mlsanityData to 13 Oct 2026

DynaShare: Task and Instance Conditioned Parameter Sharing for Multi-Task Learning

arXiv 2305.17305 ↗First posted 26 May 2023cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Multi-task networks rely on effective parameter sharing to achieve robust generalization across tasks. In this paper, we present a novel parameter sharing method for multi-task learning that conditions parameter sharing on both the task and the intermediate feature representations at inference time. In contrast to traditional parameter sharing approaches, which fix or learn a deterministic sharing pattern during training and apply the same pattern to all examples during inference, we propose to dynamically decide which parts of the network to activate based on both the task and the input instance. Our approach learns a hierarchical gating policy consisting of a task-specific policy for coarse layer selection and gating units for individual input instances, which work together to determine the execution path at inference time. Experiments on the NYU v2, Cityscapes and MIMIC-III datasets demonstrate the potential of the proposed approach and its applicability across problem domains.

Key facts. Cited by 3 papers in the map (data through 13 Oct 2026). Builds on 34 of its 43 references that are in the map. First posted on arXiv 26 May 2023.

Builds on

34 of 43 references.

References · 34

  1. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,435
  2. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,726
  3. 2018DARTS: Differentiable Architecture Searchcited by 1,789
  4. 2018End-to-End Multi-Task Learning with Attentioncited by 533
  5. 2016Cross-stitch Networks for Multi-task Learningcited by 466
  6. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 439
  7. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 412
  8. 2021Dynamic Neural Networks: A Surveycited by 406
  9. 2019Multi-Task Deep Neural Networks for Natural Language Understandingcited by 350
  10. 2018Slimmable Neural Networkscited by 302
  11. 2017Multitask learning and benchmarking with clinical time series datacited by 287
  12. 201912-in-1: Multi-Task Vision and Language Representation Learningcited by 278
22 more
  1. 2019Universally Slimmable Networks and Improved Training Techniquescited by 219
  2. 2016UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memorycited by 200
  3. 2017BlockDrop: Dynamic Inference Paths in Residual Networkscited by 187
  4. 2019AdaShare: Learning What To Share For Efficient Deep Multi-Task Learningcited by 159
  5. 2020MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learningcited by 157
  6. 2019Attentive Single-Tasking of Multiple Taskscited by 148
  7. 2018Multi-task Deep Reinforcement Learning with PopArtcited by 139
  8. 2016Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruningcited by 133
  9. 2018NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reductioncited by 127
  10. 2021Rethinking Architecture Selection in Differentiable NAScited by 92
  11. 2019Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inferencecited by 91
  12. 2021Dynamic Slimmable Networkcited by 83
  13. 2018A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Taskscited by 54
  14. 2018You Look Twice: GaterNet for Dynamic Filter Selection in CNNscited by 46
  15. 2016Learning to Push by Grasping: Using multiple tasks for effective learningcited by 36
  16. 2019Dual Dynamic Inference: Enabling More Efficient, Adaptive and Controllable Deep Inferencecited by 31
  17. 2019OmniNet: A unified architecture for multi-modal multi-task learningcited by 25
  18. 2019Deep Elastic Networks with Model Selection for Multi-Task Learningcited by 20
  19. 2020Resolution Switchable Networks for Runtime Efficient Image Recognitioncited by 19
  20. 2021Heterogeneous Multi-task Learning with Expert Diversitycited by 18
  21. 2022DiSparse: Disentangled Sparsification for Multitask Model Compressioncited by 14
  22. 2020Hierarchical Multitask Learning Approach for BERTcited by 3

Built on by

Cited by year (2026 to 13 Oct)

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

3 papers.

  1. 2025Multi-Task Semantic Communication With Graph Attention-Based Feature Correlation Extractioncited by 3
  2. 2026Evolving Without Ending: Unifying Multimodal Incremental Learning for Continual Panoptic Perceptioncited by 0
  3. 2026BTI-Net: Bidirectional Decoder-Level Task Interaction via Uncertainty-Aware Gating for Multi-Task Medical Image Analysiscited by 0