Simple Yet Effective Self-Supervised Graph Learning with Inverse Laplacian
Open Access
Abstract
Self-supervised learning (SSL) has become a powerful paradigm for graph representation learning. However, most existing methods operate in the graph topology domain and rely on complex data augmentations or contrastive objectives, which constrain them to local structural information and hinder the effective modeling of global or long-range dependencies. In this work, we propose the inverse-filter graph neural network (IF-GNN), an alternative spectral-based method for SSL. IF-GNN employs a fixed spectral operator as a low-pass inverse filter, enabling efficient and label-free node representation learning in the spectral domain. The inverse filter can be interpreted as an infinite-order polynomial filter, allowing the model to aggregate high-order neighborhood information without layer stacking or explicit message passing. This design helps alleviate over-smoothing by avoiding repeated feature averaging and improves the interpretability of spectral SSL models. Extensive experiments on multiple benchmark datasets demonstrate that IF-GNN achieves competitive or superior performance compared to both spectral and self-supervised baselines, establishing inverse filtering as a new and effective spectral SSL paradigm.
Keywords
Funding Information
- National Natural Science Foundation of China (11901094)
- Chinese Academy of Sciences (2025QYB015)
This publication has 38 references indexed in Scilit:
- Generative data-physics fusion for hierarchical reliability assessmentReliability Engineering & System Safety, 2026
- Robot learning in the era of foundation models: a surveyNeurocomputing, 2025
- A unified approach to Krylov subspace methods for solving linear systemsNumerical Algorithms, 2023
- Unexpected interest recommender system with graph neural networkComplex & Intelligent Systems, 2022
- Graph Self-Supervised Learning: A SurveyIEEE Transactions on Knowledge and Data Engineering, 2022
- Self-Supervised Learning on Graphs: Contrastive, Generative, or PredictiveIEEE Transactions on Knowledge and Data Engineering, 2021
- A graph CNN-LSTM neural network for short and long-term traffic forecasting based on trajectory dataTransportation Research Part C: Emerging Technologies, 2020
- Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and ForecastingIEEE Transactions on Intelligent Transportation Systems, 2019
- Leveraging Domain Context for Question Answering Over Knowledge GraphData Science and Engineering, 2019
- Practical High-Quality Electrostatic Potential Surfaces for Drug Discovery Using a Graph-Convolutional Deep Neural NetworkJournal of Medicinal Chemistry, 2019