Online Multitask Learning

By Ofer Dekel, Philip M. Long, Yoram Singer. 2006

81 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Management Science and Operations Research, Representation & Self-Supervised Learning

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

In Computer Networks and Communications

In Management Science and Operations Research

In Representation & Self-Supervised Learning

Citations in the corpus

An Overview of Multi-task Learning (2018, methodology): “When the training data in multiple tasks come in a sequentialway,traditionalMTLmodelscannothan-dlethembutmulti-taskonlinelearningiscapable ofdoingthisjob,asshowninsomerepresentative works[74–79].”
A Survey on Multi-Task Learning (2017, methodology): “In [152], [153], under a setting where all the tasks contribute toward a common goal, the relation between tasks is measured via a global loss function and several online algorithms are proposed to use absolute norms as the global loss function.”
Asynchronous Online Federated Learning for Edge Devices with Non-IID Data (2019, unknown): “[24].”
Asynchronous Online Federated Learning for Edge Devices (2019, unknown): “The online learning problem with multiple tasks was ﬁrst introduced by Dekel et al. [30].”
Distributed multi-task classification: a decentralized online learning approach (2017, background): “Recent years also witness extensive studies (Cavallanti et al. 2010; Dekel et al. 2006; Saha et al. 2011; Li et al. 2014; Zhang et al. 2016) on streaming data, also known as online multi-task learning (OMTL) algorithms, for the merits of low computation cost and strong adaptation to the changing…”
Using Task Descriptions in Lifelong Machine Learning for Improved Performance and Zero-Shot Transfer (2017, methodology): “Saha et al. (2011) use a task interaction matrix to model task relations online and Dekel et al. (2006) propose a shared global loss function that can be minimized as tasks arrive.”
Multitask Sparsity via Maximum Entropy Discrimination (2011, background): “Even more recently, online algorithms have been proposed (Dekel et al., 2006) for multitask learning with margin-based predictors and provideinteresting worst-case guarantees.”
Online Methods for Multi-Domain Learning and Adaptation (2008, methodology): “The goal of multi-task learning is to generalize across tasks/domains (Dekel et al., 2006; Evgeniou and Pontil, 2004).”
Multi-domain learning by confidence-weighted parameter combination (2010, background): “…MD 21211, USA e-mail: mdredze@cs.jhu.edu A. Kulesza Department of Computer and Information Science, University of Pennsylvania, Philadelphia, PA 19104, USA e-mail: kulesza@cis.upenn.edu K. Crammer Department of Electrical Engineering, The Technion, Haifa 32000, Israel e-mail: koby@ee.technion.ac.il”
Online Learning: A Comprehensive Survey (2018, background): “The multitask Perceptron algorithm (Cavallanti et al., 2010) is a pioneering work of OML that considers the inter-task relationship.”
Online Learning of Multiple Tasks and Their Relationships (2011, methodology): “The online multitask learning problem was first addressed in [Dekel et al., 2006].”
Learning Transferable Knowledge Through Embedding Spaces (2019, background): “[185] propose a shared global loss function that can be minimized as tasks arrive.”
Large-Scale Personalized Human Activity Recognition Using Online Multitask Learning (2013, methodology): “Huynh et al. [4] tried to discover latent activity patterns by using a Bayesian latent topic model (Bayesian LTM).”