Marginalized Denoising Autoencoders for Domain Adaptation
This work addresses efficiency issues in domain adaptation for machine learning practitioners, offering a faster alternative to SDAs with comparable performance, though it is incremental as it builds directly on existing SDA methods.
The paper tackled the high computational cost and lack of scalability of stacked denoising autoencoders (SDAs) for domain adaptation by proposing marginalized SDA (mSDA), which marginalizes noise to compute parameters in closed-form, speeding up SDAs by two orders of magnitude while maintaining similar accuracy on benchmark tasks.
Stacked denoising autoencoders (SDAs) have been successfully used to learn new representations for domain adaptation. Recently, they have attained record accuracy on standard benchmark tasks of sentiment analysis across different text domains. SDAs learn robust data representations by reconstruction, recovering original features from data that are artificially corrupted with noise. In this paper, we propose marginalized SDA (mSDA) that addresses two crucial limitations of SDAs: high computational cost and lack of scalability to high-dimensional features. In contrast to SDAs, our approach of mSDA marginalizes noise and thus does not require stochastic gradient descent or other optimization algorithms to learn parameters ? in fact, they are computed in closed-form. Consequently, mSDA, which can be implemented in only 20 lines of MATLAB^{TM}, significantly speeds up SDAs by two orders of magnitude. Furthermore, the representations learnt by mSDA are as effective as the traditional SDAs, attaining almost identical accuracies in benchmark tasks.