Piecewise Constant Spectral Graph Neural Network
Not on the map. Why?
Abstract (arXiv)
Graph Neural Networks (GNNs) have achieved significant success across various domains by leveraging graph structures in data. Existing spectral GNNs, which use low-degree polynomial filters to capture graph spectral properties, may not fully identify the graph's spectral characteristics because of the polynomial's small degree. However, increasing the polynomial degree is computationally expensive and beyond certain thresholds leads to performance plateaus or degradation. In this paper, we introduce the Piecewise Constant Spectral Graph Neural Network(PieCoN) to address these challenges. PieCoN combines constant spectral filters with polynomial filters to provide a more flexible way to leverage the graph structure. By adaptively partitioning the spectrum into intervals, our approach increases the range of spectral properties that can be effectively learned. Experiments on nine benchmark datasets, including both homophilic and heterophilic graphs, demonstrate that PieCoN is particularly effective on heterophilic datasets, highlighting its potential for a wide range of applications.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 32 of its 43 references that are in the map. First posted on arXiv 7 May 2025.
Builds on
32 of 43 references.
References · 32
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2018How Powerful are Graph Neural Networks?cited by 4,393
- 2017Neural Message Passing for Quantum Chemistrycited by 3,487
- 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
- 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
- 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
- 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,138
- 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
- 2020Simple and Deep Graph Convolutional Networkscited by 860
- 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 595
20 more
- 2017Graph Signal Processing: Overview, Challenges and Applicationscited by 413
- 2018Session-based Recommendation with Graph Neural Networkscited by 312
- 2021BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximationcited by 195
- 2022Sign and Basis Invariant Networks for Spectral Graph Representation Learningcited by 179
- 2022How Powerful are Spectral Graph Neural Networkscited by 169
- 2023Specformer: Spectral Graph Neural Networks Meet Transformerscited by 102
- 2022Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisitedcited by 87
- 2020Molecular graph generation with Graph Neural Networkscited by 80
- 2019LanczosNet: Multi-Scale Deep Graph Convolutional Networkscited by 73
- 2023FAENet: Frame Averaging Equivariant GNN for Materials Modelingcited by 73
- 2023A Fractional Graph Laplacian Approach to Oversmoothingcited by 45
- 2023Graph Neural Networks with Learnable and Optimal Polynomial Basescited by 36
- 2024How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashingcited by 24
- 2022Node-oriented Spectral Filtering for Graph Neural Networkscited by 17
- 2023Resurrecting Label Propagation for Graphs with Heterophily and Label Noisecited by 12
- 2024Gegenbauer Graph Neural Networks for Time-varying Signal Reconstructioncited by 12
- 2023Graph Neural Networks with Diverse Spectral Filteringcited by 9
- 2021Maximizing Influence with Graph Neural Networkscited by 8
- 2021A Piece-wise Polynomial Filtering Approach for Graph Neural Networkscited by 7
- 2024Improving Expressive Power of Spectral Graph Neural Networks with Eigenvalue Correctioncited by 5
Built on by
Citing papers per year: 2026: 1.
1 paper.