MergeNet: Knowledge Migration across Heterogeneous Models, Tasks, and Modalities
This addresses the limitation of existing knowledge transfer methods that rely on shared elements, enabling broader applicability across diverse AI models and tasks.
The paper tackles the problem of transferring knowledge across models with different architectures, tasks, and modalities, and presents MergeNet, which uses parameter adapters to bridge parameter spaces, resulting in significant improvements in challenging heterogeneous transfer settings.
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 parameter spaces. The core mechanism of MergeNet lies in the parameter adapter, which operates by querying the source model's low-rank parameters and adeptly learning to identify and map parameters into the target model. MergeNet is learned alongside both models, allowing our framework to dynamically transfer and adapt knowledge relevant to the current stage, including the training trajectory knowledge of the source model. Extensive experiments on heterogeneous knowledge transfer demonstrate significant improvements in challenging settings, where representative approaches may falter or prove less applicable.