Improving Knowledge Distillation in Transfer Learning with Layer-wise Learning Rates
원문 초록
Transfer learning methods start performing poorly when the complexity of the learning task is increased. Most of these methods calculate the cumulative differences of all the matched features and then use them to back-propagate that loss through all the layers. Contrary to these methods, in this work, we propose a novel layer-wise learning scheme that adjusts learning parameters per layer as a function of the differences in the Jacobian/Attention/Hessian of the output activations w.r.t. the network parameters. We applied this novel scheme for attention map-based and derivative-based (first and second order) transfer learning methods. We received improved learning performance and stability against a wide range of datasets. From extensive experimental evaluation, we observed that the performance boost achieved by our method becomes more significant with the increasing difficulty of the learning task.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Knowledge Grafting of Large Language Models
Distilling Normalizing Flows
Client Clustering Meets Knowledge Sharing: Enhancing Privacy and Robustness in Personalized Peer-to-Peer Learning
AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes
Proactive Guidance of Multi-Turn Conversation in Industrial Search
Progressive Class-level Distillation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.