AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

Efficient Task Grouping Through Sample-Wise Optimisation Landscape Analysis

Anshul Thakur, Yichen Huang, Soheila Molaei, Yujiang Wang, David Andrew Clifton

TPAMI 2025 · Learning theory and algorithms › Clustering · approach: Clustering approximation algorithms · 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
use SCA informed task grouping instead of random groupingReptile joint training · Image classification (2 splits)balanced accuracy average: 85.05 -> 86.17Improved
use SCA informed task grouping instead of random groupingReptile joint training · MIMIC-III Waveform ECG (2 splits)AUROC average: 0.62 -> 0.65Improved
use SCA instead of TAG for task groupingReptile joint training · MIMIC-III Waveform ECG (2 splits)AUROC average: 0.643 -> 0.65Improved
use SCA instead of TAG for task groupingReptile joint training · MIMIC-III Waveform ECG (3 splits)AUROC average: 0.657 -> 0.657No clear effect
use SCA instead of TAG for task groupingResNet-15 MTL · Celeb-Amean absolute error: 49.66 -> 49.6No clear effect
use SCA instead of TAG for task grouping (training time)ResNet-15 MTL · Celeb-A (2 splits)training time (GPU hours): 5.4 -> 3.61Improved
use SCA instead of HOA for task grouping (training time)ResNet-15 MTL · Celeb-A (2 splits)training time (GPU hours): 57.6 -> 3.61Improved
use SCA two-group task grouping instead of standard MTLCeleb-A MTL · Celeb-Arelative improvement: 45%Improved
use SCA two-group task grouping instead of Nash MTLCeleb-A MTL · Celeb-Arelative improvement: 23.1%Improved
use informed grouping (SCA, TAG, HOA) instead of random groupingpatient care Reptile · MIMIC-III patient careAUROC average: 0.824 -> 0.845Improved
increase number of task groupingsall grouping methods · QM9 (2 to 7 splits)mean absolute errorNo clear effect
increase samples for SCA from 100 to 250, 500, 1000, 2000, 4000 (ablation)SCA scores · image and patient care tasksrelative task similarityNo clear effect

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