Feedback Control for Multi-Objective Graph Self-Supervision
This addresses a key challenge in multi-task graph self-supervised learning for researchers and practitioners, offering a novel coordination method to improve reliability and performance.
The paper tackled the problem of coordinating multiple self-supervised objectives in graph learning, which often leads to interference and instability, by introducing ControlG, a control-theoretic framework that schedules optimization budgets temporally, resulting in consistent outperformance over state-of-the-art baselines across 9 datasets.
Can multi-task self-supervised learning on graphs be coordinated without the usual tug-of-war between objectives? Graph self-supervised learning (SSL) offers a growing toolbox of pretext objectives: mutual information, reconstruction, contrastive learning; yet combining them reliably remains a challenge due to objective interference and training instability. Most multi-pretext pipelines use per-update mixing, forcing every parameter update to be a compromise, leading to three failure modes: Disagreement (conflict-induced negative transfer), Drift (nonstationary objective utility), and Drought (hidden starvation of underserved objectives). We argue that coordination is fundamentally a temporal allocation problem: deciding when each objective receives optimization budget, not merely how to weigh them. We introduce ControlG, a control-theoretic framework that recasts multi-objective graph SSL as feedback-controlled temporal allocation by estimating per-objective difficulty and pairwise antagonism, planning target budgets via a Pareto-aware log-hypervolume planner, and scheduling with a Proportional-Integral-Derivative (PID) controller. Across 9 datasets, ControlG consistently outperforms state-of-the-art baselines, while producing an auditable schedule that reveals which objectives drove learning.