7 papers
Position: Embodied AI Requires a Privacy-Utility Trade-off
Xiaoliang Fan, Jiarui Chen, Zhuodong Liu +6
Embodied AI (EAI) systems are rapidly transitioning from simulations into real-world domestic and other sensitive environments. However, recent EAI solutions have largely demonstra…
Federated Learning with Domain Shift Eraser
Zheng Wang, Zihui Wang, Xiaoliang Fan +1
Federated learning (FL) is emerging as a promising technique for collaborative learning without local data leaving their devices. However, clients' data originating from diverse do…
Federated Graph Learning for Cross-Domain Recommendation
Ziqi Yang, Zhaopeng Peng, Zihui Wang +6
Cross-domain recommendation (CDR) offers a promising solution to the data sparsity problem by enabling knowledge transfer across source and target domains. However, many recent CDR…
P4GCN: Vertical Federated Social Recommendation with Privacy-Preserving Two-Party Graph Convolution Network
Zheng Wang, Wanwan Wang, Yimin Huang +5
In recent years, graph neural networks (GNNs) have been commonly utilized for social recommendation systems. However, real-world scenarios often present challenges related to user…
Selective Knowledge Sharing for Personalized Federated Learning Under Capacity Heterogeneity
Zheng Wang, Zhaopeng Peng, Zihui Wang +1
Federated Learning (FL) stands to gain significant advantages from collaboratively training capacity-heterogeneous models, enabling the utilization of private data and computing po…
FedSAC: Dynamic Submodel Allocation for Collaborative Fairness in Federated Learning
Zihui Wang, Zheng Wang, Lingjuan Lyu +6
Collaborative fairness stands as an essential element in federated learning to encourage client participation by equitably distributing rewards based on individual contributions. E…
FedPFT: Federated Proxy Fine-Tuning of Foundation Models
Zhaopeng Peng, Xiaoliang Fan, Yufan Chen +5
Adapting Foundation Models (FMs) for downstream tasks through Federated Learning (FL) emerges a promising strategy for protecting data privacy and valuable FMs. Existing methods fi…