Self-Paced Multi-Task Learning
نویسندگان
چکیده
Multi-task learning is a paradigm, where multiple tasks are jointly learnt. Previous multi-task learning models usually treat all tasks and instances per task equally during learning. Inspired by the fact that humans often learn from easy concepts to hard ones in the cognitive process, in this paper, we propose a novel multi-task learning framework that attempts to learn the tasks by simultaneously taking into consideration the complexities of both tasks and instances per task. We propose a novel formulation by presenting a new task-oriented regularizer that can jointly prioritize tasks and instances. Thus it can be interpreted as a self-paced learner for multi-task learning. An efficient block coordinate descent algorithm is developed to solve the proposed objective function, and the convergence of the algorithm can be guaranteed. Experimental results on the toy and real-world datasets demonstrate the effectiveness of the proposed approach, compared to the state-of-the-arts.
منابع مشابه
Next or Beyond Next: Effect of Contrastive Phrase-Based Treatment on Stage Gain Across Self-Paced and More Time-Constrained Tasks
This study explored the effect of contrastive phrase resynthesis instruction ongaining the teachability hypothesis stages in self-paced versus time-constrained oralproduction and recognition. Three groups (i.e., 23 learners) of high beginner femalelearners in an English language institute were randomly selected from a cohort oflearners. One group received contrastive metalinguistic instruction ...
متن کاملThe effect of verbal and visuospatial working memory spans on collocation processing in learners of English
Much interest has recently been directed toward the knowledge of collocations in the field of second language learning since they have been asserted to improve fluency. The current study was intended to examine the effect of verbal and visuospatial working memory spans on the processing of collocations using a Self-Pace Reading Task (SPRT) and relevant working memory tasks. To this end, partici...
متن کاملA Self-Paced Regularization Framework for Multi-Label Learning
In this brief, we propose a novel multilabel learning framework, called multilabel self-paced learning, in an attempt to incorporate the SPL scheme into the regime of multilabel learning. Specifically, we first propose a new multilabel learning formulation by introducing a self-paced function as a regularizer, so as to simultaneously prioritize label learning tasks and instances in each iterati...
متن کاملSelf-Learning Camera: Autonomous Adaptation of Object Detectors to Unlabeled Video Streams
Learning object detectors requires massive amounts of labeled training samples from the specific data source of interest. This is impractical when dealing with many different sources (e.g., in camera networks), or constantly changing ones such as mobile cameras (e.g., in robotics or driving assistant systems). In this paper, we address the problem of self-learning detectors in an autonomous man...
متن کاملMotivational beliefs and perceptions of instructional quality: predicting satisfaction with online training
Many would agree that learning on the Web – a highly autonomous learning environment – may be difficult for individuals who lack motivation and self-regulated learning skills. Using a social cognitive view of academic motivation and self-regulation, the objective of the present study was to investigate the relations between students’ motivational beliefs, their perceptions of the learning envir...
متن کامل