mlsanityData to 7 Oct 2026

Adaptive and Robust Multi-Task Learning

arXiv 2202.05250 ↗First posted 10 Feb 2022stat.ML cs.LG math.STcited by 33

Not on the map. Why?

Abstract (arXiv)

We study the multi-task learning problem that aims to simultaneously analyze multiple datasets collected from different sources and learn one model for each of them. We propose a family of adaptive methods that automatically utilize possible similarities among those tasks while carefully handling their differences. We derive sharp statistical guarantees for the methods and prove their robustness against outlier tasks. Numerical experiments on synthetic and real datasets demonstrate the efficacy of our new methods.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 26 of its 92 references that are in the map. First posted on arXiv 10 Feb 2022.

Builds on

26 of 92 references.

References · 26

  1. 2019Advances and Open Problems in Federated Learningcited by 3,021
  2. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  3. 2020Few-Shot Learning via Learning the Representation, Provablycited by 213
  4. 2015The Benefit of Multitask Representation Learningcited by 194
  5. 2020On the Theory of Transfer Learning: The Importance of Task Diversitycited by 186
  6. 2020Provable Meta-Learning of Linear Representationscited by 161
  7. 2020Understanding and Improving Information Transfer in Multi-Task Learningcited by 113
  8. 2020Transfer Learning for High-dimensional Linear Regression: Prediction, Estimation, and Minimax Optimalitycited by 89
  9. 2016The Landscape of Empirical Risk for Non-convex Lossescited by 86
  10. 2021Transfer Learning under High-dimensional Generalized Linear Modelscited by 69
  11. 2019Provable Guarantees for Gradient-Based Meta-Learningcited by 67
  12. 2018Marginal Singularity, and the Benefits of Labels in Covariate-Shiftcited by 65
14 more
  1. 2019Transfer Learning for Nonparametric Classification: Minimax Rate and Adaptive Classifiercited by 64
  2. 2019Learning-to-Learn Stochastic Gradient Descent with Biased Regularizationcited by 49
  3. 2015Robust Covariance and Scatter Matrix Estimation under Huber's Contamination Modelcited by 47
  4. 2021Near-Optimal Linear Regression under Distribution Shiftcited by 40
  5. 2022A new similarity measure for covariate shift with applications to nonparametric regressioncited by 33
  6. 2020Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networkscited by 30
  7. 2020A No-Free-Lunch Theorem for MultiTask Learningcited by 28
  8. 2018Predicting with Proxies: Transfer Learning in High Dimensioncited by 24
  9. 2021Minimax Estimation for Personalized Federated Learning: An Alternative between FedAvg and Local Training?cited by 15
  10. 2020On the Sample Complexity of Adversarial Multi-Source PAC Learningcited by 11
  11. 2015New Perspectives on k-Support and Cluster Normscited by 9
  12. 2021Minimax Rates and Adaptivity in Combining Experimental and Observational Datacited by 8
  13. 2013Data enriched linear regressioncited by 7
  14. 2019Distributed Linear Model Clustering over Networks: A Tree-Based Fused-Lasso ADMM Approachcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 7; 2024: 6; 2025: 10; 2026: 8.

33 papers.

Sort:

  1. 2023Learning from Similar Linear Representations: Adaptivity, Minimaxity, and Robustnesscited by 27
  2. 2024Smoothness Adaptive Hypothesis Transfer Learningcited by 8
  3. 2023Optimal Multitask Linear Regression and Contextual Bandits under Sparse Heterogeneitycited by 7
  4. 2023Multi-Task Learning with Summary Statisticscited by 7
  5. 2023FedGKD: Unleashing the Power of Collaboration in Federated Graph Neural Networkscited by 7
  6. 2023Towards the Theory of Unsupervised Federated Learning: Non-asymptotic Analysis of Federated EM Algorithmscited by 7
  7. 2025Representation Retrieval Learning for Heterogeneous Data Integrationcited by 5
  8. 2022Personalized Federated Learning with Multiple Known Clusterscited by 3
  9. 2022Adaptive Data Fusion for Multi-task Non-smooth Optimizationcited by 3
  10. 2023Multi-dimensional domain generalization with low-rank structurescited by 2
  11. 2024Few-shot Multi-Task Learning of Linear Invariant Features with Meta Subspace Pursuitcited by 2
  12. 2023Joint Graph Learning and Model Fitting in Laplacian Regularized Stratified Modelscited by 1
21 more
  1. 2024Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guaranteescited by 1
  2. 2024Multi-Task Dynamic Pricing in Credit Market with Contextual Informationcited by 1
  3. 2025Sharp Gaussian approximations for Decentralized Federated Learningcited by 1
  4. 2025Measuring Fine-Grained Relatedness in Multitask Learning via Data Attributioncited by 1
  5. 2025Multi-task Learning for Heterogeneous Multi-source Block-Wise Missing Datacited by 1
  6. 2025Late Fusion Multi-task Learning for Semiparametric Inference with Nuisance Parameterscited by 1
  7. 2026When More Data Doesn't Help: Limits of Adaptation in Multitask Learningcited by 1
  8. 2024Personalized Multi-tier Federated Learningcited by 0
  9. 2024Learning with Shared Representations: Statistical Rates and Efficient Algorithmscited by 0
  10. 2025GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifoldscited by 0
  11. 2025Joint estimation of smooth graph signals from partial linear measurementscited by 0
  12. 2025Multi-Task Learning with Covariate-Overlap Regularizationcited by 0
  13. 2025Adaptive Multi-task Learning for Multi-sector Portfolio Optimizationcited by 0
  14. 2025Robust and Adaptive Spectral Method for Representation Multi-Task Learning with Contaminationcited by 0
  15. 2026On the Power of Source Screening for Learning Shared Feature Extractorscited by 0
  16. 2026Adaptive Personalized Federated Learning via Multi-task Averaging of Kernel Mean Embeddingscited by 0
  17. 2026Near-optimal and Efficient First-Order Algorithm for Multi-Task Learning with Shared Linear Representationcited by 0
  18. 2026Adaptive Estimation and Inference in Semi-parametric Heterogeneous Clustered Multitask Learning via Neyman Orthogonalitycited by 0
  19. 2026From Dual Tracking to Clipping: Provably Faster Distributionally Robust Multi-Objective Optimizationcited by 0
  20. 2026Sample Complexity of Transfer Learning: An Optimal Transport Approachcited by 0
  21. 2026Transfer Learning in Nonparametric Regression with Deep ReLU Networkscited by 0