mlsanityData to 7 Oct 2026

Multi-task Learning by Leveraging the Semantic Information

arXiv 2103.02546 ↗First posted 3 Mar 2021cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

One crucial objective of multi-task learning is to align distributions across tasks so that the information between them can be transferred and shared. However, existing approaches only focused on matching the marginal feature distribution while ignoring the semantic information, which may hinder the learning performance. To address this issue, we propose to leverage the label information in multi-task learning by exploring the semantic conditional relations among tasks. We first theoretically analyze the generalization bound of multi-task learning based on the notion of Jensen-Shannon divergence, which provides new insights into the value of label information in multi-task learning. Our analysis also leads to a concrete algorithm that jointly matches the semantic distribution and controls label distribution divergence. To confirm the effectiveness of the proposed method, we first compare the algorithm with several baselines on some benchmarks and then test the algorithms under label space shift conditions. Empirical results demonstrate that the proposed method could outperform most baselines and achieve state-of-the-art performance, particularly showing the benefits under the label shift conditions.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 28 of its 57 references that are in the map. First posted on arXiv 3 Mar 2021.

Builds on

28 of 57 references.

References · 28

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  4. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  5. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  6. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 809
  7. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 405
  8. 2018Detecting and Correcting for Label Shift with Black Box Predictorscited by 364
  9. 2018Recent Advances in Open Set Recognition: A Surveycited by 309
  10. 2017Distral: Robust Multitask Reinforcement Learningcited by 231
  11. 2015The Benefit of Multitask Representation Learningcited by 194
  12. 2019Domain Generalization Using a Mixture of Multiple Latent Domainscited by 170
16 more
  1. 2018Partial Adversarial Domain Adaptationcited by 127
  2. 2019Domain-Symmetric Networks for Adversarial Domain Adaptationcited by 120
  3. 2019Regularized Learning for Domain Adaptation under Label Shiftscited by 118
  4. 2017Few-Shot Adversarial Domain Adaptationcited by 111
  5. 2016Theoretical Analysis of Domain Adaptation with Optimal Transportcited by 105
  6. 2017Adversarial Multi-task Learning for Text Classificationcited by 91
  7. 2017Identifying beneficial task relations for multi-task learning in deep neural networkscited by 59
  8. 2017Label Efficient Learning of Transferable Representations across Domains and Taskscited by 49
  9. 2018A Modulation Module for Multi-task Learning with Applications in Image Retrievalcited by 49
  10. 2019A Principled Approach for Learning Task Similarity in Multitask Learningcited by 32
  11. 2020Domain Generalization via Optimal Transport with Metric Similarity Learningcited by 27
  12. 2018Multi-task Learning of Hierarchical Vision-Language Representationcited by 26
  13. 2017Deep Learning for Multi-Task Medical Image Segmentation in Multiple Modalitiescited by 25
  14. 2016Multi-Task Learning with Labeled and Unlabeled Taskscited by 17
  15. 2020Beyond H-Divergence: Domain Adaptation Theory With Jensen-Shannon Divergencecited by 15
  16. 2014Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Networkcited by 11

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 2.

5 papers.

  1. 2021Learning to Transfer for Traffic Forecasting via Multi-task Learningcited by 7
  2. 2023Personalised Federated Learning On Heterogeneous Feature Spacescited by 5
  3. 2022Gap Minimization for Knowledge Sharing and Transfercited by 4
  4. 2022Compressed Hierarchical Representations for Multi-Task Learning and Task Clusteringcited by 2
  5. 2023Learning Easily Updated General Purpose Text Representations with Adaptable Task-Specific Prefixescited by 0