AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Feedback Control for Multi-Objective Graph Self-Supervision

Karish Grover, Theodore Vasiloudis, Han Xie, Sixing Lu, Xiang song, Christos Faloutsos

ICML 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Data-efficient and robust self-supervision · 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 log-hypervolume planner (vs uniform allocation) (ablation)ControlG · Cora node classificationaccuracy: 78.52 -> 81.92Improved
add the log-hypervolume planner (vs uniform allocation) (ablation)ControlG · PubMed node classificationaccuracy: 80.86 -> 84.24Improved
add both state signals (spectral demand and interference) (ablation)ControlG · Arxiv node classificationaccuracy: 69.82 -> 72.86Improved
add spectral demand signal (ablation)ControlG · 9 node classification datasetsaccuracy: Cora 80.14 -> 81.92Improved
add interference signal (ablation)ControlG · Chameleon, Squirrelaccuracy: Chameleon 68.26 -> 69.54; Squirrel 52.12 -> 53.18Improved
add PID deficit-tracking controller (vs i.i.d. sampling from f) (ablation)ControlG · node classificationaccuracy: Cora 80.28 -> 81.92Improved
use single-task temporal blocks with random scheduling instead of per-step gradient mixingRandom scheduler vs ParetoGNN/PCGrad/CAGrad/AutoSSL · node clusteringaverage rank: avg rank 5.0 vs 7.3-8.4Improved
add feedback-controlled scheduling on top of random temporal schedulingRandom scheduler · node classificationaverage rank: avg rank 9.4 -> 1.4Improved
use ControlG instead of per-step mixing methodsAUTOSSL, ParetoGNN · training timeruntime: 5-15x fasterImproved
replace per-step Pareto mixing with ControlGParetoGNN · PubMed node classificationaccuracy: 67.72 -> 84.24Improved

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