mlsanityData to 7 Oct 2026

Label Budget Allocation in Multi-Task Learning

arXiv 2308.12949 ↗First posted 24 Aug 2023cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The cost of labeling data often limits the performance of machine learning systems. In multi-task learning, related tasks provide information to each other and improve overall performance, but the label cost can vary among tasks. How should the label budget (i.e. the amount of money spent on labeling) be allocated among different tasks to achieve optimal multi-task performance? We are the first to propose and formally define the label budget allocation problem in multi-task learning and to empirically show that different budget allocation strategies make a big difference to its performance. We propose a Task-Adaptive Budget Allocation algorithm to robustly generate the optimal budget allocation adaptive to different multi-task learning settings. Specifically, we estimate and then maximize the extent of new information obtained from the allocated budget as a proxy for multi-task learning performance. Experiments on PASCAL VOC and Taskonomy demonstrate the efficacy of our approach over other widely used heuristic labeling strategies.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 48 of its 74 references that are in the map. First posted on arXiv 24 Aug 2023.

Builds on

48 of 74 references.

References · 48

  1. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  2. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  3. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  4. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  5. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  6. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  7. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  8. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  9. 2020Gradient Surgery for Multi-Task Learningcited by 1,210
  10. 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 816
  11. 2017Deep Bayesian Active Learning with Image Datacited by 812
  12. 2018Taskonomy: Disentangling Task Transfer Learningcited by 631
36 more
  1. 2018End-to-End Multi-Task Learning with Attentioncited by 533
  2. 2016Cross-stitch Networks for Multi-task Learningcited by 466
  3. 2019Which Tasks Should Be Learned Together in Multi-task Learning?cited by 367
  4. 2015Learning Deconvolution Network for Semantic Segmentationcited by 365
  5. 2018Slimmable Neural Networkscited by 301
  6. 2021Efficiently Identifying Task Groupings for Multi-Task Learningcited by 218
  7. 2022Multi-Task Learning as a Bargaining Gamecited by 209
  8. 2016UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memorycited by 200
  9. 2019Task2Vec: Task Embedding for Meta-Learningcited by 197
  10. 2019AdaShare: Learning What To Share For Efficient Deep Multi-Task Learningcited by 159
  11. 2020MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learningcited by 157
  12. 2019Attentive Single-Tasking of Multiple Taskscited by 148
  13. 2018NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reductioncited by 127
  14. 2016HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognitioncited by 103
  15. 2018Adapting Auxiliary Losses Using Gradient Similaritycited by 98
  16. 2018PCL: Proposal Cluster Learning for Weakly Supervised Object Detectioncited by 97
  17. 2022InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understandingcited by 89
  18. 2021RotoGrad: Gradient Homogenization in Multitask Learningcited by 82
  19. 2019C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detectioncited by 71
  20. 2019AdaBits: Neural Network Quantization with Adaptive Bit-Widthscited by 63
  21. 2015Cross-domain Image Retrieval with a Dual Attribute-aware Ranking Networkcited by 53
  22. 2018Deep Bilevel Learningcited by 48
  23. 2019Min-Entropy Latent Model for Weakly Supervised Object Detectioncited by 45
  24. 2019Stochastic Filter Groups for Multi-Task CNNs: Learning Specialist and Generalist Convolution Kernelscited by 42
  25. 2018Learning to Teach with Dynamic Loss Functionscited by 40
  26. 2019LoGAN: Latent Graph Co-Attention Network for Weakly-Supervised Video Moment Retrievalcited by 40
  27. 2019Regularizing Deep Multi-Task Networks using Orthogonal Gradientscited by 36
  28. 2021Dynamic Network Quantization for Efficient Video Inferencecited by 36
  29. 2019Addressing the Loss-Metric Mismatch with Adaptive Loss Alignmentcited by 33
  30. 2017BlitzNet: A Real-Time Deep Network for Scene Understandingcited by 29
  31. 2016Integrated perception with recurrent multi-task neural networkscited by 24
  32. 2019Deep Elastic Networks with Model Selection for Multi-Task Learningcited by 20
  33. 2021AutoMTL: A Programming Framework for Automating Efficient Multi-Task Learningcited by 17
  34. 2016Deep Cross Residual Learning for Multitask Visual Recognitioncited by 16
  35. 2018AutoLoss: Learning Discrete Schedules for Alternate Optimizationcited by 12
  36. 2021How to distribute data across tasks for meta-learning?cited by 7

Built on by

Not cited yet.