Position-aware Structure Learning for Graph Topology-imbalance by Relieving Under-reaching and Over-squashing

by   Qingyun Sun, et al.
Beihang University
University of Illinois at Chicago

Topology-imbalance is a graph-specific imbalance problem caused by the uneven topology positions of labeled nodes, which significantly damages the performance of GNNs. What topology-imbalance means and how to measure its impact on graph learning remain under-explored. In this paper, we provide a new understanding of topology-imbalance from a global view of the supervision information distribution in terms of under-reaching and over-squashing, which motivates two quantitative metrics as measurements. In light of our analysis, we propose a novel position-aware graph structure learning framework named PASTEL, which directly optimizes the information propagation path and solves the topology-imbalance issue in essence. Our key insight is to enhance the connectivity of nodes within the same class for more supervision information, thereby relieving the under-reaching and over-squashing phenomena. Specifically, we design an anchor-based position encoding mechanism, which better incorporates relative topology position and enhances the intra-class inductive bias by maximizing the label influence. We further propose a class-wise conflict measure as the edge weights, which benefits the separation of different node classes. Extensive experiments demonstrate the superior potential and adaptability of PASTEL in enhancing GNNs' power in different data annotation scenarios.


Topology-Imbalance Learning for Semi-Supervised Node Classification

The class imbalance problem, as an important issue in learning node repr...

Hyperbolic Geometric Graph Representation Learning for Hierarchy-imbalance Node Classification

Learning unbiased node representations for imbalanced samples in the gra...

TopoImb: Toward Topology-level Imbalance in Learning from Graphs

Graph serves as a powerful tool for modeling data that has an underlying...

Exploiting Path Information for Anchor Based Graph Neural Network

Learning node representation that incorporating information from graph s...

Topological Augmentation for Class-Imbalanced Node Classification

Class imbalance is prevalent in real-world node classification tasks and...

Structural Imbalance Aware Graph Augmentation Learning

Graph machine learning (GML) has made great progress in node classificat...

Semantic-aware Node Synthesis for Imbalanced Heterogeneous Information Networks

Heterogeneous graph neural networks (HGNNs) have exhibited exceptional e...

Please sign up or login with your details

Forgot password? Click here to reset