Cascade Processes for Sparse Machine Learning

Información del proyecto

SPARSE-ML

Identificador del acuerdo de subvención: 101116395

DOI

10.3030/101116395

Fecha de la firma de la CE 25 Octubre 2023

Fecha de inicio 1 Diciembre 2023

Fecha de finalización 30 Noviembre 2028

Financiado con arreglo a

• European Research Council (ERC)

Coste total

€ 1 499 285,00

Aportación de la UE

€ 1 499 285,00

Coordinado por

CISPA - HELMHOLTZ-ZENTRUM FUR INFORMATIONSSICHERHEIT GGMBH
Germany

CORDIS proporciona enlaces a los documentos públicos y las publicaciones de los proyectos de los programas marco HORIZONTE.

Los enlaces a los documentos y las publicaciones de los proyectos del Séptimo Programa Marco, así como los enlaces a algunos tipos de resultados específicos, como conjuntos de datos y «software», se obtienen dinámicamente de OpenAIRE .

Publicaciones

Conference proceedings (31)

Robustness of Mixtures of Experts to Feature Noise

Autores: Dong Sun; Rahul Nittala; Rebekka Burkholz
Publicado en: Forty-third International Conference on Machine Learning, 2026, Edición 43, 2026
Editor: arXiv
DOI: 10.60882/CISPA.32771433

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

Autores: Intekhab Hossain, Jonas Fischer, Rebekka Burkholz, John Quackenbush
Publicado en: Advances in Neural Information Processing Systems 37, 2024
Editor: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.60882/CISPA.31169941

Bridging Domains through Subspace-Aware Model Merging

Autores: Levy Chaves; Chao Zhou; Rebekka Burkholz; Eduardo Valle; Andra Avila
Publicado en: IEEE Conference on Computer Vision and Pattern Recognition, 2026, 2026
Editor: Computer Vision Foundation (CVF) / IEEE

Are GATs Out of Balance?

Autores: Nimrah Mustafa; Aleksandar Bojchevski; Rebekka Burkholz
Publicado en: Thirty-seventh Conference on Neural Information Processing Systems, 2023, Edición 37, 2023, ISSN 1049-5258
Editor: NeurIPS
DOI: 10.60882/CISPA.25233052

Masks, Signs, And Learning Rate Rewinding.

Autores: Advait Gadhikar; Rebekka Burkholz
Publicado en: The Twelfth International Conference on Learning Representations, 2024, Edición 12, 2024
Editor: ICLR
DOI: 10.60882/CISPA.26808280

Fixed Aggregation Features Can Rival GNNs

Autores: Celia Rubio-Madrigal; Rebekka Burkholz
Publicado en: Forty-third International Conference on Machine Learning, 2026, Edición 43, 2026
Editor: PMLR
DOI: 10.60882/CISPA.32771526

When Shift Happens - Confounding Is to Blame

Autores: Abbavaram Gowtham Reddy; Celia Rubio-Madrigal; Rebekka Burkholz; Krikamol Muandet
Publicado en: The Fourteenth International Conference on Learning Representations, 2026, Edición 14, 2026
Editor: International Conference on Learning Representations (ICLR)
DOI: 10.60882/CISPA.31150255

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

Autores: Hoang Pham; The-Anh Ta; Tom Jacobs; Rebekka Burkholz; Long Tran-Thanh
Publicado en: The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025, Edición 39, 2025
Editor: eural Information Processing Systems Foundation
DOI: 10.60882/CISPA.31170061

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

Autores: Rebekka Burkholz, Jonas Fischer, Intekhab Hossain, John Quackenbush
Publicado en: Advances in Neural Information Processing Systems 37, 2025
Editor: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.52202/079017-3732

Spectral Graph Pruning Against Over-Squashing and Over-Smoothing

Autores: Adarsh Jamadandi, Celia Rubio-Madrigal, Rebekka Burkholz
Publicado en: Advances in Neural Information Processing Systems 37, 2026
Editor: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.60882/CISPA.31169929

SparseOpt: Addressing Normalization-induced Gradient Skew in Sparse Training

Autores: Mohammed Adnan; Rohan Jain; Tom Jacobs; Ekansh Sharma; Rahul G Krishnan; Rebekka Burkholz; Yani Ioannou
Publicado en: Forty-third International Conference on Machine Learning, 2026, Edición 43, 2026
Editor: OpenReview
DOI: 10.60882/CISPA.32771370

Linear GCNs Need Better Bias, Not More Expressive Power

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

HAM: A Hyperbolic Step to Regulate Implicit Bias

Autores: Tom Jacobs et al
Publicado en: 2026
Editor: International Con-ference on Learning Representations (ICLR)
DOI: 10.48550/ARXIV.2506.02630

