Learning with Whom to Share in Multi-task Feature Learning

By Zhuoliang Kang, Kristen Grauman, Fei Sha. 2011

404 citations recorded by the source corpus.

Subfields: 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 Representation & Self-Supervised Learning

Citations in the corpus

Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges (2019, background): “While “learning to share” approaches (Kang et al., 2011; Ruder et al., 2017; Platanios et al., 2018) are promising alternatives, a more straightforward solution could be implicitly increasing the per-task capacity by increasing overall model capacity.”
An Overview of Multi-task Learning (2018, methodology): “The MTFL method is extended in [32] to the case of multiple clusters, where each cluster applies the MTFL method, and in order to learn the cluster structure, a regularizer, i.e. (cid”
Cross-Stitch Networks for Multi-task Learning (2016, methodology): “The term multi-task learning (MTL) itself has been broadly used [2, 14, 28, 42, 54, 55] as an umbrella term to include representation learning and selection [4, 13, 31, 37], transfer learning [39, 41, 56] etc.”
UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory (2016, neutral): “[27, 46].”
A Survey on Multi-Task Learning (2017, methodology): “[66] extend the MTFL method [11], [12], which treats all the tasks as a whole cluster, to the case with multiple task clusters and aim to minimize the squared trace norm in each cluster.”
Forward and Reverse Gradient-Based Hyperparameter Optimization (2017, background): “Other approaches (e.g. (Kang et al., 2011) tackle the same problem in a similar framework, but a complete analysis of MTL is beyond the scope of this paper.”
Learning Task Grouping and Overlap in Multi-task Learning (2012, methodology): “Recently, task grouping in the subspace based regularization framework was proposed in (Kang et al., 2011).”
Meta-Learning in Neural Networks: A Survey (2020, methodology): “, methods that group tasks into clusters [290] or subspaces [291].”
GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks (2017, methodology): “Clustering methods have shown success beyond deep models (Jacob et al., 2009; Kang et al., 2011), while constructs such as deep relationship networks (Long & Wang, 2015) and cross-stich networks (Misra et al.”
Diverse Few-Shot Text Classification with Multiple Metrics (2018, methodology): “Previous works (Kumar and Daume III, 2012; Kang et al., 2011; Crammer and Mansour, 2012; Barzilai and Crammer, 2015) mainly focused on convex objectives, and assumed the number of classes is the same across different tasks (e.”
Deep Multi-task Representation Learning: A Tensor Factorisation Approach (2016, methodology): “For an unfair comparison, shallow matrix-based MTL methods [Kang et al., 2011, Kumar and Daum´e III, 2012] report around 14% error rate (binary classiﬁcation, 64 dimensional PCA feature) with 1000 training data, and with the same amount of data, our methods have error rate below 6%.”
SpotTune: Transfer Learning Through Adaptive Fine-Tuning (2018, background): “In the multi-task setting, knowing which tasks or parameters are shareable is a longstanding challenge [19, 23, 45, 29].”
Fully-Adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classification (2016, neutral): “A few methods have addressed the problem of “with whom” each task should share features [45, 16, 51, 18, 21, 26].”
Learning Multi-Level Task Groups in Multi-Task Learning (2015, methodology): “We thank Prof. Kunqing Xie and Prof. Guojie Song for providing the traffic data and valuable discussions.”
Dynamic Task Prioritization for Multitask Learning (2018, background): “Multitask learning benefits from multiple related tasks [63, 64] as they can reinforce one another and improve overall performance [23, 65].”