AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Selecting Samples on Graphs: A Unified Dataset Pruning Framework for Lossless Training Acceleration

Dongyue Wu, Zilin Guo, Xiaoyu Li, Jiajia Liu, Jingdong Chen, Nong Sang, Changxin Gao

ICML 2026 · Graph learning › Graph algorithms and clustering · approach: Graph comparison and random features · 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 the extrinsic (diversity) term to the intrinsic term (ablation)UGIES · ImageNet-1k ResNet-50accuracyImproved
use greedy solver instead of top-k selection (ablation)UGIES · ImageNet-1k ResNet-50accuracyImproved
promote diversity (monotone-increasing extrinsic term) instead of similarity (ablation)UGIES · ImageNet-1k ResNet-50accuracyImproved
use cosine distance instead of Chebyshev distance (ablation)UGIES · ImageNet-1k ResNet-50 (30% pruned)accuracy: 76.6 -> 77.0Improved
use cosine distance instead of L2 distance (ablation)UGIES · ImageNet-1k ResNet-50 (30% pruned)accuracy: 76.8 -> 77.0Improved
change the mapping function g among g1 to g4 (ablation)UGIES · ImageNet-1k ResNet-50 (30% pruned)accuracy: 76.9 -> 77.0No clear effect
extract features with current training model instead of pretrained ResNet-34 (ablation)UGIES · ImageNet-1k ResNet-50 (30% pruned)top-1 accuracy: 76.82 -> 77.02Improved
use pretrained ResNet-50 features instead of ResNet-34 (ablation)UGIES · ImageNet-1k ResNet-50 (30% pruned)top-1 accuracy: 76.82 -> 76.96No clear effect
swap in DivBS gradient similarity as extrinsic term (ablation)UGIES · ImageNet-1k ResNet-50 (70% pruned)accuracy: 75.3 -> 75.5Improved
use UGIES instead of InfoBatchUGIES · ImageNet-1k ResNet-50 (70% pruned)accuracy: 74.9 -> 75.3Improved
use UGIES instead of PFB for training accelerationUGIES · ImageNet-1k ResNet-50 (50% pruned)total time (h): 8.7 -> 7.9Improved
use UGIES instead of InfoBatchUGIES · COCO2017 SSD ResNet-50AP: 25.0 -> 25.5Improved

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