Autoencoder Based Sample Selection for Self-Taught Learning

by   Siwei Feng, et al.

Self-taught learning is a technique that uses a large number of unlabeled data as source samples to improve the task performance on target samples. Compared with other transfer learning techniques, self-taught learning can be applied to a broader set of scenarios due to the loose restrictions on source data. However, knowledge transferred from source samples that are not sufficiently related to the target domain may negatively influence the target learner, which is referred to as negative transfer. In this paper, we propose a metric for the relevance between a source sample and target samples. To be more specific, both source and target samples are reconstructed through a single-layer autoencoder with a linear relationship between source samples and target samples simultaneously enforced. An l_2,1-norm sparsity constraint is imposed on the transformation matrix to identify source samples relevant to the target domain. Source domain samples that are deemed relevant are assigned pseudo-labels reflecting their relevance to target domain samples, and are combined with target samples in order to provide an expanded training set for classifier training. Local data structures are also preserved during source sample selection through spectral graph analysis. Promising results in extensive experiments show the advantages of the proposed approach.


page 9

page 11

page 12


A new semi-supervised inductive transfer learning framework: Co-Transfer

In many practical data mining scenarios, such as network intrusion detec...

Self-training for Few-shot Transfer Across Extreme Task Differences

All few-shot learning techniques must be pre-trained on a large, labeled...

Source data selection for out-of-domain generalization

Models that perform out-of-domain generalization borrow knowledge from h...

Fine-grained Knowledge Fusion for Sequence Labeling Domain Adaptation

In sequence labeling, previous domain adaptation methods focus on the ad...

Influential Sample Selection: A Graph Signal Processing Approach

With the growing complexity of machine learning techniques, understandin...

PhyAug: Physics-Directed Data Augmentation for Deep Sensing Model Transfer in Cyber-Physical Systems

Run-time domain shifts from training-phase domains are common in sensing...

Model-based Transfer Learning for Automatic Optical Inspection based on domain discrepancy

Transfer learning is a promising method for AOI applications since it ca...

Please sign up or login with your details

Forgot password? Click here to reset