WANN

Weighting Adversarial Neural Network (paper link: https://arxiv.org/pdf/2006.08251.pdf)

WANN is a supervised domain adaptation method suited for regression tasks. The algorithm is an instance-based method which learns a reweighting of source instance losses in order to correct the difference between source and target distributions.

Requirements

Code for the numerical experiments requires the following packages:

• tensorflow (>= 2.0)
• scikit-learn
• numpy
• pandas
• matplotlib
• nltk
• adapt

Experiments

WANN algorithm is compared to several domain adaptation base-lines:

• KMM Huang et al.
• KLIEP Sugiyama et al.
• TrAdaBoostR2 Pardoe et al.
• DANN Ganin et al.
• ADDA Tzeng et al.
• MDD Zhang et al.

The implementation of WANN can be found in the wann\methods folder. The implementation of the base-lines come from the ADAPT library

The experiments are conducted on one synthetic and two benchmark datasets:

• CityCam
• Sentiment analysis