HyperSMOTE: A Hypergraph-based Oversampling Approach for Imbalanced Node Classifications

TL;DR

HyperSMOTE introduces a hypergraph-based oversampling method that synthesizes and integrates minority class nodes to address class imbalance in hypergraph learning, improving classification accuracy across multiple datasets.

Contribution

The paper presents HyperSMOTE, a novel oversampling technique specifically designed for hypergraphs, combining node synthesis and adaptive integration to enhance minority class representation.

Findings

Achieves an average accuracy improvement of around 3% on multiple datasets.

Effectively synthesizes and integrates minority class nodes in hypergraphs.

Demonstrates superior performance over existing methods like GraphSMOTE.

Abstract

Hypergraphs are increasingly utilized in both unimodal and multimodal data scenarios due to their superior ability to model and extract higher-order relationships among nodes, compared to traditional graphs. However, current hypergraph models are encountering challenges related to imbalanced data, as this imbalance can lead to biases in the model towards the more prevalent classes. While the existing techniques, such as GraphSMOTE, have improved classification accuracy for minority samples in graph data, they still fall short when addressing the unique structure of hypergraphs. Inspired by SMOTE concept, we propose HyperSMOTE as a solution to alleviate the class imbalance issue in hypergraph learning. This method involves a two-step process: initially synthesizing minority class nodes, followed by the nodes integration into the original hypergraph. We synthesize new nodes based on samples from minority classes and their neighbors. At the same time, in order to solve the problem on integrating the new node into the hypergraph, we train a decoder based on the original hypergraph incidence matrix to adaptively associate the augmented node to hyperedges. We conduct extensive evaluation on multiple single-modality datasets, such as Cora, Cora-CA and Citeseer, as well as multimodal conversation dataset MELD to verify the effectiveness of HyperSMOTE, showing an average performance gain of 3.38% and 2.97% on accuracy, respectively.