Deep Multi-task Augmented Feature Learning via Hierarchical Graph Neural Network
نویسندگان
چکیده
Deep multi-task learning attracts much attention in recent years as it achieves good performance many applications. Feature is important to deep for sharing common information among tasks. In this paper, we propose a Hierarchical Graph Neural Network (HGNN) learn augmented features learning. The HGNN consists of two-level graph neural networks. the low level, an intra-task network responsible powerful representation each data point task by aggregating its neighbors. Based on learned representation, embedding can be generated similar way max pooling. second inter-task updates embeddings all tasks based mechanism model relations. Then one used augment feature points task. Moreover, classification tasks, inter-class introduced conduct operations finer granularity, i.e., class generate using representation. proposed augmentation strategy models. Experiments real-world datasets show significant improvement when strategy.
منابع مشابه
Multi-task learning deep neural networks for speech feature denoising
Traditional automatic speech recognition (ASR) systems usually get a sharp performance drop when noise presents in speech. To make a robust ASR, we introduce a new model using the multi-task learning deep neural networks (MTL-DNN) to solve the speech denoising task in feature level. In this model, the networks are initialized by pre-training restricted Boltzmann machines (RBM) and fine-tuned by...
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 کاملComposite Task-Completion Dialogue System via Hierarchical Deep Reinforcement Learning
Building a dialogue agent to fulfill complex tasks, such as travel planning, is challenging because the agent has to learn to collectively complete multiple subtasks. For example, the agent needs to reserve a hotel and book a flight so that there leaves enough time for commute between arrival and hotel check-in. This paper addresses this challenge by formulating the task in the mathematical fra...
متن کاملMulti-Task Feature Learning
We present a method for learning a low-dimensional representation which is shared across a set of multiple related tasks. The method builds upon the wellknown 1-norm regularization problem using a new regularizer which controls the number of learned features common for all the tasks. We show that this problem is equivalent to a convex optimization problem and develop an iterative algorithm for ...
متن کاملGeneralization Tower Network: A Novel Deep Neural Network Architecture for Multi-Task Learning
Deep learning (DL) advances state-of-the-art reinforcement learning (RL), by incorporating deep neural networks in learning representations from the input to RL. However, the conventional deep neural network architecture is limited in learning representations for multi-task RL (MT-RL), as multiple tasks can refer to different kinds of representations. In this paper, we thus propose a novel deep...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Lecture Notes in Computer Science
سال: 2021
ISSN: ['1611-3349', '0302-9743']
DOI: https://doi.org/10.1007/978-3-030-86486-6_33