ECGN: A CLUSTER-AWARE APPROACH TO GRAPH NEURAL NETWORKS FOR IMBALANCED CLASSIFICATION.

Bishal Thapaliya, Anh Nguyen, Yao Lu, Tian Xie, Igor Grudetskyi, Fudong Lin, Antonios Valkanas, Jingyu Liu, Deepayan Chakrabarti, Bilel Fehri

Keywords: Graph Neural Networks, Uniform Node Updates Issue, Imbalanced Node Classification, Cluster Specific Updates, Synthetic Node Generation

TL;DR: ECGN improves graph node classification by addressing class imbalance and clustering. It learns cluster-specific aggregations and generates synthetic nodes to enhance decision boundaries using novel technique, achieving up to 11% better accuracy.

Abstract:

Classifying nodes in a graph is a common problem. The ideal classifier must
adapt to any imbalances in the class distribution. It must also use information in
the clustering structure of real-world graphs. Existing Graph Neural Networks
(GNNs) have not addressed both problems together. We propose the Enhanced
Cluster-aware Graph Network (ECGN), a novel method that addresses these is-
sues by integrating cluster-specific training with synthetic node generation. Unlike
traditional GNNs that apply the same node update process for all nodes, ECGN
learns different aggregations for different clusters. We also use the clusters to gen-
erate new minority-class nodes in a way that helps clarify the inter-class decision
boundary. By combining cluster-aware embeddings with a global integration step,
ECGN enhances the quality of the resulting node embeddings. Our method works
with any underlying GNN and any cluster generation technique. Experimental
results show that ECGN consistently outperforms its closest competitors by up to
11% on some widely-studied benchmark datasets. The GitHub implementation
for implementation and replication is publicly available on https://github.com/anonymous753341/ECGN.

Primary Area: learning on graphs and other geometries & topologies

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 5083