# Graph convolutions that can finally model local structure

arXiv: https://arxiv.org/abs/2011.15069 · HTML: https://mlsanity.com/paper/2011.15069/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2020.

## Built on by (most cited first, 30 of 31)

- [Do Transformers Really Perform Bad for Graph Representation?](https://mlsanity.com/paper/2106.05234/) (2021)
- [Nested Graph Neural Networks](https://mlsanity.com/paper/2110.13197/) (2021)
- [Meta-Transformer: A Unified Framework for Multimodal Learning](https://mlsanity.com/paper/2307.10802/) (2023)
- [Global Self-Attention as a Replacement for Graph Convolution](https://mlsanity.com/paper/2108.03348/) (2021)
- [How Powerful are K-hop Message Passing Graph Neural Networks](https://mlsanity.com/paper/2205.13328/) (2022)
- [One Transformer Can Understand Both 2D & 3D Molecular Data](https://mlsanity.com/paper/2210.01765/) (2022)
- [GRPE: Relative Positional Encoding for Graph Transformer](https://mlsanity.com/paper/2201.12787/) (2022)
- [Your Transformer May Not be as Powerful as You Expect](https://mlsanity.com/paper/2205.13401/) (2022)
- [Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passing](https://mlsanity.com/paper/2102.08786/) (2021)
- [Autobahn: Automorphism-based Graph Neural Nets](https://mlsanity.com/paper/2103.01710/) (2021)
- [The Expressive Power of Graph Neural Networks: A Survey](https://mlsanity.com/paper/2308.08235/) (2023)
- [A New Perspective on the Effects of Spectrum in Graph Neural Networks](https://mlsanity.com/paper/2112.07160/) (2021)
- [Highly Accurate Quantum Chemical Property Prediction with Uni-Mol+](https://mlsanity.com/paper/2303.16982/) (2023)
- [GraphGPT: Generative Pre-trained Graph Eulerian Transformer](https://mlsanity.com/paper/2401.00529/) (2023)
- [Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers](https://mlsanity.com/paper/2402.04538/) (2024)
- [Graph Propagation Transformer for Graph Representation Learning](https://mlsanity.com/paper/2305.11424/) (2023)
- [Improving the Expressiveness of K-hop Message-Passing GNNs by Injecting Contextualized Substructure Information](https://mlsanity.com/paper/2406.19244/) (2024)
- [GeoMFormer: A General Architecture for Geometric Molecular Representation Learning](https://mlsanity.com/paper/2406.16853/) (2024)
- [Equilibrium Aggregation: Encoding Sets via Optimization](https://mlsanity.com/paper/2202.12795/) (2022)
- [GEM-2: Next Generation Molecular Property Prediction Network by Modeling Full-range Many-body Interactions](https://mlsanity.com/paper/2208.05863/) (2022)
- [Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering](https://mlsanity.com/paper/2305.06102/) (2023)
- [Demystifying Higher-Order Graph Neural Networks](https://mlsanity.com/paper/2406.12841/) (2024)
- [RAN-GNNs: breaking the capacity limits of graph neural networks](https://mlsanity.com/paper/2103.15565/) (2021)
- [Enhancing Molecular Property Predictions by Learning from Bond Modelling and Interactions](https://mlsanity.com/paper/2603.00568/) (2026)
- [HelixADMET: a robust and endpoint extensible ADMET system incorporating self-supervised knowledge transfer](https://mlsanity.com/paper/2205.08055/) (2022)
- [GNN Applied to Ego-nets for Friend Suggestions](https://mlsanity.com/paper/2412.11888/) (2024)
- [FloydNet: A Learning Paradigm for Global Relational Reasoning](https://mlsanity.com/paper/2601.19094/) (2026)
- [Rethinking the Power of Graph Canonization in Graph Representation Learning with Stability](https://mlsanity.com/paper/2309.00738/) (2023)
- [Sampling Foundational Transformer: A Theoretical Perspective](https://mlsanity.com/paper/2408.05822/) (2024)
- [Exact Subgraph Isomorphism Network with Mixed L0,2 Norm Constraint for Predictive Graph Mining](https://mlsanity.com/paper/2509.21699/) (2025)

## Abstract (arXiv)

Despite quick progress in the last few years, recent studies have shown that modern graph neural networks can still fail at very simple tasks, like detecting small cycles. This hints at the fact that current networks fail to catch information about the local structure, which is problematic if the downstream task heavily relies on graph substructure analysis, as in the context of chemistry. We propose a very simple correction to the now standard GIN convolution that enables the network to detect small cycles with nearly no cost in terms of computation time and number of parameters. Tested on real life molecule property datasets, our model consistently improves performance on large multi-tasked datasets over all baselines, both globally and on a per-task setting.