Improving Signed Propagation for Graph Neural Networks in Multi-Class Environments
Message-passing Graph Neural Networks (GNNs), which collect information from adjacent nodes achieve dismal performance on heterophilic graphs. Various schemes have been proposed to solve this problem, and propagating signed information on heterophilic edges has gained great attention. Recently, some works provided theoretical analysis that signed propagation always leads to performance improvement under a binary class scenario. However, we notice that prior analyses do not align well with multi-class benchmark datasets. This paper provides a new understanding of signed propagation for multi-class scenarios and points out two drawbacks in terms of message-passing and parameter update: (1) Message-passing: if two nodes belong to different classes but have a high similarity, signed propagation can decrease the separability. (2) Parameter update: the prediction uncertainty (e.g., conflict evidence) of signed neighbors increases during training, which can impede the stability of the algorithm. Based on the observation, we introduce two novel strategies for improving signed propagation under multi-class graphs. The proposed scheme combines calibration to secure robustness while reducing uncertainty. We show the efficacy of our theorem through extensive experiments on six benchmark graph datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph Neural NetworkMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Better Not to Propagate: Understanding Edge Uncertainty and Over-smoothing in Signed Graph Neural Networks
Traditional Graph Neural Networks (GNNs) rely on network homophily, which can lead to performance degradation due to over-smoothing in many real-world heterophily scenarios. Recent studies analyze the smoothing effect (s…
BlockingSecuring Multi-Agent Systems Against Corruptions via Node Contribution Backpropagation
Multi-Agent Systems (MAS) have become a prevalent paradigm for Large Language Model (LLM) applications. However, the complex multi-agent design in MAS introduces unique trustworthiness concerns: adversarial agents can in…
Text2Graph: Combining Lightweight LLMs and GNNs for Efficient Text Classification in Label-Scarce Scenarios
Large Language Models (LLMs) have become effective zero-shot classifiers, but their high computational requirements and environmental costs limit their practicality for large-scale annotation in high-performance computin…
Graph ClassificationGraph Neural NetworkText ClassificationSentiment AnalysisOversmoothing as Loss of Sign: Towards Structural Balance in Graph Neural Networks
Oversmoothing is a common issue in graph neural networks (GNNs), where node representations become excessively homogeneous as the number of layers increases, resulting in degraded performance. Various strategies have bee…
Improved propagation models for lte path loss prediction in urban & suburban Ghana
To maximize the benefits of LTE cellular networks, careful and proper planning is needed. This requires the use of accurate propagation models to quantify the path loss required for base station deployment. Deployed LTE …