arXivDaily arXiv每日学术速递 周一至周五更新
看起来今天可以划水了
arXiv 2602.05036cs.LG
收藏

多目标图自监督学习的反馈控制

Feedback Control for Multi-Objective Graph Self-Supervision

Carnegie Mellon University(卡内基梅隆大学);Amazon(亚马逊)

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

AI总结:

ControlG通过反馈控制框架解决多目标图自监督学习中的目标协调问题,通过时间分配优化提升性能并揭示学习驱动因素。

摘要:

图自监督学习(SSL)提供了一套日益丰富的预设目标:互信息、重建、对比学习;然而,由于目标干扰和训练不稳定,可靠地结合它们仍然具有挑战性。大多数多预设管道使用每次更新混合,迫使每次参数更新都成为妥协,导致三种失败模式:分歧(冲突引起的负迁移)、漂移(非平稳目标效用)和干旱(未受重视目标的隐藏饥饿)。我们主张协调本质上是一个时间分配问题:决定每个目标何时接收优化预算,而不是仅仅如何权衡它们。我们引入了ControlG,一个控制论框架,将多目标图SSL重新表述为通过估计每个目标的难度和成对对抗性,通过帕累托意识的对数超体积规划器规划目标预算,并通过比例-积分-微分(PID)控制器调度,将其作为反馈控制的时间分配。在9个数据集中,ControlG始终优于最先进的基线,同时生成可审计的调度,揭示了哪些目标推动了学习。

英文摘要:

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 like mutual information, reconstruction, and contrastive learning, yet combining them reliably remains challenging due to objective interference and training instability. Most multi-pretext pipelines use per-update mixing, forcing every parameter update to be a compromise and 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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