mlsanityData to 7 Oct 2026

Identifying beneficial task relations for multi-task learning in deep neural networks

arXiv 1702.08303 ↗First posted 27 Feb 2017cs.CLcited by 59

Not on the map. Why?

Abstract (arXiv)

Multi-task learning (MTL) in deep neural networks for NLP has recently received increasing interest due to some compelling benefits, including its potential to efficiently regularize models and to reduce the need for labeled data. While it has brought significant improvements in a number of NLP tasks, mixed results have been reported, and little is known about the conditions under which MTL leads to gains in NLP. This paper sheds light on the specific task relations that can lead to gains from MTL models over single-task setups.

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Feb 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 19; 2023: 10; 2024: 9; 2025: 3; 2026: 4.

59 papers.

Sort:

By area:

  1. 2021SPoT: Better Frozen Model Adaptation through Soft Prompt Transfercited by 235
  2. 2021ExT5: Towards Extreme Multi-Task Scaling for Transfer Learningcited by 161
  3. 2021What to Pre-Train on? Efficient Intermediate Task Selectioncited by 62
  4. 2023PIGEON: Predicting Image Geolocationscited by 55
  5. 2024A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learningcited by 52
  6. 2023π-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolationcited by 40
  7. 2022Towards Versatile Embodied Navigationcited by 26
  8. 2021Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learningcited by 22
  9. 2025Pareto Set Learning for Multi-Objective Reinforcement Learningcited by 18
  10. 2022Task Compass: Scaling Multi-task Pre-training with Task Prefixcited by 14
  11. 2021To Share or not to Share: Predicting Sets of Sources for Model Transfer Learningcited by 11
  12. 2022FETA: A Benchmark for Few-Sample Task Transfer in Open-Domain Dialoguecited by 11
38 more
  1. 2021Language Modelling as a Multi-Task Problemcited by 10
  2. 2022Robust Natural Language Processing: Recent Advances, Challenges, and Future Directionscited by 9
  3. 2023Toward Building General Foundation Models for Language, Vision, and Vision-Language Understanding Taskscited by 9
  4. 2023Interpreting and Exploiting Functional Specialization in Multi-Head Attention under Multi-task Learningcited by 9
  5. 2022Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representationcited by 8
  6. 2022Let the Model Decide its Curriculum for Multitask Learningcited by 8
  7. 2022Multi-Task Meta Learning: learn how to adapt to unseen taskscited by 8
  8. 2023Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learningcited by 8
  9. 2021GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer Networkscited by 7
  10. 2022Efficiently Tuned Parameters are Task Embeddingscited by 7
  11. 2021Latent-Optimized Adversarial Neural Transfer for Sarcasm Detectioncited by 6
  12. 2023When Multi-Task Learning Meets Partial Supervision: A Computer Vision Reviewcited by 6
  13. 2024Towards Better Multi-task Learning: A Framework for Optimizing Dataset Combinations in Large Language Modelscited by 6
  14. 2021Multi-task Learning by Leveraging the Semantic Informationcited by 5
  15. 2023Constructing Time-Series Momentum Portfolios with Deep Multi-Task Learningcited by 5
  16. 2021Learning More for Free - A Multi Task Learning Approach for Improved Pathology Classification in Capsule Endoscopycited by 4
  17. 2021A Flexible Multi-Task Model for BERT Servingcited by 4
  18. 2022Gap Minimization for Knowledge Sharing and Transfercited by 4
  19. 2023Task Grouping for Automated Multi-Task Machine Learning via Task Affinity Predictioncited by 4
  20. 2024MAGPIE: Multi-Task Media-Bias Analysis Generalization for Pre-Trained Identification of Expressionscited by 4
  21. 2024Glider: Global and Local Instruction-Driven Expert Routercited by 4
  22. 2024Identifying Task Groupings for Multi-Task Learning Using Pointwise V-Usable Informationcited by 4
  23. 2021One Semantic Parser to Parse Them All: Sequence to Sequence Multi-Task Learning on Semantic Parsing Datasetscited by 3
  24. 2022Interpretable Low-Resource Legal Decision Makingcited by 3
  25. 2022MT-GBM: A Multi-Task Gradient Boosting Machine with Shared Decision Treescited by 3
  26. 2026Will it Merge? On The Causes of Model Mergeabilitycited by 3
  27. 2022Learning Multi-Tasks with Inconsistent Labels by using Auxiliary Big Taskcited by 2
  28. 2022Efficient Extraction of Pathologies from C-Spine Radiology Reports using Multi-Task Learningcited by 2
  29. 2023Towards Robust and Efficient Continual Language Learningcited by 2
  30. 2024Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyondcited by 2
  31. 2025MINT: Multimodal Instruction Tuning with Multimodal Interaction Groupingcited by 2
  32. 2021Predictive Representation Learning for Language Modelingcited by 1
  33. 2021Contextualizing Variation in Text Style Transfer Datasetscited by 1
  34. 2022On partitioning of an SHM problem and parallels with transfer learningcited by 1
  35. 2022Explaining the Effectiveness of Multi-Task Learning for Efficient Knowledge Extraction from Spine MRI Reportscited by 1
  36. 2022Multi-Task Learning for Depression Detection in Dialogscited by 1
  37. 2023"It's a Match!" -- A Benchmark of Task Affinity Scores for Joint Learningcited by 1
  38. 2025Regularization of ML models for Earth systems by using longer model timestepscited by 1

50 most cited of 59 All 59 (JSON)