# Augmentation-Free Graph Contrastive Learning with Performance Guarantee

arXiv: https://arxiv.org/abs/2204.04874 · HTML: https://mlsanity.com/paper/2204.04874/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 61 references that are in the map.
- First posted on arXiv 11 Apr 2022.

## Builds on (most cited first, 30 of 45)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [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)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Geom-GCN: Geometric Graph Convolutional Networks](https://mlsanity.com/paper/2002.05287/) (2020)
- [Contrastive Multi-View Representation Learning on Graphs](https://mlsanity.com/paper/2006.05582/) (2020)
- [On Variational Bounds of Mutual Information](https://mlsanity.com/paper/1905.06922/) (2019)
- [A Survey on Contrastive Self-supervised Learning](https://mlsanity.com/paper/2011.00362/) (2020)
- [Deep Graph Contrastive Representation Learning](https://mlsanity.com/paper/2006.04131/) (2020)
- [A Theoretical Analysis of Contrastive Unsupervised Representation Learning](https://mlsanity.com/paper/1902.09229/) (2019)
- [Graph Contrastive Learning with Adaptive Augmentation](https://mlsanity.com/paper/2010.14945/) (2020)
- [f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization](https://mlsanity.com/paper/1606.00709/) (2016)
- [GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training](https://mlsanity.com/paper/2006.09963/) (2020)
- [Beyond Low-frequency Information in Graph Convolutional Networks](https://mlsanity.com/paper/2101.00797/) (2021)
- [Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss](https://mlsanity.com/paper/2106.04156/) (2021)
- [Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods](https://mlsanity.com/paper/2110.14446/) (2021)
- [Revisiting Graph Neural Networks: All We Have is Low-Pass Filters](https://mlsanity.com/paper/1905.09550/) (2019)

## Built on by (most cited first, 16 of 16)

- [GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner](https://mlsanity.com/paper/2304.04779/) (2023)
- [Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?](https://mlsanity.com/paper/2306.01323/) (2023)
- [Spectral Augmentation for Self-Supervised Learning on Graphs](https://mlsanity.com/paper/2210.00643/) (2022)
- [Self-supervised Heterogeneous Graph Pre-training Based on Structural Clustering](https://mlsanity.com/paper/2210.10462/) (2022)
- [Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative](https://mlsanity.com/paper/2210.03801/) (2022)
- [Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding](https://mlsanity.com/paper/2205.14814/) (2022)
- [COIN: Co-Cluster Infomax for Bipartite Graphs](https://mlsanity.com/paper/2206.00006/) (2022)
- [Graph Contrastive Learning with Personalized Augmentation](https://mlsanity.com/paper/2209.06560/) (2022)
- [Single-Pass Contrastive Learning Can Work for Both Homophilic and Heterophilic Graph](https://mlsanity.com/paper/2211.10890/) (2022)
- [Code Recommendation for Open Source Software Developers](https://mlsanity.com/paper/2210.08332/) (2022)
- [Generative Subgraph Contrast for Self-Supervised Graph Representation Learning](https://mlsanity.com/paper/2207.11996/) (2022)
- [Towards Generalizable Graph Contrastive Learning: An Information Theory Perspective](https://mlsanity.com/paper/2211.10929/) (2022)
- [Multi-View Graph Representation Learning Beyond Homophily](https://mlsanity.com/paper/2304.07509/) (2023)
- [Self-Supervised Node Representation Learning via Node-to-Neighbourhood Alignment](https://mlsanity.com/paper/2302.04626/) (2023)
- [NESS: Node Embeddings from Static SubGraphs](https://mlsanity.com/paper/2303.08958/) (2023)
- [A Fused Gromov-Wasserstein Approach to Subgraph Contrastive Learning](https://mlsanity.com/paper/2502.20885/) (2025)

## Abstract (arXiv)

Graph contrastive learning (GCL) is the most representative and prevalent self-supervised learning approach for graph-structured data. Despite its remarkable success, existing GCL methods highly rely on an augmentation scheme to learn the representations invariant across different augmentation views. In this work, we revisit such a convention in GCL through examining the effect of augmentation techniques on graph data via the lens of spectral theory. We found that graph augmentations preserve the low-frequency components and perturb the middle-and high-frequency components of the graph, which contributes to the success of GCL algorithms on homophilic graphs but hinder its application on heterophilic graphs, due to the high-frequency preference of heterophilic data. Motivated by this, we propose a novel, theoretically-principled, and augmentation-free GCL method, named AF-GCL, that (1) leverages the features aggregated by Graph Neural Network to construct the self-supervision signal instead of augmentations and therefore (2) is less sensitive to the graph homophily degree. Theoretically, We present the performance guarantee for AF-GCL as well as an analysis for understanding the efficacy of AF-GCL. Extensive experiments on 14 benchmark datasets with varying degrees of heterophily show that AF-GCL presents competitive or better performance on homophilic graphs and outperforms all existing state-of-the-art GCL methods on heterophilic graphs with significantly less computational overhead.