HG-CAD: Hierarchical Graph Learning for Material Prediction and Recommendation in Computer-Aided Design

arXiv 2023 27.9 method

TLDR

HG-CAD uses hierarchical graph learning to predict and recommend materials for CAD assembly bodies, outperforming baselines on the Fusion 360 dataset.

Reasoning

The paper introduces a novel hierarchical graph representation for joint learning of body geometry and assembly topology, achieving strong results on material prediction. However, its scope is limited to material recommendation rather than broader CAD generation or reconstruction tasks, and evaluation is confined to a single dataset.

Read-first score

Read-first score 27.9, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 21.

Recency 8%

65.1

Uses a gentle age decay so recent papers surface without erasing older foundations. 2023

Methodology quality 25%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=baseline,dataset,evaluation,metric

Topical relevance 42%

13.1

Uses existing LLM keyword relevance scores normalized to 0-100. AI for CAD,computer-aided design,neural CAD,generative CAD,parametric CAD,B-Rep,boundary representation,constructive solid geometry,CSG,sketch extrusion,CAD generation,CAD reconstruction,text-to-CAD,image-to-CAD,point cloud to CAD,CAD program

Reproducibility 25%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=False; code=False; dataset=False; markers=dataset

Field roles

Candidate

Rank sensitivity

Stability: volatile; rank range: 61.

Keyword Scores

computer-aided design

AI for CAD

neural CAD

generative CAD

parametric CAD

B-Rep

boundary representation

constructive solid geometry

CSG

sketch extrusion

CAD generation

CAD reconstruction

text-to-CAD

image-to-CAD

point cloud to CAD

CAD program