Self-Paced Multitask Learning with Shared Knowledge
نویسندگان
چکیده
This paper introduces self-paced task selection to multitask learning, where instances from more closely related tasks are selected in a progression of easier-to-harder tasks, to emulate an effective human education strategy, but applied to multitask machine learning. We develop the mathematical foundation for the approach based on iterative selection of the most appropriate task, learning the task parameters, and updating the shared knowledge, optimizing a new bi-convex loss function. This proposed method applies quite generally, including to multitask feature learning, multitask learning with alternating structure optimization and multitask manifold regularization learning. Results show that in each of the above formulations selfpaced (easier-to-harder) task selection outperforms the baseline version of these methods in all the experiments.
منابع مشابه
Generalized Dictionary for Multitask Learning with Boosting
While multitask learning has been extensively studied, most existing methods rely on linear models (e.g. linear regression, logistic regression), which may fail in dealing with more general (nonlinear) problems. In this paper, we present a new approach that combines dictionary learning with gradient boosting to achieve multitask learning with general (nonlinear) basis functions. Specifically, f...
متن کاملDeep Asymmetric Multi-task Feature Learning
We propose Deep Asymmetric Multitask Feature Learning (Deep-AMTFL) which can learn deep representations shared across multiple tasks while effectively preventing negative transfer that may happen in the feature sharing process. Specifically, we introduce an asymmetric autoencoder term that allows predictors for the confident tasks to have high contribution to the feature learning while suppress...
متن کاملIncorporating Prior Knowledge About Financial Markets Through Neural Multitask Learning
We present the systematic method of Multitask Learning for incorporating prior knowledge (hints) into the inductive learning system of neural networks. Multitask Learning is an inductive transfer method which uses domain information about related tasks as inductive bias to guide the learning process towards better solutions of the main problem. These tasks are presented to the learning system i...
متن کاملMultitask Sparsity via Maximum Entropy Discrimination
A multitask learning framework is developed for discriminative classification and regression where multiple large-margin linear classifiers are estimated for different prediction problems. These classifiers operate in a common input space but are coupled as they recover an unknown shared representation. A maximum entropy discrimination (MED) framework is used to derive the multitask algorithm w...
متن کاملCo-Clustering for Multitask Learning
This paper presents a new multitask learning framework that learns a shared representation among the tasks, incorporating both task and feature clusters. The jointlyinduced clusters yield a shared latent subspace where task relationships are learned more effectively and more generally than in state-of-the-art multitask learning methods. The proposed general framework enables the derivation of m...
متن کامل