Asymmetric multi-task learning based on task relatedness and loss

By Giwoong Lee, Eunho Yang, Sung Ju Hwang. 2016

109 citations recorded by the source corpus.

How researchers see this paper

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

In Optimization & Training

Citations in the corpus

Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges (2019, background): “Research on exploiting task-relatedness (Lee et al., 2016; Neubig and Hu, 2018), curriculum learning on noisy data (van der Wees et al.”
An Overview of Multi-task Learning (2018, methodology): “In [51], a similar regularizer to that of the MTRL method is proposed by assuming a parametric form of as − 1 = ( I m − A )( I m − A ) T , where A is an asymmetric task relation claimed in [51].”
LEAF: A Benchmark for Federated Settings (2018, background): “…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 School [26, 17, 1, 2, 14] datasets have at most 200 tasks each.”
A Survey on Multi-Task Learning (2017, methodology): “[99] focus on learning asymmetric task relations.”
Learning to Multitask (2018, methodology): “…Schatten norm regularization with r = 2 (SSNR 2 ) which is equivalent to squared Schatten -norm regularization according to Theorem 2, clustered multitask learning (CMTL) [16], multitask learning with graphical Lasso (glMTL) [32, 27], asymmetric multitask learning (AMTL) [19], and SPATS [33].”
Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation (2019, methodology): “In general, MTL algorithms can be classified into several categories, including feature learning approach [34, 41], low-rank approach [7, 16], task clustering approach [47], task relation learning approach [12], and decomposition approach [6].”
Efficiently Identifying Task Groupings for Multi-Task Learning (2021, background): “A plethora of multi-task methods addressing what parameters to share among tasks in a model have been developed, such as Neural Architecture Search [19, 47, 49, 35, 22, 39], Soft-Parameter Sharing [40, 14, 52], and asymmetric information transfer [31, 44, 32] to improve multi-task performance.”
Transferability and Hardness of Supervised Classification Tasks (2019, background): “Finally, in some scenarios, establishing task relationships requires multi-task learning of the models, to measure the influence different tasks have on each other [30, 36, 59, 66, 71].”