arXiv Machine Learning

Hierarchical Projection for Adaptive Knowledge Transfer

arXiv:2606. 08691v1 Announce Type: new Abstract: Modern data-driven applications increasingly involve learning from multiple heterogeneous sources, where a target dataset is limited but related information is available across domains.

Hugging Face Trending Papers
Jul 23

UnDA: Unpaired Domain Alignment for Cross-Modal Knowledge Transfer in Medical Imaging

Multimodal based approaches often outperform single modality approaches in downstream tasks as the different modalities provide complementary information, yet acquiring paired clinical data remains a significant challenge in real world scenarios. While cross-modal knowledge distillation addresses this, existing methods often struggle with large modality gaps and the propagation of noise from uncertain source-domain predictions.

arXiv AI
Aug 11

Biologically Informed Representation Learning for Robust Cross-Center Generalization of MALDI-TOF Mass Spectrometry

arXiv:2608. 08182v1 Announce Type: cross Abstract: Machine learning models for MALDI-TOF mass spectrometry have shown considerable promise for clinical microbiology tasks such as microbial identification and antimicrobial resistance prediction.

By Alejandro L. Garc\'ia-Navarro, Carlos Sevilla-Salcedo, Bel\'en Rodr\'iguez-S\'anchez, Vanessa G\'omez-Verdejo
arXiv Machine Learning
Jun 16

GRASP: Gradient-Aligned Sequential Parameter Transfer for Memory-Efficient Multi-Source Learning

arXiv:2606. 14900v1 Announce Type: new Abstract: Multi-source transfer learning faces a fundamental scalability bottleneck: existing approaches require either loading all K source models into memory simultaneously during parameter fusion, requiring O(K) memory, or deploying all models at inference time, making production deployment infeasible.

By Mary Isabelle Wisell, Nicholas Jacobs, Aayush Manandhar, Salimeh Yasaei Sekeh
arXiv Machine Learning
Aug 11

CPDA: Class-Conditional Path Distribution Alignment for Unsupervised Time-Series Domain Adaptation

arXiv:2608. 09193v1 Announce Type: cross Abstract: Unsupervised time-series domain adaptation (DA) addresses the challenge of transferring a classifier from a labeled source domain to an unlabeled target domain under distribution shifts induced by different users, sensors, devices, acquisition conditions, or temporal dynamics.

By Felix Ott, Christopher Mutschler