Edoardo Ponti; Callie Hao; Rebekka Burkholz; Olga Saukh; Lu Yin; Andreas Zinonos; Tianjin Huang; Jared Tanner; Yunhe Wang
Publié dans: NeurIPS 2024 Competition Track, 2024, Numéro 38, 2024
Éditeur: NeurIPS

Dynamic Rescaling for Training GNNs

Auteurs: Rebekka Burkholz, Nimrah Mustafa
Publié dans: Advances in Neural Information Processing Systems 37, 2024
Éditeur: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.60882/CISPA.31169848

Don't Trust Stubborn Neighbors: A Security Framework for Agentic Networks

Auteurs: Samira Abedini; Sina Mavali; Lea Schönherr; Martin Pawelczyk; Rebekka Burkholz
Publié dans: Workshop on Compositional Learning: Safety, Interpretability, and Agents (CompLearn) @ ICML, 2026, 2026
Éditeur: PMLR
DOI: 10.60882/CISPA.32771607

Frequency-Based Hyperparameter Selection in Games

Auteurs: Aniket Sanyal et al.
Publié dans: 2026
Éditeur: ML Research Press (PMLR)
DOI: 10.60882/CISPA.31157677

GNNs Getting ComFy: Community and Feature Similarity Guided Rewiring

Auteurs: Celia Rubio-Madrigal; Adarsh Jamadandi; Rebekka Burkholz
Publié dans: The Thirteenth International Conference on Learning Representations, 2025, Numéro 13, 2025
Éditeur: International Conference on Learning Representations
DOI: 10.60882/CISPA.28731815

Never Saddle for Reparameterized Steepest Descent as Mirror Flow

Auteurs: Tom Jacobs, Chao Zhou, and Rebekka Burkholz
Publié dans: The Fourteenth International Conference on Learning Representations, 2026, Numéro 14, 2026
Éditeur: nternational Conference on Learning Representations (ICLR)
DOI: 10.60882/CISPA.31171063

Mirror, Mirror of the Flow: How Does Regular-ization Shape Implicit Bias?

Auteurs: Tom Jacobs, Chao Zhou, and Rebekka Burkholz
Publié dans: Forty-second International Conference on Machine Learning, 2025, Numéro 42, 2025
Éditeur: Modern Language Association of America (PMLA)
DOI: 10.60882/CISPA.31169938

Mask in the Mirror: Implicit Sparsification

Auteurs: Tom Jacobs and Rebekka Burkholz
Publié dans: The Thirteenth International Conference on Learning Representations, 2025, Numéro 13, 2025
Éditeur: arXiv
DOI: 10.60882/CISPA.31169785

Sign-In to the Lottery: Reparameterizing Sparse Training

Auteurs: Advait Gadhikar; Tom Jacobs; Chao Zhou; Rebekka Burkholz
Publié dans: The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025, Numéro 39, 2025
Éditeur: Conference on Neural Information Processing Systems (NeurIPS)
DOI: 10.60882/CISPA.31169662

Peer reviewed articles (2)

Sex differences in gene regulation and its impact on cancer incidence

Auteurs: Camila M. Lopes-Ramos, Rebekka Burkholz, Marouen Ben Guebila, Viola Fanfani, Enakshi Saha, Katherine H. Shutta, Kimberly Glass, John Quackenbush, Dawn L. DeMeo
Publié dans: iScience, Numéro 29, 2026, ISSN 2589-0042
Éditeur: Elsevier BV
DOI: 10.60882/CISPA.32323656

Biologically informed NeuralODEs for genome-wide regulatory dynamics

Auteurs: Intekhab Hossain, Viola Fanfani, Jonas Fischer, John Quackenbush, Rebekka Burkholz
Publié dans: Genome Biology, Numéro 25, 2024, ISSN 1474-760X
Éditeur: Springer Science and Business Media LLC
DOI: 10.60882/CISPA.25469869