Deep Multi-Task Augmented Feature Learning via Hierarchical Graph Neural Network

02/12/2020
by   Pengxin Guo, et al.
15

Deep multi-task learning attracts much attention in recent years as it achieves good performance in many applications. Feature learning is important to deep multi-task learning for sharing common information among tasks. In this paper, we propose a Hierarchical Graph Neural Network (HGNN) to learn augmented features for deep multi-task learning. The HGNN consists of two-level graph neural networks. In the low level, an intra-task graph neural network is responsible of learning a powerful representation for each data point in a task by aggregating its neighbors. Based on the learned representation, a task embedding can be generated for each task in a similar way to max pooling. In the second level, an inter-task graph neural network updates task embeddings of all the tasks based on the attention mechanism to model task relations. Then the task embedding of one task is used to augment the feature representation of data points in this task. Moreover, for classification tasks, an inter-class graph neural network is introduced to conduct similar operations on a finer granularity, i.e., the class level, to generate class embeddings for each class in all the tasks use class embeddings to augment the feature representation. The proposed feature augmentation strategy can be used in many deep multi-task learning models. we analyze the HGNN in terms of training and generalization losses. Experiments on real-world datastes show the significant performance improvement when using this strategy.

READ FULL TEXT
research
11/26/2018

Multi-task Learning over Graph Structures

We present two architectures for multi-task learning with neural sequenc...
research
02/21/2023

MulGT: Multi-task Graph-Transformer with Task-aware Knowledge Injection and Domain Knowledge-driven Pooling for Whole Slide Image Analysis

Whole slide image (WSI) has been widely used to assist automated diagnos...
research
11/15/2021

Multi-Task Classification of Sewer Pipe Defects and Properties using a Cross-Task Graph Neural Network Decoder

The sewerage infrastructure is one of the most important and expensive i...
research
04/12/2022

Medusa: Universal Feature Learning via Attentional Multitasking

Recent approaches to multi-task learning (MTL) have focused on modelling...
research
09/15/2021

Learning Robot Structure and Motion Embeddings using Graph Neural Networks

We propose a learning framework to find the representation of a robot's ...
research
09/22/2019

Deep Universal Graph Embedding Neural Network

Learning powerful data embeddings has become a center piece in machine l...
research
09/18/2023

A Heterogeneous Graph-Based Multi-Task Learning for Fault Event Diagnosis in Smart Grid

Precise and timely fault diagnosis is a prerequisite for a distribution ...

Please sign up or login with your details

Forgot password? Click here to reset