[KDD 2022] Implementation of "Feature Overcorrelation in Deep Graph Neural Networks: A New Perspective"
Code will be updated soon. Stay Tuned :)
Oversmoothing has been identified as one of the key issues which limit the performance of deep GNNs. In this work, we propose a new perspective to look at the performance degradation of deep GNNs, i.e., feature overcorrelation. Through empirical and theoretical study on this matter, we demonstrate the existence of feature overcorrelation in deeper GNNs and reveal potential reasons leading to this issue. To reduce the feature correlation, we propose a general framework DeCorr which can encourage GNNs to encode less redundant information.
For more information, you can take a look at the paper.
If you find this repo to be useful, please cite our paper. Thank you.
@inproceedings{jin2022feature,
author = {Wei Jin and Xiaorui Liu and Yao Ma and Charu Aggarwal and Jiliang Tang},
booktitle = {Proceedings of the 28th {ACM} {SIGKDD} Conference on
Knowledge Discovery and Data Mining},
title = {Feature Overcorrelation in Deep Graph Neural Networks: A New Perspective},
year = {2022}
}