Distributed Multi-Task Learning with Shared Representation
By Jialei Wang, Mladen Kolar, Nati Srebro. 2016
23 citations recorded by the source corpus.
We study the problem of distributed multi-task learning with shared representation, where each machine aims to learn a separate, but related, task in an unknown shared low-dimensional subspaces, i.e. when the predictor matrix has low rank. We consider a setting where each task is handled by a different machine, with samples for the task available locally on the machine, and study communication-efficient methods for exploiting the shared structure.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
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
- Virginia Smith
- Ameet Talwalkar
- Maziar Sanjabi
- Peter Richtárik
- Jakub Konecný
- Qiang Yang
- Chunyan Miao
- Mingchen Li
In Computer Vision and Pattern Recognition
- Peilin Zhao
- Ameet Talwalkar
- Chunyan Miao
- Steven C. H. Hoi
- Virginia Smith
- Yingcong Li
- Shuji Hao
- Maziar Sanjabi
Citations in the corpus
- Federated Multi-Task Learning (2017, background): “While several recent works [1, 33, 51, 52] have considered the issue of distributed MTL training, the proposed methods do not allow for flexibility of communication versus computation.”
- Provable and Efficient Continual Representation Learning (2022, background): “Some of the earliest works towards this goal include Baxter (2000) and linear settings of Lounici et al. (2011); Pontil and Maurer (2013); Wang et al. (2016); Cavallanti et al. (2010).”
- Distributed Multi-Task Relationship Learning (2017, unknown): “Different from prior solutions to distributed MTL, which are focused on the former category [5, 29, 30], our proposed DMTRL falls into the latter category.”
- Personalized Federated Learning With Differential Privacy (2020, background): “Besides, some works recently studied the problem of collaborative learning of personalized models, however, they did not address any privacy issue [7], [24], [27].”
- Distributed multi-task classification: a decentralized online learning approach (2017, methodology): “Dinuzzo [16] first explored distributed MTL by performing information fusion with a server-client strategy, while later research [37,38] proposed distributed MTL algorithms by further restricting task relatedness through shared sparsity.”