Federated Meta-Learning for Recommendation

By Fei Chen, Zhenhua Dong, Zhenguo Li, Xiuqiang He. 2018

140 citations recorded by the source corpus.

Subfields: Meta & Continual Learning, Federated & Distributed Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Meta & Continual Learning

In Federated & Distributed Learning

Citations in the corpus

Backdoor Attacks on Federated Meta-Learning (2020, background): “While the use of meta-learning in a federated setting and its privacy concerns were explored by previous work [10, 11], the influence of backdoor attacks on federated meta-learning has not been investigated.”
Personalized Federated Learning with Moreau Envelopes (2020, methodology): “hat FedAvg can be interpreted as meta-learning and proposed combining FedAvg with Reptile [32] for FL personalization. The application of federated meta-learning in recommender systems was studied in [36]. Finally, multi-task learning can be used for personalization: [20] introduced a federated mult”
Personalized Federated Learning: A Meta-Learning Approach (2020, background): “Moreover, Chen et al. (2018) focused on recommendation systems and proposed a meta-federated learning framework in which a parameterized meta-algorithm is used to train parameterized recommendation models and both meta-algorithm and local models’ parameters need to be optimized.”
Secure Federated Submodel Learning (2019, background): “[35] instead adopted meta-learning to enable client-specific modeling, where clients contribute information at the algorithm level rather than the model level to help train the meta-learner.”
Differentially Private Meta-Learning (2019, background): “That being said, a federated setting involving per-user personalization (Chen et al., 2018; Smith et al., 2017) is a natural meta-learning application.”
Adaptive Gradient-Based Meta-Learning Methods (2019, methodology): “GBML is used in a variety of LTL domains such as vision [38, 44, 35], federated learning [16], and robotics [20, 1].”
Federated Machine Learning (2019, background): “There are also research efforts to make federated learning more personalizable [13, 60].”
LEAF: A Benchmark for Federated Settings (2018, background): “voice commands in [15], and proprietary data by Huawei in [4]; and (3) realistic federated datasets that are derived from publicly available data, but which are not straightforward to reproduce, e.”
Federated Learning: Challenges, Methods, and Future Directions (2019, background): “There exists a large body of literature in machine learning that has modeled statistical heterogeneity via methods such as meta-learning [114] and multi-task learning [18, 37]; these ideas have been recently extended to the federated setting [24, 26, 35, 58, 106, 138].”
FedMD: Heterogenous Federated Learning via Model Distillation (2019, background): “There is also statistical heterogne-ity (the non i.i.d. problem) where clients have a varying amount of data coming from distinct distributions [9, 10, 11, 12, 13, 14].”
Federated User Representation Learning (2019, methodology): “Research on collaborative personalization in FL [28, 27, 7, 33] has generally focused on the development of new techniques tailored to the FL setting.”
Personalized Federated Learning: An Attentive Collaboration Approach (2020, background): “2, most existing methods [9, 10, 11, 12, 13, 14, 15, 16] that produce personalized models by locally customizing a global model cannot effectively identify the underlying collaboration relationships between clients.”
FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare (2019, background): “Since then, other researchers started to focus on privacy-preserving machine learning [Bonawitz et al. , 2017; Shokri and Shmatikov, 2015; Geyer et al. , 2017], federated multi-task learning [Smith et al. , 2017 ] , as well as personalized federated learning [ Chen et al. , 2018a ] .”
Survey of Personalization Techniques for Federated Learning (2020, background): “Chen et al. [29] present a federated meta-learning framework for building personalized recommendation models where both the algorithm and the model are parameterized and need to be optimized.”
CMFL: Mitigating Communication Overhead for Federated Learning (2019, background): “Another recent advance is Federated Meta-Learning [18], where the user’s information is shared at the level of algorithms instead of models or data as assumed in the previous approaches.”
Multi-Step Model-Agnostic Meta-Learning: Convergence and Improved Algorithms (2020, background): “…is a simple and effective approach used in a wide range of domains including classification/regression (Rajeswaran et al., 2019), reinforcement learning (Finn et al., 2017a), robotics (Al-Shedivat et al., 2017), federated learning (Chen et al., 2018), and imitation learning (Finn et al., 2017b).”
Personalized Cross-Silo Federated Learning on Non-IID Data (2020, methodology): “Similarly, meta-learning methods (Chen et al. 2018; Fallah, Mokhtari, and Ozdaglar 2020; Jiang et al. 2019; Khodak, Balcan, and Talwalkar 2019; Kulkarni, Kulkarni, and Pant 2020; Nichol, Achiam, and Schulman 2018) can be extended to customize personalized models by adapting a well-trained global…”
Wireless Networks Design in the Era of Deep Learning: Model-Based, AI-Based, or Both? (2019, methodology): “As a refinement of this approach, [88] proposes not to exchange the updates of the model, but rather the updates of the algorithm that is used to compute the model.”