Cascade Processes for Sparse Machine Learning

Informacje na temat projektu

SPARSE-ML

Identyfikator umowy o grant: 101116395

DOI

10.3030/101116395

Data podpisania przez KE 25 Października 2023

Data rozpoczęcia 1 Grudnia 2023

Data zakończenia 30 Listopada 2028

Finansowanie w ramach

• European Research Council (ERC)

Koszt całkowity

€ 1 499 285,00

Wkład UE

€ 1 499 285,00

Koordynowany przez

CISPA - HELMHOLTZ-ZENTRUM FUR INFORMATIONSSICHERHEIT GGMBH
Germany

CORDIS oferuje możliwość skorzystania z odnośników do publicznie dostępnych publikacji i rezultatów projektów realizowanych w ramach programów ramowych HORYZONT.

Odnośniki do rezultatów i publikacji związanych z poszczególnymi projektami 7PR, a także odnośniki do niektórych konkretnych kategorii wyników, takich jak zbiory danych i oprogramowanie, są dynamicznie pobierane z systemu OpenAIRE .

Publikacje

Conference proceedings (31)

Robustness of Mixtures of Experts to Feature Noise

Autorzy: Dong Sun; Rahul Nittala; Rebekka Burkholz
Opublikowane w: Forty-third International Conference on Machine Learning, 2026, Numer 43, 2026
Wydawca: arXiv
DOI: 10.60882/CISPA.32771433

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

Autorzy: Intekhab Hossain, Jonas Fischer, Rebekka Burkholz, John Quackenbush
Opublikowane w: Advances in Neural Information Processing Systems 37, 2024
Wydawca: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.60882/CISPA.31169941

Bridging Domains through Subspace-Aware Model Merging

Autorzy: Levy Chaves; Chao Zhou; Rebekka Burkholz; Eduardo Valle; Andra Avila
Opublikowane w: IEEE Conference on Computer Vision and Pattern Recognition, 2026, 2026
Wydawca: Computer Vision Foundation (CVF) / IEEE

Are GATs Out of Balance?

Autorzy: Nimrah Mustafa; Aleksandar Bojchevski; Rebekka Burkholz
Opublikowane w: Thirty-seventh Conference on Neural Information Processing Systems, 2023, Numer 37, 2023, ISSN 1049-5258
Wydawca: NeurIPS
DOI: 10.60882/CISPA.25233052

Masks, Signs, And Learning Rate Rewinding.

Autorzy: Advait Gadhikar; Rebekka Burkholz
Opublikowane w: The Twelfth International Conference on Learning Representations, 2024, Numer 12, 2024
Wydawca: ICLR
DOI: 10.60882/CISPA.26808280

Fixed Aggregation Features Can Rival GNNs

Autorzy: Celia Rubio-Madrigal; Rebekka Burkholz
Opublikowane w: Forty-third International Conference on Machine Learning, 2026, Numer 43, 2026
Wydawca: PMLR
DOI: 10.60882/CISPA.32771526

When Shift Happens - Confounding Is to Blame

Autorzy: Abbavaram Gowtham Reddy; Celia Rubio-Madrigal; Rebekka Burkholz; Krikamol Muandet
Opublikowane w: The Fourteenth International Conference on Learning Representations, 2026, Numer 14, 2026
Wydawca: International Conference on Learning Representations (ICLR)
DOI: 10.60882/CISPA.31150255

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

Autorzy: Hoang Pham; The-Anh Ta; Tom Jacobs; Rebekka Burkholz; Long Tran-Thanh
Opublikowane w: The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025, Numer 39, 2025
Wydawca: eural Information Processing Systems Foundation
DOI: 10.60882/CISPA.31170061

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

Autorzy: Rebekka Burkholz, Jonas Fischer, Intekhab Hossain, John Quackenbush
Opublikowane w: Advances in Neural Information Processing Systems 37, 2025
Wydawca: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.52202/079017-3732

Spectral Graph Pruning Against Over-Squashing and Over-Smoothing

Autorzy: Adarsh Jamadandi, Celia Rubio-Madrigal, Rebekka Burkholz
Opublikowane w: Advances in Neural Information Processing Systems 37, 2026
Wydawca: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.60882/CISPA.31169929

SparseOpt: Addressing Normalization-induced Gradient Skew in Sparse Training

Autorzy: Mohammed Adnan; Rohan Jain; Tom Jacobs; Ekansh Sharma; Rahul G Krishnan; Rebekka Burkholz; Yani Ioannou
Opublikowane w: Forty-third International Conference on Machine Learning, 2026, Numer 43, 2026
Wydawca: OpenReview
DOI: 10.60882/CISPA.32771370

Linear GCNs Need Better Bias, Not More Expressive Power

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

HAM: A Hyperbolic Step to Regulate Implicit Bias

Autorzy: Tom Jacobs et al
Opublikowane w: 2026
Wydawca: International Con-ference on Learning Representations (ICLR)
DOI: 10.48550/ARXIV.2506.02630

