Abstract | ||
---|---|---|
Transfer learning has been found helpful at enhancing the target domain's learning process by transferring useful knowledge from other different but related source domains. In many applications, however, collecting and labeling target information is not only very difficult but also expensive. At the same time, considerable prior experience in this regard exists in other application domains. This paper proposes a feature-based transfer learning method based on distribution similarity that aims at the partial overlap of features between two domains. The non-overlapping features are completed by leveraging the distribution similarity of other features within the source domain. Features of the two domains are then reweighted in accordance with the distribution similarity between the source and target domains. This, in turn, decreases the distribution discrepancy between the two domains, therefore achieving the desired feature transfer. Results of the experiments performed on Facebook and Sina Microblog data sets demonstrate that the proposed method is capable of effectively enhancing the accuracy of the prediction function. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/ACCESS.2018.2843773 | IEEE ACCESS |
Keywords | Field | DocType |
Distribution similarity,feature transfer,KL divergence,transfer learning | Data mining,Data set,Social media,Computer science,Transfer of learning,Microblogging,Probability distribution,Feature based,Kullback–Leibler divergence,Distributed computing | Journal |
Volume | ISSN | Citations |
6 | 2169-3536 | 1 |
PageRank | References | Authors |
0.35 | 0 | 6 |