# Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2212.10822 · HTML: https://mlsanity.com/paper/2212.10822/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 81 references that are in the map.
- First posted on arXiv 21 Dec 2022.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Spectral Networks and Locally Connected Networks on Graphs](https://mlsanity.com/paper/1312.6203/) (2013)
- [Geometric deep learning: going beyond Euclidean data](https://mlsanity.com/paper/1611.08097/) (2016)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Simple and Deep Graph Convolutional Networks](https://mlsanity.com/paper/2007.02133/) (2020)
- [Geom-GCN: Geometric Graph Convolutional Networks](https://mlsanity.com/paper/2002.05287/) (2020)
- [GraphSAINT: Graph Sampling Based Inductive Learning Method](https://mlsanity.com/paper/1907.04931/) (2019)
- [Adaptive Universal Generalized PageRank Graph Neural Network](https://mlsanity.com/paper/2006.07988/) (2020)
- [Multi-scale Attributed Node Embedding](https://mlsanity.com/paper/1909.13021/) (2019)
- [Geometric deep learning on graphs and manifolds using mixture model CNNs](https://mlsanity.com/paper/1611.08402/) (2016)
- [Beyond Low-frequency Information in Graph Convolutional Networks](https://mlsanity.com/paper/2101.00797/) (2021)
- [Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods](https://mlsanity.com/paper/2110.14446/) (2021)
- [PairNorm: Tackling Oversmoothing in GNNs](https://mlsanity.com/paper/1909.12223/) (2019)
- [Revisiting Graph Neural Networks: All We Have is Low-Pass Filters](https://mlsanity.com/paper/1905.09550/) (2019)
- [Graph Neural Networks with Heterophily](https://mlsanity.com/paper/2009.13566/) (2020)
- [BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation](https://mlsanity.com/paper/2106.10994/) (2021)
- [Revisiting Heterophily For Graph Neural Networks](https://mlsanity.com/paper/2210.07606/) (2022)
- [How to learn a graph from smooth signals](https://mlsanity.com/paper/1601.02513/) (2016)
- [Graph Wavelet Neural Network](https://mlsanity.com/paper/1904.07785/) (2019)
- [Non-Local Graph Neural Networks](https://mlsanity.com/paper/2005.14612/) (2020)

## Built on by (most cited first, 19 of 19)

- [Feature Transportation Improves Graph Neural Networks](https://mlsanity.com/paper/2307.16092/) (2023)
- [ReactZyme: A Benchmark for Enzyme-Reaction Prediction](https://mlsanity.com/paper/2408.13659/) (2024)
- [When Heterophily Meets Heterogeneous Graphs: Latent Graphs Guided Unsupervised Representation Learning](https://mlsanity.com/paper/2409.00687/) (2024)
- [Domain-adaptive Message Passing Graph Neural Network](https://mlsanity.com/paper/2308.16470/) (2023)
- [What Is Missing In Homophily? Disentangling Graph Homophily For Graph Neural Networks](https://mlsanity.com/paper/2406.18854/) (2024)
- [LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework](https://mlsanity.com/paper/2405.13902/) (2024)
- [When Do Graph Neural Networks Help with Node Classification? Investigating the Impact of Homophily Principle on Node Distinguishability](https://mlsanity.com/paper/2304.14274/) (2023)
- [Homophily-Related: Adaptive Hybrid Graph Filter for Multi-View Graph Clustering](https://mlsanity.com/paper/2401.02682/) (2024)
- [Representation Learning on Heterophilic Graph with Directional Neighborhood Attention](https://mlsanity.com/paper/2403.01475/) (2024)
- [AGS-GNN: Attribute-guided Sampling for Graph Neural Networks](https://mlsanity.com/paper/2405.15218/) (2024)
- [Graph Contrastive Learning under Heterophily via Graph Filters](https://mlsanity.com/paper/2303.06344/) (2023)
- [Effective Protein-Protein Interaction Exploration with PPIretrieval](https://mlsanity.com/paper/2402.03675/) (2024)
- [EnzymeFlow: Generating Reaction-specific Enzyme Catalytic Pockets through Flow Matching and Co-Evolutionary Dynamics](https://mlsanity.com/paper/2410.00327/) (2024)
- [Revealing the Pitfalls and Re-Evaluating the Advancement of Heterophilic Graph Learning](https://mlsanity.com/paper/2409.05755/) (2024)
- [Flexible Diffusion Scopes with Parameterized Laplacian for Heterophilic Graph Learning](https://mlsanity.com/paper/2409.09888/) (2024)
- [On Addressing the Limitations of Graph Neural Networks](https://mlsanity.com/paper/2306.12640/) (2023)
- [Flexible Infinite-Width Graph Convolutional Neural Networks](https://mlsanity.com/paper/2402.06525/) (2024)
- [Novel Approaches to Artificial Intelligence Development Based on the Nearest Neighbor Method](https://mlsanity.com/paper/2508.18953/) (2025)
- [P2GNN: Two Prototype Sets to boost GNN Performance](https://mlsanity.com/paper/2603.09195/) (2026)

## Abstract (arXiv)

The core operation of current Graph Neural Networks (GNNs) is the aggregation enabled by the graph Laplacian or message passing, which filters the neighborhood information of nodes. Though effective for various tasks, in this paper, we show that they are potentially a problematic factor underlying all GNN models for learning on certain datasets, as they force the node representations similar, making the nodes gradually lose their identity and become indistinguishable. Hence, we augment the aggregation operations with their dual, i.e. diversification operators that make the node more distinct and preserve the identity. Such augmentation replaces the aggregation with a two-channel filtering process that, in theory, is beneficial for enriching the node representations. In practice, the proposed two-channel filters can be easily patched on existing GNN methods with diverse training strategies, including spectral and spatial (message passing) methods. In the experiments, we observe desired characteristics of the models and significant performance boost upon the baselines on 9 node classification tasks.