Hyperbolic Aware Minimization: Implicit Bias for Sparsity

Autorzy: Tom Jacobs; Advait Gadhikar; Celia Rubio-Madrigal; Rebekka Burkholz
Opublikowane w: The Fourteenth International Conference on Learning Representations, 2026, Numer 41, 2026
Wydawca: arXiv
DOI: 10.60882/CISPA.31229218

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

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

HORST: Composing Optimizer Geometries for Sparse Transformer Training

Autorzy: Tom Jacobs; Rohan Jain; Rebekka Burkholz
Opublikowane w: Workshop on High-dimensional Learning Dynamics (HiLD) @ ICML, 2026, 2026
Wydawca: arXiv
DOI: 10.60882/CISPA.32771553

Batch normalization is sufficient for universal function approximation in CNNs

Autorzy: Rebekka Burkholz
Opublikowane w: The Twelfth International Conference on Learning Representations, 2024, Numer 12, 2024
Wydawca: International Conference on Learning Representations (ICLR)
DOI: 10.60882/CISPA.26892709

GATE: How to Keep Out Intrusive Neighbors

Autorzy: Nimrah Mustafa; Rebekka Burkholz
Opublikowane w: Forty-first International Conference on Machine Learning, 2024, Numer 41, 2024
Wydawca: PMLR
DOI: 10.60882/CISPA.27195786

Continuous Sparsification via Minimizing Movement

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

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

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

Boosting for Predictive Sufficiency

Autorzy: Abbavaram Gowtham Reddy; Rajeev Verma; Celia Rubio-Madrigal; Krikamol Muandet; Rebekka Burkholz
Opublikowane w: The Fourteenth International Conference on Learning Representations, 2026, Numer 14, 2026
Wydawca: International Con-ference on Learning Representations (ICLR)
DOI: 10.60882/CISPA.31150249

Spectral Graph Pruning Against Over-Squashing and Over-Smoothing

Autorzy: Rebekka Burkholz, Adarsh Jamadandi, Celia Rubio-Madrigal
Opublikowane w: Advances in Neural Information Processing Systems 37, 2024
Wydawca: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.52202/079017-0331

Edge-LLMs: Edge-Device Large Language Model Competition

Autorzy: 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
Opublikowane w: NeurIPS 2024 Competition Track, 2024, Numer 38, 2024
Wydawca: NeurIPS

Dynamic Rescaling for Training GNNs

Autorzy: Rebekka Burkholz, Nimrah Mustafa
Opublikowane w: Advances in Neural Information Processing Systems 37, 2024
Wydawca: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.60882/CISPA.31169848

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

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

Frequency-Based Hyperparameter Selection in Games

Autorzy: Aniket Sanyal et al.
Opublikowane w: 2026
Wydawca: ML Research Press (PMLR)
DOI: 10.60882/CISPA.31157677

GNNs Getting ComFy: Community and Feature Similarity Guided Rewiring

Autorzy: Celia Rubio-Madrigal; Adarsh Jamadandi; Rebekka Burkholz
Opublikowane w: The Thirteenth International Conference on Learning Representations, 2025, Numer 13, 2025
Wydawca: International Conference on Learning Representations
DOI: 10.60882/CISPA.28731815

Never Saddle for Reparameterized Steepest Descent as Mirror Flow

Autorzy: Tom Jacobs, Chao Zhou, and Rebekka Burkholz
Opublikowane w: The Fourteenth International Conference on Learning Representations, 2026, Numer 14, 2026
Wydawca: nternational Conference on Learning Representations (ICLR)
DOI: 10.60882/CISPA.31171063

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

Autorzy: Tom Jacobs, Chao Zhou, and Rebekka Burkholz
Opublikowane w: Forty-second International Conference on Machine Learning, 2025, Numer 42, 2025
Wydawca: Modern Language Association of America (PMLA)
DOI: 10.60882/CISPA.31169938

Mask in the Mirror: Implicit Sparsification

Autorzy: Tom Jacobs and Rebekka Burkholz
Opublikowane w: The Thirteenth International Conference on Learning Representations, 2025, Numer 13, 2025
Wydawca: arXiv
DOI: 10.60882/CISPA.31169785

Sign-In to the Lottery: Reparameterizing Sparse Training

Autorzy: Advait Gadhikar; Tom Jacobs; Chao Zhou; Rebekka Burkholz
Opublikowane w: The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025, Numer 39, 2025
Wydawca: 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

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

Biologically informed NeuralODEs for genome-wide regulatory dynamics

Autorzy: Intekhab Hossain, Viola Fanfani, Jonas Fischer, John Quackenbush, Rebekka Burkholz
Opublikowane w: Genome Biology, Numer 25, 2024, ISSN 1474-760X
Wydawca: Springer Science and Business Media LLC
DOI: 10.60882/CISPA.25469869