# Neighbor Contrastive Learning on Learnable Graph Augmentation

arXiv: https://arxiv.org/abs/2301.01404 · HTML: https://mlsanity.com/paper/2301.01404/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jan 2023.

## Built on by (most cited first, 25 of 25)

- [CONVERT:Contrastive Graph Clustering with Reliable Augmentation](https://mlsanity.com/paper/2308.08963/) (2023)
- [Graph Learning under Distribution Shifts: A Comprehensive Survey on Domain Adaptation, Out-of-distribution, and Continual Learning](https://mlsanity.com/paper/2402.16374/) (2024)
- [Learn Beneficial Noise as Graph Augmentation](https://mlsanity.com/paper/2505.19024/) (2025)
- [Leveraging Contrastive Learning for Enhanced Node Representations in Tokenized Graph Transformers](https://mlsanity.com/paper/2406.19258/) (2024)
- [Graph Contrastive Learning via Cluster-refined Negative Sampling for Semi-supervised Text Classification](https://mlsanity.com/paper/2410.18130/) (2024)
- [Community-Invariant Graph Contrastive Learning](https://mlsanity.com/paper/2405.01350/) (2024)
- [HyperGCL: Multi-Modal Graph Contrastive Learning via Learnable Hypergraph Views](https://mlsanity.com/paper/2502.13277/) (2025)
- [KAT-Coder-V2.5 Technical Report](https://mlsanity.com/paper/2607.05471/) (2026)
- [Virtual Nodes Can Help: Tackling Distribution Shifts in Federated Graph Learning](https://mlsanity.com/paper/2412.19229/) (2024)
- [RCoCo: Contrastive Collective Link Prediction across Multiplex Network in Riemannian Space](https://mlsanity.com/paper/2403.01864/) (2024)
- [Unifying Dual-Space Embedding for Entity Alignment via Contrastive Learning](https://mlsanity.com/paper/2412.05028/) (2024)
- [Hybrid-Collaborative Augmentation and Contrastive Sample Adaptive-Differential Awareness for Robust Attributed Graph Clustering](https://mlsanity.com/paper/2510.02731/) (2025)
- [Edge Contrastive Learning: An Augmentation-Free Graph Contrastive Learning Model](https://mlsanity.com/paper/2412.11075/) (2024)
- [SE-GCL: An Event-Based Simple and Effective Graph Contrastive Learning for Text Representation](https://mlsanity.com/paper/2412.11652/) (2024)
- [AS-GCL: Asymmetric Spectral Augmentation on Graph Contrastive Learning](https://mlsanity.com/paper/2502.13525/) (2025)
- [Clustering-Oriented Generative Attribute Graph Imputation](https://mlsanity.com/paper/2507.19085/) (2025)
- [Robust Anomaly Detection Under Normality Distribution Shift in Dynamic Graphs](https://mlsanity.com/paper/2509.17400/) (2025)
- [RABot: Reinforcement-Guided Graph Augmentation for Imbalanced and Noisy Social Bot Detection](https://mlsanity.com/paper/2602.21749/) (2026)
- [LAC: Graph Contrastive Learning with Learnable Augmentation in Continuous Space](https://mlsanity.com/paper/2410.15355/) (2024)
- [GNN-Transformer Cooperative Architecture for Trustworthy Graph Contrastive Learning](https://mlsanity.com/paper/2412.16218/) (2024)
- [Enhancing Contrastive Link Prediction With Edge Balancing Augmentation](https://mlsanity.com/paper/2508.14808/) (2025)
- [Dual-Kernel Graph Community Contrastive Learning](https://mlsanity.com/paper/2511.08287/) (2025)
- [Explainable Graph Representation Learning via Graph Pattern Analysis](https://mlsanity.com/paper/2512.04530/) (2025)
- [Simple Network Graph Comparative Learning](https://mlsanity.com/paper/2601.10150/) (2026)
- [A Unified Perspective for Learning Graph Representations Across Multi-Level Abstractions](https://mlsanity.com/paper/2605.12685/) (2026)

## Abstract (arXiv)

Recent years, graph contrastive learning (GCL), which aims to learn representations from unlabeled graphs, has made great progress. However, the existing GCL methods mostly adopt human-designed graph augmentations, which are sensitive to various graph datasets. In addition, the contrastive losses originally developed in computer vision have been directly applied to graph data, where the neighboring nodes are regarded as negatives and consequently pushed far apart from the anchor. However, this is contradictory with the homophily assumption of networks that connected nodes often belong to the same class and should be close to each other. In this work, we propose an end-to-end automatic GCL method, named NCLA to apply neighbor contrastive learning on learnable graph augmentation. Several graph augmented views with adaptive topology are automatically learned by the multi-head graph attention mechanism, which can be compatible with various graph datasets without prior domain knowledge. In addition, a neighbor contrastive loss is devised to allow multiple positives per anchor by taking network topology as the supervised signals. Both augmentations and embeddings are learned end-to-end in the proposed NCLA. Extensive experiments on the benchmark datasets demonstrate that NCLA yields the state-of-the-art node classification performance on self-supervised GCL and even exceeds the supervised ones, when the labels are extremely limited. Our code is released at https://github.com/shenxiaocam/NCLA.