MetaLLMix : An XAI Aided LLM-Meta-learning Based Approach for Hyper-parameters Optimization
This addresses the challenge of automating hyperparameter selection for deep learning practitioners, particularly in medical imaging, offering a more efficient and interpretable alternative to existing methods, though it is incremental as it builds on prior LLM and meta-learning approaches.
The paper tackles hyperparameter optimization in deep learning by proposing MetaLLMiX, a zero-shot framework combining meta-learning, explainable AI, and LLMs, which achieves competitive or superior performance to traditional methods on medical imaging datasets while drastically reducing computational costs, with response time reductions of 99.6-99.9% and training times up to 15.7x faster.
Effective model and hyperparameter selection remains a major challenge in deep learning, often requiring extensive expertise and computation. While AutoML and large language models (LLMs) promise automation, current LLM-based approaches rely on trial and error and expensive APIs, which provide limited interpretability and generalizability. We propose MetaLLMiX, a zero-shot hyperparameter optimization framework combining meta-learning, explainable AI, and efficient LLM reasoning. By leveraging historical experiment outcomes with SHAP explanations, MetaLLMiX recommends optimal hyperparameters and pretrained models without additional trials. We further employ an LLM-as-judge evaluation to control output format, accuracy, and completeness. Experiments on eight medical imaging datasets using nine open-source lightweight LLMs show that MetaLLMiX achieves competitive or superior performance to traditional HPO methods while drastically reducing computational cost. Our local deployment outperforms prior API-based approaches, achieving optimal results on 5 of 8 tasks, response time reductions of 99.6-99.9%, and the fastest training times on 6 datasets (2.4-15.7x faster), maintaining accuracy within 1-5% of best-performing baselines.