mlsanityData to 7 Oct 2026

GO4Align: Group Optimization for Multi-Task Alignment

arXiv 2404.06486 ↗First posted 9 Apr 2024cs.LG cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

This paper proposes textitGO4Align, a multi-task optimization approach that tackles task imbalance by explicitly aligning the optimization across tasks. To achieve this, we design an adaptive group risk minimization strategy, comprising two techniques in implementation: (i) dynamical group assignment, which clusters similar tasks based on task interactions; (ii) risk-guided group indicators, which exploit consistent task correlations with risk information from previous iterations. Comprehensive experimental results on diverse benchmarks demonstrate our method's performance superiority with even lower computational costs.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 38 of its 57 references that are in the map. First posted on arXiv 9 Apr 2024.

Builds on

38 of 57 references.

References · 38

  1. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  2. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  3. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  4. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  5. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  6. 2020Gradient Surgery for Multi-Task Learningcited by 1,210
  7. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 866
  8. 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 816
  9. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 809
  10. 2018End-to-End Multi-Task Learning with Attentioncited by 533
  11. 2016Cross-stitch Networks for Multi-task Learningcited by 466
  12. 2021Conflict-Averse Gradient Descent for Multi-task Learningcited by 441
26 more
  1. 2019Which Tasks Should Be Learned Together in Multi-task Learning?cited by 367
  2. 2021Efficiently Identifying Task Groupings for Multi-Task Learningcited by 218
  3. 2022Multi-Task Learning as a Bargaining Gamecited by 209
  4. 2016UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memorycited by 200
  5. 2020Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropoutcited by 199
  6. 2021Multi-Task Reinforcement Learning with Context-based Representationscited by 169
  7. 2019AdaShare: Learning What To Share For Efficient Deep Multi-Task Learningcited by 159
  8. 2019Attentive Single-Tasking of Multiple Taskscited by 148
  9. 2018NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reductioncited by 127
  10. 2020Learning to Branch for Multi-Task Learningcited by 114
  11. 2021Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learningcited by 100
  12. 2016Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classificationcited by 93
  13. 2017Adversarial Multi-task Learning for Text Classificationcited by 91
  14. 2019Branched Multi-Task Networks: Deciding What Layers To Sharecited by 76
  15. 2023FAMO: Fast Adaptive Multitask Optimizationcited by 74
  16. 2022Auto-Lambda: Disentangling Dynamic Task Relationshipscited by 73
  17. 2023Independent Component Alignment for Multi-Task Learningcited by 69
  18. 2022In Defense of the Unitary Scalarization for Deep Multi-Task Learningcited by 65
  19. 2021Multi-Task Learning in Natural Language Processing: An Overviewcited by 61
  20. 2022Do Current Multi-Task Optimization Methods in Deep Learning Even Help?cited by 60
  21. 2020Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Datacited by 50
  22. 2021Variational Multi-Task Learning with Gumbel-Softmax Priorscited by 15
  23. 2023Episodic Multi-Task Learning with Heterogeneous Neural Processescited by 8
  24. 2017Self-Paced Multitask Learning with Shared Knowledgecited by 2
  25. 2023Task Weighting in Meta-learning with Trajectory Optimisationcited by 2
  26. 2017Clustering is semidefinitely not that hard: Nonnegative SDP for manifold disentanglingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 8; 2026: 2.

11 papers.

  1. 2025FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Expertscited by 34
  2. 2024Jacobian Descent for Multi-Objective Optimizationcited by 18
  3. 2025LDC-MTL: Balancing Multi-Task Learning through Scalable Loss Discrepancy Controlcited by 7
  4. 2025Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learningcited by 2
  5. 2025NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspectivecited by 2
  6. 2026Delve into the Applicability of Advanced Optimizers for Multi-Task Learningcited by 2
  7. 2025Graph Coloring for Multi-Task Learningcited by 1
  8. 2025Uniform Loss vs. Specialized Optimization: A Comparative Analysis in Multi-Task Learningcited by 0
  9. 2025Monotonic Transformation Invariant Multi-task Learningcited by 0
  10. 2025VAO: Validation-Aligned Optimization for Cross-Task Generative Auto-Biddingcited by 0
  11. 2026Efficient RGB-D Scene Understanding via Multi-task Adaptive Learning and Cross-dimensional Feature Guidancecited by 0