Collaborating between Local and Global Learning for Distributed Online Multiple Tasks
By Xin Jin, Ping Luo, Fuzhen Zhuang, Jia He, Jia He, Qing He. 2015
22 citations recorded by the source corpus.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Mohammad Rostami
- Virginia Smith
- Ameet Talwalkar
- Qiang Yang
- Maziar Sanjabi
- Eric Eaton
- Jiayu Zhou
- Ming Yan
Citations in the corpus
- Federated Multi-Task Learning (2017, background): “The works of [22] and [6] allow for asynchronous updates to help mitigate stragglers, but do not address fault tolerance.”
- SAFA: A Semi-Asynchronous Protocol for Fast Federated Learning With Low Overhead (2019, methodology): “e basis of FedAvg [3] for achieving fast, communication-efficient federated optimization. SAFA takes advantage of several efficiency-boosting featuresfromasynchronousmachinelearningapproaches(e.g., [10][11][12]) while we make use of refined steering control mechanism to mitigate the impact on the globa”
- Asynchronous Online Federated Learning for Edge Devices with Non-IID Data (2019, unknown): “Jin et al. [28] developed an asynchronous distributed framework to perform local training and central learning alternatively with a soft confidence-weighted classifier.”
- Asynchronous Multi-task Learning (2016, background): “, on the other hand, proposed collaborating between local and global learning for distributed online multiple tasks in [11].”
- Multi-Agent Distributed Lifelong Learning for Collective Knowledge Acquisition (2017, methodology): “Existing methods in the literature have only investigated special cases of this setting for distributed multi-task learning (MTL) (Dinuzzo, Pillonetto, and De Nicolao 2011; Chen, Richard, and Sayed 2014; Parameswaran and Wein-berger 2010; Jin et al. 2015).”
- Learning Transferable Knowledge Through Embedding Spaces (2019, methodology): “Existing methods in the literature have mostly investigated special cases of this setting for distributed multi-task learning (MTL) [237; 238; 235].”
- Privacy-Preserving Distributed Multi-Task Learning with Asynchronous Updates (2017, background): “Another study [29] proposed distributed online MTL (DOM) framework, which includes collaborative local learning in local task nodes and asynchronous online MTL method as the global learning in central node.”