Hyperbolic Aware Minimization: Implicit Bias for Sparsity

Autores: Tom Jacobs; Advait Gadhikar; Celia Rubio-Madrigal; Rebekka Burkholz
Publicado en: The Fourteenth International Conference on Learning Representations, 2026, Edición 41, 2026
Editor: arXiv
DOI: 10.60882/CISPA.31229218

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

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

HORST: Composing Optimizer Geometries for Sparse Transformer Training

Autores: Tom Jacobs; Rohan Jain; Rebekka Burkholz
Publicado en: Workshop on High-dimensional Learning Dynamics (HiLD) @ ICML, 2026, 2026
Editor: arXiv
DOI: 10.60882/CISPA.32771553

Batch normalization is sufficient for universal function approximation in CNNs

Autores: Rebekka Burkholz
Publicado en: The Twelfth International Conference on Learning Representations, 2024, Edición 12, 2024
Editor: International Conference on Learning Representations (ICLR)
DOI: 10.60882/CISPA.26892709

GATE: How to Keep Out Intrusive Neighbors

Autores: Nimrah Mustafa; Rebekka Burkholz
Publicado en: Forty-first International Conference on Machine Learning, 2024, Edición 41, 2024
Editor: PMLR
DOI: 10.60882/CISPA.27195786

Continuous Sparsification via Minimizing Movement

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

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

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

Boosting for Predictive Sufficiency

Autores: Abbavaram Gowtham Reddy; Rajeev Verma; Celia Rubio-Madrigal; Krikamol Muandet; Rebekka Burkholz
Publicado en: The Fourteenth International Conference on Learning Representations, 2026, Edición 14, 2026
Editor: International Con-ference on Learning Representations (ICLR)
DOI: 10.60882/CISPA.31150249

Spectral Graph Pruning Against Over-Squashing and Over-Smoothing

Autores: Rebekka Burkholz, Adarsh Jamadandi, Celia Rubio-Madrigal
Publicado en: Advances in Neural Information Processing Systems 37, 2024
Editor: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.52202/079017-0331

Edge-LLMs: Edge-Device Large Language Model Competition

Autores: 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
Publicado en: NeurIPS 2024 Competition Track, 2024, Edición 38, 2024
Editor: NeurIPS

Dynamic Rescaling for Training GNNs

Autores: Rebekka Burkholz, Nimrah Mustafa
Publicado en: Advances in Neural Information Processing Systems 37, 2024
Editor: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.60882/CISPA.31169848

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

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

Frequency-Based Hyperparameter Selection in Games

Autores: Aniket Sanyal et al.
Publicado en: 2026
Editor: ML Research Press (PMLR)
DOI: 10.60882/CISPA.31157677

GNNs Getting ComFy: Community and Feature Similarity Guided Rewiring

Autores: Celia Rubio-Madrigal; Adarsh Jamadandi; Rebekka Burkholz
Publicado en: The Thirteenth International Conference on Learning Representations, 2025, Edición 13, 2025
Editor: International Conference on Learning Representations
DOI: 10.60882/CISPA.28731815

Never Saddle for Reparameterized Steepest Descent as Mirror Flow

Autores: Tom Jacobs, Chao Zhou, and Rebekka Burkholz
Publicado en: The Fourteenth International Conference on Learning Representations, 2026, Edición 14, 2026
Editor: nternational Conference on Learning Representations (ICLR)
DOI: 10.60882/CISPA.31171063

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

Autores: Tom Jacobs, Chao Zhou, and Rebekka Burkholz
Publicado en: Forty-second International Conference on Machine Learning, 2025, Edición 42, 2025
Editor: Modern Language Association of America (PMLA)
DOI: 10.60882/CISPA.31169938

Mask in the Mirror: Implicit Sparsification

Autores: Tom Jacobs and Rebekka Burkholz
Publicado en: The Thirteenth International Conference on Learning Representations, 2025, Edición 13, 2025
Editor: arXiv
DOI: 10.60882/CISPA.31169785

Sign-In to the Lottery: Reparameterizing Sparse Training

Autores: Advait Gadhikar; Tom Jacobs; Chao Zhou; Rebekka Burkholz
Publicado en: The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025, Edición 39, 2025
Editor: 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

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

Biologically informed NeuralODEs for genome-wide regulatory dynamics

Autores: Intekhab Hossain, Viola Fanfani, Jonas Fischer, John Quackenbush, Rebekka Burkholz
Publicado en: Genome Biology, Edición 25, 2024, ISSN 1474-760X
Editor: Springer Science and Business Media LLC
DOI: 10.60882/CISPA.25469869