mlsanityData to 14 Oct 2026

Transfer Learning with Neural AutoML

arXiv 1803.02780 ↗First posted 7 Mar 2018cs.LG stat.MLcited by 15

Not on the map. Why?

Abstract (arXiv)

We reduce the computational cost of Neural AutoML with transfer learning. AutoML relieves human effort by automating the design of ML algorithms. Neural AutoML has become popular for the design of deep learning architectures, however, this method has a high computation cost. To address this we propose Transfer Neural AutoML that uses knowledge from prior tasks to speed up network design. We extend RL-based architecture search methods to support parallel training on multiple tasks and then transfer the search strategy to new tasks. On language and image classification tasks, Transfer Neural AutoML reduces convergence time over single-task training by over an order of magnitude on many tasks.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 4; 2023: 3; 2024: 1.

15 papers.

Sort:

  1. 2021Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyondcited by 153
  2. 2023Neural Architecture Search: Insights from 1000 Paperscited by 139
  3. 2021TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Searchcited by 58
  4. 2021A Fully Single Loop Algorithm for Bilevel Optimization without Hessian Inversecited by 53
  5. 2023An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine Learningcited by 41
  6. 2022Local Stochastic Bilevel Optimization with Momentum-Based Variance Reductioncited by 20
  7. 2022Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Searchcited by 9
  8. 2023AutoTransfer: AutoML with Knowledge Transfer -- An Application to Graph Neural Networkscited by 8
  9. 2021Dynamically Grown Generative Adversarial Networkscited by 6
  10. 2022Privacy-preserving Online AutoML for Domain-Specific Face Detectioncited by 4
  11. 2021AutoSmart: An Efficient and Automatic Machine Learning framework for Temporal Relational Datacited by 3
  12. 2021Width Transfer: On the (In)variance of Width Optimizationcited by 1
3 more
  1. 2022Meta-Learning of NAS for Few-shot Learning in Medical Image Applicationscited by 1
  2. 2024Learning Morphisms with Gauss-Newton Approximation for Growing Networkscited by 1
  3. 2021Evaluation of Representation Models for Text Classification with AutoML Toolscited by 0