Prototype-Based Layered Federated Cross-Modal Hashing
Not on the map. Why?
Abstract (arXiv)
Recently, deep cross-modal hashing has gained increasing attention. However, in many practical cases, data are distributed and cannot be collected due to privacy concerns, which greatly reduces the cross-modal hashing performance on each client. And due to the problems of statistical heterogeneity, model heterogeneity, and forcing each client to accept the same parameters, applying federated learning to cross-modal hash learning becomes very tricky. In this paper, we propose a novel method called prototype-based layered federated cross-modal hashing. Specifically, the prototype is introduced to learn the similarity between instances and classes on server, reducing the impact of statistical heterogeneity (non-IID) on different clients. And we monitor the distance between local and global prototypes to further improve the performance. To realize personalized federated learning, a hypernetwork is deployed on server to dynamically update different layers' weights of local model. Experimental results on benchmark datasets show that our method outperforms state-of-the-art methods.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 17 of its 29 references that are in the map. First posted on arXiv 27 Oct 2022.
Builds on
17 of 29 references.
References · 17
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2018Federated Learning with Non-IID Datacited by 1,108
- 2016HyperNetworkscited by 1,027
- 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 503
- 2021Towards Personalized Federated Learningcited by 464
- 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 352
- 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 283
- 2022Layer-wised Model Aggregation for Personalized Federated Learningcited by 96
- 2021Adaptive Quantization of Model Updates for Communication-Efficient Federated Learningcited by 63
- 2020Federated Learning with Only Positive Labelscited by 55
- 2016Deep Cross-Modal Hashingcited by 54
5 more
- 2015Supervised Discrete Hashingcited by 40
- 2018Neural Compatibility Modeling with Attentive Knowledge Distillationcited by 17
- 2021A Quantitative Metric for Privacy Leakage in Federated Learningcited by 12
- 2021Deep Hashing with Hash Center Update for Efficient Image Retrievalcited by 4
- 2017Measuring the Accuracy of Object Detectors and Trackerscited by 2
Built on by
Citing papers per year: 2023: 1.
1 paper.