Unified Principles For Multi-Source Transfer Learning Under Label Shifts
We study the label shift problem in multi-source transfer learning and derive new generic principles to control the target generalization risk. Our theoretical grounded framework unifies the principles of conditional feature alignment, label distribution ratio estimation and domain relation weights estimation. Moreover, the inspired practice provides a unified algorithm for various multi-source label shift transfer scenarios: learning with limited target data, unsupervised domain adaptation and label partial unsupervised domain adaptation. We evaluate the proposed method on these scenarios by extensive experiments and show that our proposed algorithm can significantly outperform the baselines.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationTransfer LearningUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Noise May Contain Transferable Knowledge: Understanding Semi-supervised Heterogeneous Domain Adaptation from an Empirical Perspective
Semi-supervised heterogeneous domain adaptation (SHDA) addresses learning across domains with distinct feature representations and distributions, where source samples are labeled while most target samples are unlabeled, …
Domain AdaptationTransfer LearningSelection, Ensemble, and Adaptation: Advancing Multi-Source-Free Domain Adaptation via Architecture Zoo
Conventional Multi-Source Free Domain Adaptation (MSFDA) assumes that each source domain provides a single source model, and all source models adopt a uniform architecture. This paper introduces Zoo-MSFDA, a more general…
Domain AdaptationModel SelectionSource-Free Domain AdaptationUnsupervised Domain AdaptationParallelKittens: Systematic and Practical Simplification of Multi-GPU AI Kernels
Inter-GPU communication has become a major bottleneck for modern AI workloads as models scale and improvements in hardware compute throughput outpace improvements in interconnect bandwidth. Existing systems mitigate this…
UniPINN: A Unified PINN Framework for Multi-task Learning of Diverse Navier-Stokes Equations
Physics-Informed Neural Networks (PINNs) have shown promise in solving incompressible Navier-Stokes equations, yet existing approaches are predominantly designed for single-flow settings. When extended to multi-flow scen…
Multi-Task LearningLance: Unified Multimodal Modeling by Multi-Task Synergy
We present Lance, a lightweight native unified model supporting multimodal understanding, generation, and editing for both images and videos. Rather than relying on model capacity scaling or text-image-dominant designs, …
Video Generation