3 papers
cs.LG2024
Federated Source-free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Data
Junki Mori, Kosuke Kihara, Taiki Miyagawa +3
Federated learning (FL) commonly assumes that the server or some clients have labeled data, which is often impractical due to annotation costs and privacy concerns. Addressing this…
cs.LG2024
Survey of Privacy Threats and Countermeasures in Federated Learning
Masahiro Hayashitani, Junki Mori, Isamu Teranishi
Federated learning is widely considered to be as a privacy-aware learning method because no training data is exchanged directly between clients. Nevertheless, there are threats to…
cs.LG2023
Heterogeneous Domain Adaptation with Positive and Unlabeled Data
Junki Mori, Ryo Furukawa, Isamu Teranishi +1
Heterogeneous unsupervised domain adaptation (HUDA) is the most challenging domain adaptation setting where the feature spaces of source and target domains are heterogeneous, and t…