Federated Adversarial Domain Adaptation

Authors: Xingchao Peng, Zijun Huang, Yizhe Zhu, Kate Saenko

ICLR 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirically, we perform extensive experiments on several image and text classification tasks and show promising results under unsupervised federated domain adaptation setting.
Researcher Affiliation Academia Xingchao Peng Boston University Boston, MA 02215, USA xpeng@bu.edu Zijun Huang Columbia University New York City, NY 10027, USA zijun.huang@columbia.edu Yizhe Zhu Rutgers University Piscataway, NJ 08854, USA yz530@scarletmail.rutgers.edu Kate Saenko Boston University Boston, MA 02215, USA saenko@bu.edu
Pseudocode Yes Algorithm 1 Federated Adversarial Domain Adaptation
Open Source Code No The paper does not provide any explicit statements about open-sourcing code or links to a code repository.
Open Datasets Yes We test our model on the following tasks: digit classification (Digit-Five), object recognition (Office Caltech10 (Gong et al., 2012), Domain Net (Peng et al., 2018)) and sentiment analysis (Amazon Review dataset (Blitzer et al., 2007a)).
Dataset Splits Yes Table 10: Detailed number of samples we used in our experiments. Digit-Five Splits mnist mnist_m svhn syn usps Total Train 25,000 25,000 25,000 25,000 7,348 107,348 Test 9,000 9,000 9,000 9,000 1,860 37,860 [...] Domain Net Splits clp inf pnt qdr rel skt Total Train 34,019 37,087 52,867 120,750 122,563 49,115 416,401 Test 14,818 16,114 22,892 51,750 52,764 21,271 179,609
Hardware Specification Yes We perform our experiments on a 10 Titan-Xp GPU cluster and simulate the federated system on a single machine (as the data communication is not the main focus of this paper).
Software Dependencies No Our model is implemented with Py Torch. However, no specific version number for PyTorch or any other software dependency is provided.
Experiment Setup Yes The detailed architecture of our model can be found in Table 7 (see supplementary material). ... Details of our model are listed in Table 9 (supplementary material).