Distributed Multi-Task Learning with Shared Representation
نویسندگان
چکیده
We study the problem of distributed multitask learning with shared representation, where each machine aims to learn a separate, but related, task in an unknown shared low-dimensional subspaces, i.e. when the predictor matrix has low rank. We consider a setting where each task is handled by a different machine, with samples for the task available locally on the machine, and study communication-efficient methods for exploiting the shared structure.
منابع مشابه
Multi-task Multi-domain Representation Learning for Sequence Tagging
Many domain adaptation approaches rely on learning cross domain shared representations to transfer the knowledge learned in one domain to other domains. Traditional domain adaptation only considers adapting for one task. In this paper, we explore multi-task representation learning under the domain adaptation scenario. We propose a neural network framework that supports domain adaptation for mul...
متن کاملMulti-Task Model and Feature Joint Learning
Given several tasks, multi-task learning (MTL) learns multiple tasks jointly by exploring the interdependence between them. The basic assumption in MTL is that those tasks are indeed related. Existing MTL methods model the task relatedness/interdependence in two different ways, either common parameter-sharing or common featuresharing across tasks. In this paper, we propose a novel multi-task le...
متن کاملJointly Predicting Arousal, Valence and Dominance with Multi-Task Learning
An appealing representation of emotions is the use of emotional attributes such as arousal (passive versus active), valence (negative versus positive) and dominance (weak versus strong). While previous studies have considered these dimensions as orthogonal descriptors to represent emotions, there are strong theoretical and practical evidences showing the interrelation between these emotional at...
متن کاملMulti-task Domain Adaptation for Sequence Tagging
Many domain adaptation approaches rely on learning cross domain shared representations to transfer the knowledge learned in one domain to other domains. Traditional domain adaptation only considers adapting for one task. In this paper, we explore multi-task representation learning under the domain adaptation scenario. We propose a neural network framework that supports domain adaptation for mul...
متن کاملAn Adaptive Quantum-based Multiobjective Evolutionary Algorithm for Efficient Task Assignment in Distributed Systems
Multi-criterion quantum programming is a new paradigm of decision making for complex systems. Quantum-based multiobjective algorithm utilizes a new representation, called a Q-bit, for the probabilistic representation that is based on the concept of qubits. Evolutionary computing with Q-bit representation has a better characteristic of population diversity than other representations, since it ca...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره abs/1603.02185 شماره
صفحات -
تاریخ انتشار 2016