AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

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

Jialiang Wang, Hanmo Liu, Shimin Di, Zhili Wang, Jiachuan Wang, Lei Chen, Xiaofang Zhou

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add dynamic (Bayesian) task similarity update (ablation)M-DESIGN · Node classification, Kendall correlationavg Kendall correlation: 0.08 -> 0.34Improved
add dynamic task similarity update (ablation)M-DESIGN · Node classification, Actoraccuracy: 33.71 -> 34.89Improved
add sliding windows to control locality (ablation)M-DESIGN · Node classification, Kendall correlationavg Kendall correlation: 0.27 -> 0.34Improved
add sliding windows (ablation)M-DESIGN · Node classification, Cornellaccuracy: 75.68 -> 77.48Improved
add OOD adaptation with predictive task planners (ablation)M-DESIGN · Node classification, Computers/Cornell/Texasaccuracy: Cornell 75.68 -> 77.48; Texas 81.98 -> 83.79Improved
add OOD adaptation (ablation)M-DESIGN · Node classification, Photo/CS/PubMedaccuracy: Photo 94.75 vs 94.62; CS 95.33 vs 95.16No clear effect
enable OOD adaptation in gain transfer from closest benchmark (ablation)M-DESIGN · Cornell, gain correlation R2R-squared: 0.03 -> 0.11Improved
reduce MKB to 25% of benchmark sources (ablation)M-DESIGN · Node classification (avg of 11)accuracy: 82.11 -> 81.50Hurt
use different similarity initialization (weighted avg, majority vote, most similar) (ablation)M-DESIGN · Node classification (avg of 11)accuracy: 81.80 / 81.79 / 81.31No clear effect
use M-DESIGN refinement vs best baseline DesiGNNNode classification · Node classification, Texasaccuracy: 81.80 -> 83.79Improved
add refinement on top of one-shot retrieval in image domainM-DESIGN-Init · NATS-Benchaccuracy: Cifar10 0.8896 vs optimal 0.8916No clear effect
use M-DESIGN simplified variant for tabular tasksOur-S · HPOBench NavalMSE: 0.000453 -> 0.000034Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy