mlsanityData to 7 Oct 2026

Feedback Control for Multi-Objective Graph Self-Supervision

arXiv 2602.05036 ↗First posted 4 Feb 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 34 references that are in the map. First posted on arXiv 4 Feb 2026.

Builds on

28 of 34 references.

References · 28

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  4. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  5. 2020Gradient Surgery for Multi-Task Learningcited by 1,210
  6. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  7. 2018Deep Graph Infomaxcited by 1,101
  8. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  9. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  10. 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 816
  11. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 809
  12. 2020Contrastive Multi-View Representation Learning on Graphscited by 651
16 more
  1. 2019Multi-scale Attributed Node Embeddingcited by 543
  2. 2020Deep Graph Contrastive Representation Learningcited by 535
  3. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  4. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 443
  5. 2021Conflict-Averse Gradient Descent for Multi-task Learningcited by 441
  6. 2021Graph Self-Supervised Learning: A Surveycited by 289
  7. 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 260
  8. 2020Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networkscited by 253
  9. 2022Multi-Task Learning as a Bargaining Gamecited by 209
  10. 2021Large-Scale Representation Learning on Graphs via Bootstrappingcited by 184
  11. 2021Automated Self-Supervised Learning for Graphscited by 50
  12. 2022Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalizationcited by 35
  13. 2024Towards Graph Contrastive Learning: A Survey and Beyondcited by 26
  14. 2024Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Taskscited by 7
  15. 2024Exploring Correlations of Self-Supervised Tasks for Graphscited by 7
  16. 2022AdaTask: Adaptive Multitask Online Learningcited by 1

Built on by

Not cited yet.