• Home
  • Search
  • Joint Autoencoders: A Flexible Meta-learning Framework
  • Cite Icon9
  • https://doi.org/10.1007/978-3-030-10925-7_30Copy DOI Icon

Joint Autoencoders: A Flexible Meta-learning Framework

  • Jan 1, 2019
  • Baruch Epstein +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

We develop a framework for learning multiple tasks simultaneously, based on sharing features that are common to all tasks, achieved through the use of a modular deep feedforward neural network consisting of shared branches, dealing with the common features of all tasks, and private branches, learning the specific unique aspects of each task. Once an appropriate weight sharing architecture has been established, learning takes place through standard algorithms for feedforward networks, e.g., stochastic gradient descent and its variations. The method deals with meta-learning (such as domain adaptation, transfer and multi-task learning) in a unified fashion, and can deal with data arising from different modalities. Numerical experiments demonstrate the effectiveness of learning in domain adaptation and transfer learning setups, and provide evidence for the flexible and task-oriented representations arising in the network. In particular, we handle transfer learning between multiple tasks in a straightforward manner, as opposed to many competing state-of-the-art methods, that are unable to handle more than two tasks. We also illustrate the network’s ability to distill task-specific and shared features.

Similar Papers
  • Research Article
  • Citations10

Iterative joint classifier and domain adaptation for visual transfer learning

  • Sep 29, 2021
  • International Journal of Machine Learning and Cybernetics
  • Shiva Noori Saray +1
  • Research Article
  • Citations21

Adversarial transfer learning for cross-domain visual recognition

  • Jul 15, 2020
  • Knowledge-Based Systems
  • Shanshan Wang +2
  • Research Article
  • Citations3

Domain-Adaptive Framework for ACL Injury Diagnosis Utilizing Contrastive Learning Techniques

  • Aug 14, 2024
  • Electronics
  • Weiqiang Liu +3
  • Research Article
  • Citations27

Domain adaptation and transfer learning for failure detection and failure-cause identification in optical networks across different lightpaths [Invited

  • Dec 01, 2021
  • Journal of Optical Communications and Networking
  • Francesco Musumeci +7
  • PDF
  • Research Article
  • Citations12

Multiclass Land Cover Mapping from Historical Orthophotos Using Domain Adaptation and Spatio-Temporal Transfer Learning

  • Nov 22, 2022
  • Remote Sensing
  • Wouter A J Van Den Broeck +2
  • Research Article
  • Citations56

A Review of Recent Work in Transfer Learning and Domain Adaptation for Natural Language Processing of Electronic Health Records

  • Aug 01, 2021
  • Yearbook of Medical Informatics
  • Egoitz Laparra +3
  • Conference Article
  • Citations6

Learning latent expression labels of child facial expression images through data-limited domain adaptation and transfer learning

  • Aug 21, 2020
  • Megan A Witherow +3
  • PDF
  • Research Article
  • Citations32

A Kernelized Unified Framework for Domain Adaptation

  • Jan 01, 2019
  • IEEE Access
  • Rakesh Kumar Sanodiya +3
  • Research Article
  • Citations48

Domain class consistency based transfer learning for image classification across domains

  • Aug 08, 2017
  • Information Sciences
  • Lei Zhang +2
  • Research Article
  • Citations2

Domain Adaptation and Transfer Learning in StochasticNets

  • Oct 31, 2015
  • Vision Letters
  • Mohammad Javad Shafiee +3
  • Book Chapter
  • Citations508

A Comprehensive Survey on Domain Adaptation for Visual Applications

  • Jan 01, 2017
  • Gabriela Csurka
  • Research Article
  • Citations5

Representation Learning with Multiple Lipschitz-Constrained Alignments on Partially-Labeled Cross-Domain Data

  • Apr 03, 2020
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Songlei Jian +3
  • Research Article
  • Citations32

Heterogeneous Domain Adaptation via Covariance Structured Feature Translators.

  • Mar 17, 2021
  • IEEE Transactions on Cybernetics
  • Chuan-Xian Ren +3
  • Research Article
  • Citations44

A framework for semi-supervised metric transfer learning on manifolds

  • Apr 01, 2019
  • Knowledge-Based Systems
  • Rakesh Kumar Sanodiya +1
  • Research Article

Abstract 1222: Efficient domain adaptation for cancer mutation prediction

  • Jun 15, 2022
  • Cancer Research
  • Ariel A Hippen +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.