Beyond Model Base Selection: Weaving Knowledge to Master Fine-grained Neural Network Design

• URL: http://arxiv.org/abs/2507.15336v1
• Date: Mon, 21 Jul 2025 07:49:19 GMT
• Title: Beyond Model Base Selection: Weaving Knowledge to Master Fine-grained Neural Network Design
• Authors: Jialiang Wang, Hanmo Liu, Shimin Di, Zhili Wang, Jiachuan Wang, Lei Chen, Xiaofang Zhou,
• Abstract summary: We propose M-DESIGN, a curated model knowledge base (MKB) pipeline for mastering neural network refinement.<n>First, we propose a knowledge weaving engine that reframes model refinement as an adaptive query problem over task metadata.<n>Given a user's task query, M-DESIGN quickly matches and iteratively refines candidate models by leveraging a graph-relational knowledge schema.
• Score: 20.31388126105889
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Database systems have recently advocated for embedding machine learning (ML) capabilities, offering declarative model queries over large, managed model repositories, thereby circumventing the huge computational overhead of traditional ML-based algorithms in automated neural network model selection. Pioneering database studies aim to organize existing benchmark repositories as model bases (MB), querying them for the model records with the highest performance estimation metrics for given tasks. However, this static model selection practice overlooks the fine-grained, evolving relational dependencies between diverse task queries and model architecture variations, resulting in suboptimal matches and failing to further refine the model effectively. To fill the model refinement gap in database research, we propose M-DESIGN, a curated model knowledge base (MKB) pipeline for mastering neural network refinement by adaptively weaving prior insights about model architecture modification. First, we propose a knowledge weaving engine that reframes model refinement as an adaptive query problem over task metadata. Given a user's task query, M-DESIGN quickly matches and iteratively refines candidate models by leveraging a graph-relational knowledge schema that explicitly encodes data properties, architecture variations, and pairwise performance deltas as joinable relations. This schema supports fine-grained relational analytics over architecture tweaks and drives a predictive query planner that can detect and adapt to out-of-distribution (OOD) tasks. We instantiate M-DESIGN for graph analytics tasks, where our model knowledge base enriches existing benchmarks with structured metadata covering 3 graph tasks and 22 graph datasets, contributing data records of 67,760 graph models. Empirical results demonstrate that M-DESIGN delivers the optimal model in 26 of 33 data-task pairs within limited budgets.

Related papers

• Relational Deep Learning: Challenges, Foundations and Next-Generation Architectures [50.46688111973999]
  Graph machine learning has led to a significant increase in the capabilities of models that learn on arbitrary graph-structured data.<n>We present a new blueprint that enables end-to-end representation of'relational entity graphs' without traditional engineering feature.<n>We discuss key challenges including large-scale multi-table integration and the complexities of modeling temporal dynamics and heterogeneous data.
  arXiv  Detail & Related papers  (2025-06-19T23:51:38Z)
• RDB2G-Bench: A Comprehensive Benchmark for Automatic Graph Modeling of Relational Databases [23.836665904554426]
  RDB-to-graph modeling helps capture cross-table dependencies, leading to enhanced performance across diverse tasks.<n>Applying a common rule for graph modeling leads to a 10% drop in performance compared to the best-performing graph model.<n>We introduce RDB2G, the first benchmark framework for evaluating such methods.
  arXiv  Detail & Related papers  (2025-06-02T06:34:10Z)
• SchemaAgent: A Multi-Agents Framework for Generating Relational Database Schema [35.57815867567431]
  Existing efforts are mostly based on customized rules or conventional deep learning models, often producing relational schema.<n>We propose a unified LLM-based multi-agent framework for the automated generation of high-quality database schema.Agent.<n>We incorporate dedicated roles for reflection and inspection, alongside an innovative error detection and correction mechanism to identify rectify issues across various phases.
  arXiv  Detail & Related papers  (2025-03-31T09:39:19Z)
• Matchmaker: Self-Improving Large Language Model Programs for Schema Matching [60.23571456538149]
  We propose a compositional language model program for schema matching, comprised of candidate generation, refinement and confidence scoring. Matchmaker self-improves in a zero-shot manner without the need for labeled demonstrations. Empirically, we demonstrate on real-world medical schema matching benchmarks that Matchmaker outperforms previous ML-based approaches.
  arXiv  Detail & Related papers  (2024-10-31T16:34:03Z)
• Can Models Help Us Create Better Models? Evaluating LLMs as Data Scientists [41.94295877935867]
  We present a benchmark for large language models designed to tackle one of the most knowledge-intensive tasks in data science. We demonstrate that the FeatEng of our proposal can cheaply and efficiently assess the broad capabilities of LLMs.
  arXiv  Detail & Related papers  (2024-10-30T17:59:01Z)
• RelBench: A Benchmark for Deep Learning on Relational Databases [78.52438155603781]
  We present RelBench, a public benchmark for solving tasks over databases with graph neural networks. We use RelBench to conduct the first comprehensive study of Deep Learning infrastructure. RDL learns better whilst reducing human work needed by more than an order of magnitude.
  arXiv  Detail & Related papers  (2024-07-29T14:46:13Z)
• A Novel Technique for Query Plan Representation Based on Graph Neural Nets [2.184775414778289]
  We study the effect of using different state-of-the-art tree models on the aggregated's cost estimation and plan selection performance. We propose a novel tree model BiGG employing GNN by Gated recurrent units (GRUs) and demonstrate experimentally that BiGG provides significant improvements to cost estimation tasks.
  arXiv  Detail & Related papers  (2024-05-08T04:59:59Z)
• AutoTransfer: AutoML with Knowledge Transfer -- An Application to Graph Neural Networks [75.11008617118908]
  AutoML techniques consider each task independently from scratch, leading to high computational cost. Here we propose AutoTransfer, an AutoML solution that improves search efficiency by transferring the prior architectural design knowledge to the novel task of interest.
  arXiv  Detail & Related papers  (2023-03-14T07:23:16Z)
• When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data [84.87772675171412]
  We study the circumstances under which explanations of individual data points can improve modeling performance. We make use of three existing datasets with explanations: e-SNLI, TACRED, SemEval.
  arXiv  Detail & Related papers  (2021-02-03T18:57:08Z)
• AutoRC: Improving BERT Based Relation Classification Models via Architecture Search [50.349407334562045]
  BERT based relation classification (RC) models have achieved significant improvements over the traditional deep learning models. No consensus can be reached on what is the optimal architecture. We design a comprehensive search space for BERT based RC models and employ neural architecture search (NAS) method to automatically discover the design choices.
  arXiv  Detail & Related papers  (2020-09-22T16:55:49Z)
• NASE: Learning Knowledge Graph Embedding for Link Prediction via Neural Architecture Search [9.634626241415916]
  Link prediction is the task of predicting missing connections between entities in the knowledge graph (KG) Previous work has tried to use Automated Machine Learning (AutoML) to search for the best model for a given dataset. We propose a novel Neural Architecture Search (NAS) framework for the link prediction task.
  arXiv  Detail & Related papers  (2020-08-18T03:34:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.