Learned Weight Sharing for Deep Multi-Task Learning by Natural Evolution Strategy and Stochastic Gradient Descent
In deep multi-task learning, weights of task-specific networks are shared between tasks to improve performance on each single one. Since the question, which weights to share between layers, is difficult to answer, human-designed architectures often share everything but a last task-specific layer. In many cases, this simplistic approach severely limits performance. Instead, we propose an algorithm to learn the assignment between a shared set of weights and task-specific layers. To optimize the non-differentiable assignment and at the same time train the differentiable weights, learning takes place via a combination of natural evolution strategy and stochastic gradient descent. The end result are task-specific networks that share weights but allow independent inference. They achieve lower test errors than baselines and methods from literature on three multi-task learning datasets.
Code (1)
Tasks
Multi-Task LearningSimilar Papers 제목 키워드 기반
Conservative Data Sharing for Multi-Task Offline Reinforcement Learning
Offline reinforcement learning (RL) algorithms have shown promising results in domains where abundant pre-collected data is available. However, prior methods focus on solving individual problems from scratch with an offl…
Offline RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)PaCo: Parameter-Compositional Multi-Task Reinforcement Learning
The purpose of multi-task reinforcement learning (MTRL) is to train a single policy that can be applied to a set of different tasks. Sharing parameters allows us to take advantage of the similarities among tasks. However…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data
Multi-Task Learning (MTL) networks have emerged as a promising method for transferring learned knowledge across different tasks. However, MTL must deal with challenges such as: overfitting to low resource tasks, catastro…
Multi-Task LearningNatural Language InferenceTransfer LearningFSNet: Compression of Deep Convolutional Neural Networks by Filter Summary
We present a novel method of compression of deep Convolutional Neural Networks (CNNs) by weight sharing through a new representation of convolutional filters. The proposed method reduces the number of parameters of each …
General Classificationimage-classificationImage ClassificationNeural Architecture Search+3Speeding up Deep Learning Training by Sharing Weights and Then Unsharing
It has been widely observed that increasing deep learning model sizes often leads to significant performance improvements on a variety of natural language processing and computer vision tasks. In the meantime, however,…