Name
Abstract | ||
|---|---|---|
AbstractMulti-source domain adaptation has received considerable attention due to its effectiveness of leveraging the knowledge from multiple related sources with different distributions to enhance the learning performance. One of the fundamental challenges in multi-source domain adaptation is how to determine the amount of knowledge transferred from each source domain to the target domain. To address this issue, we propose a new algorithm, called Domain-attention Conditional Wasserstein Distance (DCWD), to learn transferred weights for evaluating the relatedness across the source and target domains. In DCWD, we design a new conditional Wasserstein distance objective function by taking the label information into consideration to measure the distance between a given source domain and the target domain. We also develop an attention scheme to compute the transferred weights of different source domains based on their conditional Wasserstein distances to the target domain. After that, the transferred weights can be used to reweight the source data to determine their importance in knowledge transfer. We conduct comprehensive experiments on several real-world data sets, and the results demonstrate the effectiveness and efficiency of the proposed method. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1145/3391229 | ACM Transactions on Intelligent Systems and Technology |
Keywords | DocType | Volume |
Domain adaptation, multiple sources, optimal transport, attention | Journal | 11 |
Issue | ISSN | Citations |
4 | 2157-6904 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hanrui Wu | 1 | 32 | 5.23 |
| Yuguang Yan | 2 | 47 | 7.16 |
| Michael K. Ng | 3 | 395 | 42.26 |
| Wu Qingyao | 4 | 259 | 33.46 |