# Beyond Localized Graph Neural Networks: An Attributed Motif Regularization Framework

arXiv: https://arxiv.org/abs/2009.05197 · HTML: https://mlsanity.com/paper/2009.05197/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2020.

## Built on by (most cited first, 10 of 10)

- [Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passing](https://mlsanity.com/paper/2102.08786/) (2021)
- [HINormer: Representation Learning On Heterogeneous Information Networks with Graph Transformer](https://mlsanity.com/paper/2302.11329/) (2023)
- [CogDL: A Comprehensive Library for Graph Deep Learning](https://mlsanity.com/paper/2103.00959/) (2021)
- [Adaptive Fault Tolerance Mechanisms of Large Language Models in Cloud Computing Environments](https://mlsanity.com/paper/2503.12228/) (2025)
- [Research on Large Language Model Cross-Cloud Privacy Protection and Collaborative Training based on Federated Learning](https://mlsanity.com/paper/2503.12226/) (2025)
- [Motif Graph Neural Network](https://mlsanity.com/paper/2112.14900/) (2021)
- [Research on Cloud Platform Network Traffic Monitoring and Anomaly Detection System based on Large Language Models](https://mlsanity.com/paper/2504.17807/) (2025)
- [Multi-modal Relational Item Representation Learning for Inferring Substitutable and Complementary Items](https://mlsanity.com/paper/2507.22268/) (2025)
- [Automatic Self-supervised Learning for Social Recommendations](https://mlsanity.com/paper/2412.18735/) (2024)
- [SafeImpute: Reliable Clinical Data Imputation via Conformal Selection](https://mlsanity.com/paper/2607.05613/) (2026)

## Abstract (arXiv)

We present InfoMotif, a new semi-supervised, motif-regularized, learning framework over graphs. We overcome two key limitations of message passing in popular graph neural networks (GNNs): localization (a k-layer GNN cannot utilize features outside the k-hop neighborhood of the labeled training nodes) and over-smoothed (structurally indistinguishable) representations. We propose the concept of attributed structural roles of nodes based on their occurrence in different network motifs, independent of network proximity. Two nodes share attributed structural roles if they participate in topologically similar motif instances over co-varying sets of attributes. Further, InfoMotif achieves architecture independence by regularizing the node representations of arbitrary GNNs via mutual information maximization. Our training curriculum dynamically prioritizes multiple motifs in the learning process without relying on distributional assumptions in the underlying graph or the learning task. We integrate three state-of-the-art GNNs in our framework, to show significant gains (3-10% accuracy) across six diverse, real-world datasets. We see stronger gains for nodes with sparse training labels and diverse attributes in local neighborhood structures.