MergeNet: Knowledge Migration across Heterogeneous Models, Tasks, and Modalities

arXiv:2404.13322v1 Announce Type: new
Abstract: In this study, we focus on heterogeneous knowledge transfer across entirely different model architectures, tasks, and modalities. Existing knowledge transfer methods (e.g., backbone sharing, knowledge distillation) often hinge on shared elements within model structures or task-specific features/labels, limiting transfers to complex model types or tasks. To overcome these challenges, we present MergeNet, which learns to bridge the gap of parameter spaces of heterogeneous models, facilitating the direct interaction, extraction, and application of knowledge within these …

abstract architectures arxiv cs.ai cs.lg distillation features focus hinge knowledge labels migration study tasks transfer type types