{"ID":2892121,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.15336","arxiv_id":"2507.15336","title":"Beyond Model Base Retrieval: Weaving Knowledge to Master Fine-grained Neural Network Design","abstract":"Designing high-performance neural networks for new tasks requires balancing optimization quality with search efficiency. Current methods fail to achieve this balance: neural architectural search is computationally expensive, while model retrieval often yields suboptimal static checkpoints. To resolve this dilemma, we model the performance gains induced by fine-grained architectural modifications as edit-effect evidence and build evidence graphs from prior tasks. By constructing a retrieval-augmented model refinement framework, our proposed M-DESIGN dynamically weaves historical evidence to discover near-optimal modification paths. M-DESIGN features an adaptive retrieval mechanism that quickly calibrates the evolving transferability of edit-effect evidence from different sources. To handle out-of-distribution shifts, we introduce predictive task planners that extrapolate gains from multi-hop evidence, thereby reducing reliance on an exhaustive repository. Based on our model knowledge base of 67,760 graph neural networks across 22 datasets, extensive experiments demonstrate that M-DESIGN consistently outperforms baselines, achieving the search-space best performance in 26 out of 33 cases under a strict budget.","short_abstract":"Designing high-performance neural networks for new tasks requires balancing optimization quality with search efficiency. Current methods fail to achieve this balance: neural architectural search is computationally expensive, while model retrieval often yields suboptimal static checkpoints. To resolve this dilemma, we m...","url_abs":"https://arxiv.org/abs/2507.15336","url_pdf":"https://arxiv.org/pdf/2507.15336v2","authors":"[\"Jialiang Wang\",\"Hanmo Liu\",\"Shimin Di\",\"Zhili Wang\",\"Jiachuan Wang\",\"Lei Chen\",\"Xiaofang Zhou\"]","published":"2025-07-21T07:49:19Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.DB\"]","methods":"[\"Graph Neural Network\"]","has_code":false}