mlsanityData to 14 Oct 2026

Evolutionary Architecture Search For Deep Multitask Networks

arXiv 1803.03745 ↗First posted 10 Mar 2018cs.NE cs.AIcited by 23

Not on the map. Why?

Abstract (arXiv)

Multitask learning, i.e. learning several tasks at once with the same neural network, can improve performance in each of the tasks. Designing deep neural network architectures for multitask learning is a challenge: There are many ways to tie the tasks together, and the design choices matter. The size and complexity of this problem exceeds human design ability, making it a compelling domain for evolutionary optimization. Using the existing state of the art soft ordering architecture as the starting point, methods for evolving the modules of this architecture and for evolving the overall topology or routing between modules are evaluated in this paper. A synergetic approach of evolving custom routings with evolved, shared modules for each task is found to be very powerful, significantly improving the state of the art in the Omniglot multitask, multialphabet character recognition domain. This result demonstrates how evolution can be instrumental in advancing deep neural network and complex system design in general.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 4; 2023: 7; 2024: 1; 2025: 4.

23 papers.

Sort:

By area:

  1. 2022Universal Representations: A Unified Look at Multiple Task and Domain Learningcited by 23
  2. 2021AutoMTL: A Programming Framework for Automating Efficient Multi-Task Learningcited by 17
  3. 2022A Survey on Computationally Efficient Neural Architecture Searchcited by 12
  4. 2021Multi-objective Search of Robust Neural Architectures against Multiple Types of Adversarial Attackscited by 11
  5. 2021Learning Versatile Neural Architectures by Propagating Network Codescited by 9
  6. 2023Dynamic Neural Network for Multi-Task Learning Searching across Diverse Network Topologiescited by 9
  7. 2023Multi-task Learning with 3D-Aware Regularizationcited by 8
  8. 2024Acceleration for Deep Reinforcement Learning using Parallel and Distributed Computing: A Surveycited by 8
  9. 2022Multi-Task Learning for Visual Scene Understandingcited by 6
  10. 2023When Multi-Task Learning Meets Partial Supervision: A Computer Vision Reviewcited by 6
  11. 2022Toward Edge-Efficient Dense Predictions with Synergistic Multi-Task Neural Architecture Searchcited by 5
  12. 2021Software/Hardware Co-design for Multi-modal Multi-task Learning in Autonomous Systemscited by 4
11 more
  1. 2021A Novel Evolutionary Algorithm for Hierarchical Neural Architecture Searchcited by 4
  2. 2025Resolving Token-Space Gradient Conflicts: Token Space Manipulation for Transformer-Based Multi-Task Learningcited by 4
  3. 2025Revisit the Imbalance Optimization in Multi-task Learning: An Experimental Analysiscited by 3
  4. 2023Visual Attention Prompted Prediction and Learningcited by 2
  5. 20253D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understandingcited by 2
  6. 2021Deep Safe Multi-Task Learningcited by 1
  7. 2023Bayesian Quadrature for Neural Ensemble Searchcited by 1
  8. 2021Reliable and Fast Recurrent Neural Network Architecture Optimizationcited by 0
  9. 2023Asynchronous Evolution of Deep Neural Network Architecturescited by 0
  10. 2023GEVO-ML: Optimizing Machine Learning Code with Evolutionary Computationcited by 0
  11. 2025Vision Generalist Model: A Surveycited by 0