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

Guo，Pengxin1; Deng，Chang3; Xu，Linjie4; Huang，Xiaonan1; Zhang，Yu1,2

10.1007/978-3-030-86486-6_33

2021

European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)

0302-9743

1611-3349

LECT NOTES ARTIF INT

12975 LNAI

538-553

SEP 13-17, 2021

null,null,ELECTR NETWORK

GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND

SPRINGER INTERNATIONAL PUBLISHING AG

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 using class embeddings to augment the feature representation. The proposed feature augmentation strategy can be used in many deep multi-task learning models. Experiments on real-world datasets show the significant performance improvement when using this strategy.

Feature learning Graph neural network Multi-task learning

第一 ; 通讯

英语

CPCI-S ; EI

NSFC[62076118]

Computer Science

Computer Science, Artificial Intelligence ; Computer Science, Information Systems

WOS:000712017700033

20213910941723

Deep learning ; Embeddings

Ergonomics and Human Factors Engineering:461.4 ; Artificial Intelligence:723.4

2-s2.0-85115443090

Scopus

1.Department of Computer Science and Engineering,Southern University of Science and Technology,Shenzhen,China
2.Peng Cheng Laboratory,Shenzhen,China
3.Committee on Computational and Applied Mathematics,University of Chicago,Chicago,United States
4.Game AI Group,Queen Mary University of London,London,United Kingdom

Guo，Pengxin,Deng，Chang,Xu，Linjie,et al. Deep Multi-task Augmented Feature Learning via Hierarchical Graph Neural Network[C]. GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND:SPRINGER INTERNATIONAL PUBLISHING AG,2021:538-553.