NetRL: Task-aware Network Denoising via Deep Reinforcement Learning
- 22 June 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. PP (10414347) , 1
Abstract
Network data in real-world is error-prone, which results in inaccurate results when performing network analysis or modeling such as node classification and link prediction on these flawed networks. In this paper, we target at reconstructing a reliable network from a flawed network, named as network enhancement. Specifically, network enhancement aims to both detect the noisy links which are observed in the network but should not exist in the real world, and predict the missing links that indeed exist in the real world yet being unobserved in the network. Different from existing works that calculate a unified score to measure the above two kinds of links, we propose E-Net, an end-to-end graph neural network model, to leverage the mutual influence of the two tasks to achieve both the goals more effectively. Because on one hand, detecting noisy links can benefit the performance of predicting missing links; and on the other hand, predicting missing links can provide indirect supervision for detecting noisy links when the labels of the noisy links are unavailable. The experimental results on several datasets show that the proposed model obtains significant improvement for predicting missing links and detecting noisy links.Keywords
Funding Information
- National Natural Science Foundation of China (61702447)
- Fundamental Research Funds for the Central Universities
- Major Scientific Project of Zhejiang Laboratory (2020MC0AE01)
- a research funding from HIKVISION Inc.
- National Key Research and Development Project of China (2018AAA0101900)
- Zhejiang University Robotics Institute Yuyao Project (K12001)
- Fundamental Research Funds for the Central Universities Zhejiang University New Generation Industrial Control System NGICS Platform
This publication has 19 references indexed in Scilit:
- Robust Network Enhancement from Flawed NetworksIEEE Transactions on Knowledge and Data Engineering, 2020
- LookCom: Learning Optimal Network for Community DetectionIEEE Transactions on Knowledge and Data Engineering, 2020
- Understanding Default Behavior in Online Lending2019
- GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders2018
- Network enhancement as a general method to denoise weighted biological networksNature Communications, 2018
- Geometric Deep Learning: Going beyond Euclidean dataIEEE Signal Processing Magazine, 2017
- node2vec2016
- Human-level control through deep reinforcement learningNature, 2015
- DeepWalk2014
- The link‐prediction problem for social networksJournal of the American Society for Information Science and Technology, 2007