Can I read Stable Prediction on Graphs with Agnostic Distribution Shift on EtoBox?

Stable Prediction on Graphs with Agnostic Distribution Shift by Zhang, Shengyu; Kuang, Kun; Qiu, Jiezhong; Yu, Jin; Zhao, Zhou; Yang, Hongxia; Zhang, Zhongfei; Wu, Fei is a scholarly article available to read on EtoBox.

What is Stable Prediction on Graphs with Agnostic Distribution Shift about?

Graph is a flexible and effective tool to represent complex structures in practice and graph neural networks (GNNs) have been shown to be effective on various graph tasks with randomly separated training and testing data. In real applications, however, the distribution of training graph might be different from that of the test one (e.g., users' interactions on the user-item training graph and their actual preference on items, i.e., testing environment, are known to have inconsistencies in recommender systems). Moreover, the distribution of test data is always agnostic when GNNs are trained. Hence, we are facing the agnostic distribution shift between training and testing on graph learning, which would lead to unstable inference of traditional GNNs across different test environments. To address this problem, we propose a novel stable prediction framework for GNNs, which permits both locally and globally stable learning and prediction on graphs. In particular, since each node is partially represented by its neighbors in GNNs, we propose to capture the stable properties for each node (locally stable) by re-weighting the information propagation/aggregation processes. For global stabili

Author

Zhang, Shengyu; Kuang, Kun; Qiu, Jiezhong; Yu, Jin; Zhao, Zhou; Yang, Hongxia; Zhang, Zhongfei; Wu, Fei

Published

2021

Language

EN