Learning Multiple Tasks using Manifold Regularization

By Alekh Agarwal, Hal Daumé Iii, Samuel Gerber. 2010

98 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning, Meta & Continual Learning

How researchers see this paper

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

In Representation & Self-Supervised Learning

In Meta & Continual Learning

Citations in the corpus

LEAF: A Benchmark for Federated Settings (2018, background): “This paradigm is also amenable to federated settings [30] but, contrary to realistic federated networks, is usually explored in regimes with small numbers of tasks and samples, e.g., the popular Landmine Detection [38, 26, 36, 30], Computer Survey [2, 1, 14] and Inner London Education Authority Scho”
A Survey on Multi-Task Learning (2017, background): “Problem (11) is extended in [46] to a general case where different w’s lie in a manifold instead of a subspace.”
Subspace Regularizers for Few-Shot Class Incremental Learning (2021, background): “Past work on other multitask learning problems has demonstrated the effectiveness of constraining parameters for related tasks to be similar (Jacob et al., 2008), lie on the same manifold (Agarwal et al., 2010) or even on the same linear subspace (Argyriou et al., 2007a).”
Learning Task Grouping and Overlap in Multi-task Learning (2012, methodology): “( Argyriou et al., 2008a; Agarwal et al., 2010; Bakker & Heskes, 2003).”
Hierarchical Multitask Structured Output Learning for Large-scale Sequence Segmentation (2011, background): “, [1]) assuming a cluster relationship [11] or a hierarchy [6, 23, 13] between tasks.”
Multi-Task Averaging (2011, methodology): “A different approach to using manifold regularization concepts for MTL was recently proposed by Agarwal et al. (2010) for parametric multi-task learning.”
Multi-Task Learning for Dense Prediction Tasks: A Survey (2020, unknown): “[47], [48] or manifold [49].”
DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics (2020, unknown): “One potential way to realize this is to model all tasks as laying on a low dimensional manifold [83].”
Convex Multitask Learning with Flexible Task Clusters (2012, background): “…cluster center of all the tasks; in (Ando & Zhang, 2005; Chen et al., 2010; 2011a), u t comes from a low-dimensional linear subspace, which is extended to a nonlinear manifold in (Agarwal et al., 2010); in (Jalali et al., 2010), u t is the component that uses features shared by other tasks.”
Branched Multi-Task Networks: Deciding what layers to share (2019, background): “A general solution to this problem is to cluster tasks based on prior knowledge about their similarity or relatedness [1, 3, 12, 22, 48].”
Multi-Task Learning with Gaussian Matrix Generalized Inverse Gaussian Model (2013, methodology): “The regularization method is widely used in multi-task learning to discover the relationship among the tasks (Evgeniou & Pontil, 2004; Argyriou et al., 2007; Agarwal et al., 2010; Jenatton et al., 2011).”
Flexible Modeling of Latent Task Structures in Multitask Learning (2012, methodology): “• Nonlinear Manifold Assumption: A mixture of linear subspaces allows modeling a nonlinear subspace (Chen et al., 2010) and can capture the case when the weight vectors live on a nonlinear manifold (Ghosn & Bengio, 2003; Agarwal et al., 2010).”
Generalized Dictionary for Multitask Learning with Boosting (2016, background): “Examples of such structure include the model parameters lying close to each other [Evgeniou and Pontil, 2004] in a low dimensional subspace [Ando and Zhang, 2005], manifold [Agarwal et al., 2010], or sharing similar sparsity patterns [Liu et al., 2009; Obozinski et al., 2010].”